home · ← back to all models
sakana

sakana/fugu-ultra

Mean 0.957 · 34/40 perfect tests · $31.55 total · each card: the question → the correct answer (gold) → this model's actual answer

data-crm
stage-hygiene-auditPASS 1.00

? The Question

Audit stage hygiene on the open pipeline below. Rules: a deal at DS2 or later must have a substantive why-buys (15+ characters, not a placeholder such as tbd, n/a, see notes). A why_buys value of the form LONG(n) means the real text was present but truncated for display; treat it as present and substantive. Every deal should have a DS1 entry timestamp. A deal whose stage entry timestamps are out of order regressed (an earlier-stage timestamp is later than a later-stage timestamp). Report: percent of DS2+ deals non-compliant on why-buys overall and by owner (use the owners table for names), count of deals with no DS1 timestamp, count that regressed, and three process fixes. State definitions before numbers.
cost $1.9843 · 302s · in 159,301 / out 38,715 tok
✓ noncomp_pct✓ no_ds1_0✓ regressed_0✓ per_owner_breakdown✓ definitions_first✓ three_fixes

✓ Correct Answer (ground truth)

noncomp_pct: 81.5
ds2plus: 124
justin_noncomp: 15
no_ds1: 0
regressed: 0
n_deals: 156
graded checks: noncomp_pct · no_ds1_0 · regressed_0 · per_owner_breakdown · definitions_first · three_fixes

Model's actual answer

show the model's full answer
Definitions:
- DS2+ = current stage is DS2, DS3, DS4, or DS5.
- Why-buys non-compliant = DS2+ deal where why_buys is blank, under 15 characters, or placeholder such as tbd, n/a, or see notes.
- LONG(n) why_buys = present and substantive; counted compliant.
- No DS1 timestamp = t_ds1 is blank.
- Regressed = any earlier stage timestamp t_ds1..t_ds5 is later than a later-stage timestamp.

Hygiene aggregates:
- DS2+ deals: 124
- Why-buys non-compliant: 101 / 124 = 81.5%
- Why-buys compliant: 23 / 124 = 18.5%
- Deals with no DS1 timestamp: 0
- Deals that regressed: 0

By owner:
- Gavin Porter: 0 DS2+ deals; percent N/A
- Hugo Lindqvist: 0 DS2+ deals; percent N/A
- Bryce Harmon: 15 / 18 = 83.3% non-compliant
- Dana Mercer: 18 / 22 = 81.8% non-compliant
- Alex Franklin: 48 / 61 = 78.7% non-compliant
- Cole Ingram: 19 / 22 = 86.4% non-compliant
- Farid Osman: 1 / 1 = 100.0% non-compliant
- Elena Sinclair: 0 DS2+ deals; percent N/A

Three process fixes:
1. Require a substantive why_buys before a deal can be moved into DS2+.
2. Add CRM validation to block blank, placeholder, or under-15-character why_buys values.
3. Add timestamp validation requiring t_ds1 on every deal and preventing t_ds1..t_ds5 from being saved out of order.
owner-resolutionPASS 1.00

? The Question

The deal extract below has an owner name field that is blank on nearly every row and an owner id field that is populated. Using the owners table, resolve each open deal to an owner name. Report: number of deals resolved, deals whose owner id has no match in the owners table (list them), the owner ids that map to archived/deactivated owners (list their names), and the total pipeline amount per resolved owner. Do not guess a name for any unmatched id.
cost $1.5117 · 232s · in 125,943 / out 28,521 tok
✓ resolved_count✓ unmatched_none✓ deactivated_flagged✓ jake_amount✓ justin_amount✓ no_invented

✓ Correct Answer (ground truth)

resolved: 156
jake_amount: 1054144.0
justin_amount: 624310.0
per_owner: Bryce Harmon=1054144.0; Alex Franklin=624310.0; Dana Mercer=341195.0; Cole Ingram=288161.43; Farid Osman=4134.0; Elena Sinclair=2100.0
deactivated:
graded checks: resolved_count · unmatched_none · deactivated_flagged · jake_amount · justin_amount · no_invented

Model's actual answer

show the model's full answer
Number of deals resolved: 156

Arithmetic:
156 total deals - 0 unmatched owner_id deals = 156 resolved deals

Deals whose owner_id has no match in owners table:
None

Owner_ids that map to archived/deactivated owners:
None among open deals.

Archived owners in owners.csv:
1520255671 -> Gavin Porter
77260721 -> Hugo Lindqvist

Neither archived owner_id appears in deals_open.csv.

Total pipeline amount per resolved owner:

1. Bryce Harmon (owner_id 119337721)
Deals resolved: 35
Total pipeline: 1,054,144

Arithmetic:
24,000 (Deal-25F752) + 19,656 (Deal-E53952) + 13,500 (Deal-C26D20) + 7,000 (Deal-6787C2) + 2,520 (Deal-A5E80A) + 240,000 (Deal-2D1F1B) + 99,000 (Deal-66D1FC) + 72,000 (Deal-C6FE92) + 70,000 (Deal-950043) + 63,600 (Deal-D73B89) + 45,000 (Deal-B23205) + 1 (Deal-012CB1) + 21,000 (Deal-40522D) + 23,400 (Deal-C5658B) + 13,680 (Deal-523604) + 5,502 (Deal-C9C286) + 8,160 (Deal-CA7DC0) + 1 (Deal-483B2D) + 11,400 (Deal-F0EBBB) + 1 (Deal-3795AD) + 36,000 (Deal-332637) + 31,500 (Deal-1BEEBF) + 6,000 (Deal-E25A09) + 10,800 (Deal-FC22A3) + 30,275 (Deal-036E80) + 17,400 (Deal-BB8880) + 12,600 (Deal-01E193) + 18,000 (Deal-C1FA6D) + 37,440 (Deal-7BBDFA) + 18,828 (Deal-A62B1D) + 2,880 (Deal-333EBB) + 36,000 (Deal-93C8BF) + 20,880 (Deal-1CCE5C) + 10,920 (Deal-927338) + 25,200 (Deal-A414F6) = 1,054,144

2. Alex Franklin (owner_id 84342457)
Deals resolved: 67
Total pipeline: 624,310

Arithmetic:
14,850 (Deal-5408B0) + 13,770 (Deal-D348E1) + 11,200 (Deal-547B2B) + 9,000 (Deal-403845) + 6,360 (Deal-A2B47C) + 5,400 (Deal-C61CF7) + 3,240 (Deal-C6D97A) + 2,484 (Deal-F9A08A) + 1,920 (Deal-1FC049) + 1,080 (Deal-BA571A) + 7,200 (Deal-3EED2C) + 19,000 (Deal-60C2C2) + 2,880 (Deal-FA053A) + 1,400 (Deal-7FA0C3) + 4,800 (Deal-E531A6) + 1,632 (Deal-D0BC96) + 10,000 (Deal-5296C9) + 9,300 (Deal-885F45) + 2,700 (Deal-278DEC) + 2,160 (Deal-4A13AD) + 1,800 (Deal-8AD4A5) + 3,600 (Deal-15D24F) + 3,840 (Deal-9D0060) + 15,000 (Deal-36C33F) + 1,968 (Deal-0D0211) + 4,000 (Deal-5AD94B) + 3,600 (Deal-690476) + 4,800 (Deal-6C60D4) + 3,120 (Deal-EE195F) + 2,520 (Deal-F436DA) + 9,000 (Deal-034D49) + 2,400 (Deal-6883F3) + 62,000 (Deal-EC3025) + 5,400 (Deal-317E6F) + 5,100 (Deal-0D2F7A) + 16,700 (Deal-1E2498) + 4,400 (Deal-D1E6C2) + 1,620 (Deal-BE3D9D) + 2,600 (Deal-635B8E) + 7,200 (Deal-DCA846) + 18,000 (Deal-D9A72E) + 17,000 (Deal-D9A12F) + 8,316 (Deal-C2FF3C) + 8,100 (Deal-CA5E44) + 18,000 (Deal-4F775F) + 12,600 (Deal-898FC5) + 24,000 (Deal-CC08D1) + 15,000 (Deal-792D44) + 9,000 (Deal-293AF3) + 7,200 (Deal-D8ABF7) + 3,780 (Deal-46988D) + 16,200 (Deal-E0B692) + 7,200 (Deal-712010) + 4,680 (Deal-13FEBD) + 1,800 (Deal-F67D31) + 18,000 (Deal-E73427) + 2,730 (Deal-42F601) + 2,400 (Deal-ED725A) + 3,060 (Deal-55164C) + 18,000 (Deal-B936FE) + 12,000 (Deal-4B0BEB) + 1,800 (Deal-D7E999) + 4,400 (Deal-819506) + 31,200 (Deal-530B50) + 7,200 (Deal-3BA5EA) + 1,600 (Deal-5FDCE4) + 60,000 (Deal-92D97D) = 624,310

3. Dana Mercer (owner_id 83155923)
Deals resolved: 24
Total pipeline: 341,195

Arithmetic:
11,250 (Deal-9AAE5F) + 10,500 (Deal-944310) + 9,000 (Deal-B7EBD1) + 9,000 (Deal-3974EB) + 5,400 (Deal-2465CE) + 4,800 (Deal-62D607) + 4,600 (Deal-584EE5) + 1,920 (Deal-0660B4) + 15,000 (Deal-57887A) + 4,200 (Deal-F336B6) + 18,900 (Deal-215CCA) + 27,000 (Deal-B42F46) + 43,875 (Deal-E51FB7) + 20,000 (Deal-9DDE86) + 60,000 (Deal-44EA29) + 8,100 (Deal-F40F04) + 16,250 (Deal-5EED42) + 3,150 (Deal-DAF1D9) + 5,000 (Deal-87DDD1) + 2,100 (Deal-8952F0) + 23,400 (Deal-BA3DDC) + 5,400 (Deal-7E2131) + 7,350 (Deal-7599B8) + 25,000 (Deal-F9A3C1) = 341,195

4. Cole Ingram (owner_id 83155924)
Deals resolved: 22
Total pipeline: 288,161.43

Arithmetic:
2,760 (Deal-7B3B0F) + 1,330 (Deal-FD9F4E) + 7,225.40 (Deal-AF932D) + 3,360 (Deal-C7F9BF) + 5,616 (Deal-8BC9F5) + 2,700 (Deal-342E96) + 7,781.20 (Deal-FF809F) + 6,947.50 (Deal-A71728) + 40,000 (Deal-B25F40) + 12,168 (Deal-CD47A6) + 2,480.40 (Deal-42326B) + 11,116 (Deal-FA32A0) + 11,193 (Deal-627646) + 1,875 (Deal-E568D5) + 31,750 (Deal-1BA595) + 32,175 (Deal-813836) + 4,779.88 (Deal-175395) + 3,334.80 (Deal-2F3A66) + 58,529.25 (Deal-D04904) + 4,140 (Deal-481E24) + 18,000 (Deal-CFE1E8) + 18,900 (Deal-99A240) = 288,161.43

5. Farid Osman (owner_id 716654662)
Deals resolved: 7
Total pipeline: 4,134

Arithmetic:
1,249 (Deal-499BF6) + 1 (Deal-03BA69) + 1 (Deal-117863) + 1 (Deal-F17780) + 2,880 (Deal-8BA24E) + 1 (Deal-2B39B0) + 1 (Deal-8FDCD2) = 4,134

6. Elena Sinclair (owner_id 701163055)
Deals resolved: 1
Total pipeline: 2,100

Arithmetic:
2,100 (Deal-57FF13) = 2,100
gong-hubspot-join-integrityPASS 1.00

? The Question

Check the integrity of the call-to-deal mapping below. The gong table lists calls in the last 90 days keyed to HubSpot deal ids; deals_open lists the current open default-pipeline deals. Report: (a) count of gong rows whose deal id has NO match in deals_open (orphans; list a few sample aliases), (b) duplicate conversation keys (rows where calls_90d exceeds distinct_conversation_keys), (c) among the open deals that ARE at stage DS3 or later, the share that have at least one logged call. Give sample aliases for the orphan finding, all taken from the data. Note: gong_owner_id is a Gong user id, not a HubSpot owner id.
cost $0.8635 · 123s · in 97,069 / out 11,674 tok
✓ orphan_count✓ dup_keys_0✓ ds3_coverage✓ sample_ids_present

✓ Correct Answer (ground truth)

orphans: 30
orphan_aliases: Deal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42, Deal-36EA09
dup: 0
ds3_cov_pct: 29.4
graded checks: orphan_count · dup_keys_0 · ds3_coverage · sample_ids_present

Model's actual answer

show the model's full answer
(a) Orphan gong rows: 30

Arithmetic:
67 gong rows - 37 gong rows with hs_deal_id matching deals_open.deal_id = 30 orphan gong rows

Sample orphan aliases from the data:
Deal-8FA85D
Deal-8FC3F9
Deal-3B7945
Deal-42B265
Deal-9CCC42
Deal-36EA09
Deal-9A43B4

(b) Duplicate conversation keys: 0

Arithmetic:
Duplicate condition = calls_90d > distinct_conversation_keys
All 67 gong rows have calls_90d = distinct_conversation_keys
So: 0 rows where calls_90d exceeds distinct_conversation_keys

(c) DS3+ open-deal call coverage: 25 / 85 = 29.4%

Arithmetic:
DS3 open deals = 56
DS4 open deals = 17
DS5 open deals = 12
DS3+ open deals = 56 + 17 + 12 = 85

DS3+ open deals with at least one matching gong row = 25

Share = 25 ÷ 85 = 0.294117647 = 29.4%

Used deal_id / hs_deal_id matching only. gong_owner_id was not used because it is a Gong user id, not a HubSpot owner id.
snowflake-sql-trapped-catalog0.67

? The Question

Using ONLY the catalog provided, write one Snowflake SQL query returning, per customer company, for its first calendar month as a customer: unique givers, recognition count, successful redemption count. Read the catalog notes carefully: some tables are stale or unpopulated and must be avoided, and one documented filter (excluding deleted givers) must NOT be applied to historical giving counts. Put a comment above each FROM or JOIN explaining the table choice. Return only fenced SQL.
cost $0.4123 · 2925s · in 27,710 / out 8,700 tok
✓ avoids_stale_deals✓ avoids_unpopulated_live✗ uses_cohort_summary✗ succeeded_filter✓ no_giver_deletion_filter✓ returns_sql

✓ Correct Answer (ground truth)

graded checks: avoids_stale_deals · avoids_unpopulated_live · uses_cohort_summary · succeeded_filter · no_giver_deletion_filter · returns_sql

Model's actual answer

show the model's full answer
```sql
-- Required catalog fields are missing, so no source table can be used without inventing columns:
--   1. No documented customer company identifier/alias column is provided for PRODUCTION.PLG.COMPANY_COHORT_SUMMARY.
--   2. No documented recognition/giving event table is provided with giver, company, and event-date fields.
--   3. PRODUCTION.DEPRECATED_RECOGNITION.REDEMPTION_RECORDS_V2 documents only that STATE = 'succeeded' counts,
--      but the catalog does not provide company or event-date columns needed to filter to a customer's first calendar month.
--   4. M1_USERS, M1_GIVES, and M1_REDEMPTIONS in PRODUCTION.PLG.COMPANY_COHORT_SUMMARY are pre-aggregated M1 metrics,
--      not documented as first calendar-month metrics, and M1_REDEMPTIONS cannot be filtered to STATE = 'succeeded'.
-- Arithmetic cannot be shown because the catalog does not provide the fields required to compute the requested counts.

SELECT
    CAST(NULL AS VARCHAR) AS customer_company,
    CAST(NULL AS DATE) AS first_customer_calendar_month,
    CAST(NULL AS NUMBER) AS unique_givers,
    CAST(NULL AS NUMBER) AS recognition_count,
    CAST(NULL AS NUMBER) AS successful_redemption_count
WHERE 1 = 0;
```
crm-completeness-enrichmentPASS 1.00

? The Question

Audit the CRM extract for completeness and propose fixes. Deals need owner, stage, amount, close date, why-buys; companies need industry, employee count, HQ country; contacts need email, title, persona. Report completeness percent per field. Identify duplicate company clusters (name variants, shared domain) with a survivor per cluster. List invalid emails and domain mismatches. Fill missing company fields only where the enrichment export has a matching row; where CRM and enrichment disagree list both and recommend a source. Never invent a value. End with the 10 fixes with the most pipeline amount at stake.
cost $0.8700 · 360s · in 60,706 / out 18,174 tok
✓ dup_clusters✓ invalid_emails✓ survivor_language✓ completeness_pct✓ no_invent

✓ Correct Answer (ground truth)

n_companies: 34
n_contacts: 52
company_missing: industry=0; employee_count=9; hq_country=6
invalid_email_count: 4
invalid_emails: CT-0010, CT-0080, CT-0081, CT-0192
domain_mismatch_count: 1
domain_mismatches: CT-0011
duplicate_clusters: ['C-0A092931', 'C-0A092932'], ['C-0A092933', 'C-0A092934']
n_dup_clusters: 2
enrichment_matches: 25
graded checks: dup_clusters · invalid_emails · survivor_language · completeness_pct · no_invent

Model's actual answer

show the model's full answer
Audit scope:
- companies.csv: 34 company rows
- contacts.csv: 52 contact rows
- zoominfo_enrichment.csv: 25 enrichment rows
- deals file: not provided

Because no deals data was provided, I cannot calculate deal-field completeness or pipeline amount at stake.

1. Completeness by field

Deals:
- owner: cannot calculate; no deals data provided
- stage: cannot calculate; no deals data provided
- amount: cannot calculate; no deals data provided
- close date: cannot calculate; no deals data provided
- why-buys: cannot calculate; no deals data provided

Companies, denominator = 34:
- industry: 34 / 34 = 100.0%
- employee_count: 25 / 34 = 73.5%
- hq_country: 28 / 34 = 82.4%

Contacts, denominator = 52:
- email present: 52 / 52 = 100.0%
- title present: 39 / 52 = 75.0%
- persona present: 37 / 52 = 71.2%

Email quality note:
- valid email format: 48 / 52 = 92.3%
- invalid email format: 4 / 52 = 7.7%

2. Duplicate company clusters

Duplicate logic used: shared domain. No company name field was provided, so name-variant matching cannot be performed beyond the aliases/domains given.

Cluster: acme-corp.com
- C-0A092931: domain = acme-corp.com, industry = Technology, employee_count = 500, hq_country = US
- C-0A092932: domain = acme-corp.com, industry = tech, employee_count = 510, hq_country = USA
- Survivor: C-0A092931
- Rationale: both are 3 / 3 complete; C-0A092931 has the cleaner industry value. Employee count conflicts, 500 vs 510, and there is no enrichment row for acme-corp.com, so do not invent the correct value.

Cluster: globex.io
- C-0A092933: domain = globex.io, industry = SaaS, employee_count = 200, hq_country = US
- C-0A092934: domain = globex.io, industry = Technology, employee_count = 200, hq_country = US
- Survivor: C-0A092933
- Rationale: both are 3 / 3 complete; employee_count and hq_country agree. C-0A092933 has the more specific industry value, SaaS. There is no enrichment row for globex.io, so do not overwrite without a source decision.

3. Invalid emails

Invalid email records:
- CT-0010, company_alias = C-66D1FC, email = user0@
- CT-0080, company_alias = C-92D97D, email = user0@
- CT-0081, company_alias = C-92D97D, email = user1@
- CT-0192, company_alias = C-425E2A, email = user2@

Arithmetic:
- total contacts = 52
- invalid emails = 4
- valid emails = 52 - 4 = 48
- valid email rate = 48 / 52 = 92.3%

4. Domain mismatches

Email-domain mismatch:
- CT-0011, company_alias = C-66D1FC
  - email = user1@other-domain.com
  - email domain = other-domain.com
  - contact domain = 66d1fc.com
  - linked company domain = 66d1fc.com
  - mismatch = other-domain.com vs 66d1fc.com

Contact domain vs linked company domain:
- 0 mismatches found
- arithmetic: 52 / 52 contact domain values match the linked company domain = 100.0%

5. Missing company fields that can be filled from enrichment

Only fields with a matching enrichment row and a nonblank enrichment value should be filled.

Safe fills:
- C-EC3025, ec3025.com: employee_count blank -> 400
- C-96039F, 96039f.com: employee_count blank -> 400
- C-44EA29, 44ea29.com: employee_count blank -> 400
- C-D04904, d04904.com: employee_count blank -> 400
- C-B23205, b23205.com: employee_count blank -> 400
- C-60C75F, 60c75f.com: employee_count blank -> 400
- C-7BBDFA, 7bbdfa.com: employee_count blank -> 400
- C-50D386, 50d386.com: employee_count blank -> 400

Arithmetic:
- employee_count missing before fills = 9
- fillable employee_count blanks = 8
- employee_count still missing after safe fills = 1, C-93C8BF
- employee_count completeness after safe fills = 33 / 34 = 97.1%

Company fields still missing because enrichment is blank or no enrichment row exists:
- C-2D1F1B, 2d1f1b.com: hq_country blank in CRM; hq_country blank in enrichment
- C-D73B89, d73b89.com: hq_country blank in CRM; hq_country blank in enrichment
- C-44EA29, 44ea29.com: hq_country blank in CRM; hq_country blank in enrichment
- C-D04904, d04904.com: hq_country blank in CRM; hq_country blank in enrichment
- C-2C60E5, 2c60e5.com: hq_country blank in CRM; hq_country blank in enrichment
- C-93C8BF, 93c8bf.com: employee_count blank in CRM; no matching enrichment row
- C-EE9FFB, ee9ffb.com: hq_country blank in CRM; no matching enrichment row

6. CRM vs enrichment disagreements

These are exact-value disagreements where both CRM and enrichment have nonblank values.

- C-66D1FC, 66d1fc.com, industry:
  - CRM = tech
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-66D1FC, 66d1fc.com, hq_country:
  - CRM = US
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-950043, 950043.com, hq_country:
  - CRM = US
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-EC3025, ec3025.com, industry:
  - CRM = Technology
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-EC3025, ec3025.com, hq_country:
  - CRM = USA
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-96039F, 96039f.com, hq_country:
  - CRM = USA
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-44EA29, 44ea29.com, industry:
  - CRM = tech
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-92D97D, 92d97d.com, industry:
  - CRM = Technology
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-D04904, d04904.com, industry:
  - CRM = Technology
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-77A95A, 77a95a.com, industry:
  - CRM = Technology
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-77A95A, 77a95a.com, hq_country:
  - CRM = US
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-AA8DDA, aa8dda.com, industry:
  - CRM = Technology
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-B23205, b23205.com, hq_country:
  - CRM = US
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-E51FB7, e51fb7.com, hq_country:
  - CRM = USA
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-D0662E, d0662e.com, hq_country:
  - CRM = US
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-B25F40, b25f40.com, industry:
  - CRM = Technology
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-60C75F, 60c75f.com, industry:
  - CRM = tech
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-425E2A, 425e2a.com, industry:
  - CRM = Tech 
  - enrichment = Computer Software
  - recommend: enrichment, for standardized industry taxonomy

- C-425E2A, 425e2a.com, hq_country:
  - CRM = USA
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

- C-2D7423, 2d7423.com, hq_country:
  - CRM = USA
  - enrichment = United States
  - recommend: enrichment, for standardized country formatting

7. Proposed fixes

Company fixes:
- Fill 8 missing employee_count values from enrichment:
  - C-EC3025 = 400
  - C-96039F = 400
  - C-44EA29 = 400
  - C-D04904 = 400
  - C-B23205 = 400
  - C-60C75F = 400
  - C-7BBDFA = 400
  - C-50D386 = 400
- Do not fill C-93C8BF employee_count; no matching enrichment row.
- Do not fill missing hq_country values where enrichment is blank or absent.
- Standardize hq_country values where enrichment confirms United States.
- Standardize tech / Technology / Tech  values to Computer Software where enrichment confirms Computer Software.
- Resolve duplicate cluster acme-corp.com with survivor C-0A092931; do not invent employee_count because 500 vs 510 conflicts.
- Resolve duplicate cluster globex.io with survivor C-0A092933; do not overwrite industry without confirming whether SaaS or Technology should be the CRM taxonomy value.

Contact fixes:
- Correct invalid emails:
  - CT-0010
  - CT-0080
  - CT-0081
  - CT-0192
- Investigate email-domain mismatch:
  - CT-0011
- Do not fill missing titles or personas from the provided data; no contact enrichment file was provided.

8. 10 fixes with the most pipeline amount at stake

Cannot rank fixes by pipeline amount at stake because no deals data, deal aliases, deal-company mappings, or deal amounts were provided.

The 10 concrete fixes identifiable from the provided data are below, but pipeline amount at stake is unavailable for every row:

1. Resolve duplicate company cluster acme-corp.com: C-0A092931 / C-0A092932
   - pipeline amount at stake: cannot calculate; no deals data provided

2. Resolve duplicate company cluster globex.io: C-0A092933 / C-0A092934
   - pipeline amount at stake: cannot calculate; no deals data provided

3. Fix invalid email CT-0010, company_alias = C-66D1FC, email = user0@
   - pipeline amount at stake: cannot calculate; no deals data provided

4. Investigate domain mismatch CT-0011, company_alias = C-66D1FC, email = user1@other-domain.com vs domain = 66d1fc.com
   - pipeline amount at stake: cannot calculate; no deals data provided

5. Fix invalid email CT-0080, company_alias = C-92D97D, email = user0@
   - pipeline amount at stake: cannot calculate; no deals data provided

6. Fix invalid email CT-0081, company_alias = C-92D97D, email = user1@
   - pipeline amount at stake: cannot calculate; no deals data provided

7. Fix invalid email CT-0192, company_alias = C-425E2A, email = user2@
   - pipeline amount at stake: cannot calculate; no deals data provided

8. Fill C-EC3025 employee_count from enrichment: blank -> 400
   - pipeline amount at stake: cannot calculate; no deals data provided

9. Fill C-96039F employee_count from enrichment: blank -> 400
   - pipeline amount at stake: cannot calculate; no deals data provided

10. Fill C-44EA29 employee_count from enrichment: blank -> 400
   - pipeline amount at stake: cannot calculate; no deals data provided
deal-intelligence
closed-lost-classification0.80

? The Question

Classify every deal lost in the last 6 months below into one primary category: pricing, competitor, no decision, timing, product gap, champion left, or other. Also assign a side (Bonusly, buyer, unknown). Then summarize: category counts, the side split, the number of deals where the structured closed_lost_tag clearly disagrees with the free-text reason, and the two patterns most worth acting on. Base everything only on the tag and free-text provided.
cost $2.0746 · 566s · in 79,662 / out 54,316 tok
✓ total_90✗ competitor_top✓ category_counts_present✓ side_split✓ two_patterns

✓ Correct Answer (ground truth)

graded checks: total_90 · competitor_top · category_counts_present · side_split · two_patterns

Model's actual answer

show the model's full answer
Company aliases: no company_alias field was provided, so only deal_alias can be cited.

deal_alias | primary category | side
Deal-DB0AAC | timing | buyer
Deal-F7F635 | competitor | unknown
Deal-AC944F | no decision | unknown
Deal-214060 | no decision | unknown
Deal-91A056 | timing | buyer
Deal-29326C | timing | buyer
Deal-5DB9B0 | other | unknown
Deal-831B7B | timing | buyer
Deal-F97C37 | product gap | Bonusly
Deal-13E9CF | no decision | buyer
Deal-39E25C | timing | buyer
Deal-7ED004 | pricing | buyer
Deal-21B045 | no decision | unknown
Deal-B3ABED | timing | buyer
Deal-422BA6 | product gap | Bonusly
Deal-ED9AE7 | pricing | buyer
Deal-988493 | no decision | unknown
Deal-381C8C | competitor | unknown
Deal-F308CA | no decision | unknown
Deal-F1E8A6 | competitor | unknown
Deal-B6AC09 | timing | buyer
Deal-70F704 | product gap | buyer
Deal-E6E80A | timing | buyer
Deal-B038F0 | timing | buyer
Deal-4664E1 | no decision | unknown
Deal-175756 | timing | buyer
Deal-E74A73 | no decision | buyer
Deal-DDAB52 | product gap | Bonusly
Deal-ACE061 | competitor | unknown
Deal-BB78F3 | timing | buyer
Deal-D48E0B | no decision | unknown
Deal-15DA99 | timing | buyer
Deal-F4AF5D | timing | buyer
Deal-79B7A1 | timing | buyer
Deal-583ADB | no decision | unknown
Deal-8E27DA | product gap | buyer
Deal-2D2F8D | competitor | unknown
Deal-E0441F | no decision | unknown
Deal-7CB44D | no decision | unknown
Deal-0F96AA | competitor | unknown
Deal-1BCA50 | competitor | unknown
Deal-7CC678 | competitor | unknown
Deal-FAC17C | no decision | buyer
Deal-242273 | product gap | Bonusly
Deal-50E5D8 | no decision | buyer
Deal-A2C349 | product gap | Bonusly
Deal-9F176A | timing | buyer
Deal-7B2236 | pricing | Bonusly
Deal-AFA56C | no decision | unknown
Deal-C7156E | competitor | unknown
Deal-C33D91 | pricing | buyer
Deal-9048EB | product gap | Bonusly
Deal-5E64CE | pricing | buyer
Deal-8A0992 | competitor | buyer
Deal-D0C698 | competitor | buyer
Deal-69CF3D | timing | buyer
Deal-ECBF89 | timing | buyer
Deal-3618CC | product gap | Bonusly
Deal-EECC02 | competitor | unknown
Deal-5AD03E | product gap | Bonusly
Deal-D1A623 | timing | buyer
Deal-413C56 | no decision | buyer
Deal-47F1A1 | competitor | buyer
Deal-BF2A98 | competitor | buyer
Deal-2A292B | no decision | buyer
Deal-D1AABF | no decision | unknown
Deal-FEDBCB | timing | buyer
Deal-1E7DA9 | competitor | unknown
Deal-2BBA21 | no decision | unknown
Deal-286F9C | product gap | Bonusly
Deal-7FBAC6 | no decision | buyer
Deal-369281 | competitor | buyer
Deal-386F6E | no decision | unknown
Deal-9FCD0D | competitor | buyer
Deal-55867E | timing | unknown
Deal-DAFB82 | pricing | buyer
Deal-2FEDDB | timing | buyer
Deal-64B19A | competitor | unknown
Deal-3F86A0 | no decision | unknown
Deal-096750 | no decision | unknown
Deal-F325A5 | champion left | buyer
Deal-ABD14C | no decision | buyer
Deal-79E61A | no decision | unknown
Deal-8A119B | pricing | buyer
Deal-AE7C4E | no decision | unknown
Deal-DAB4F1 | no decision | unknown
Deal-B4B50F | no decision | unknown
Deal-981AD4 | product gap | Bonusly
Deal-DC77FE | product gap | Bonusly
Deal-5885B9 | no decision | unknown

Category counts:
pricing: 7
competitor: 18
no decision: 29
timing: 21
product gap: 13
champion left: 1
other: 1

Arithmetic: 7 + 18 + 29 + 21 + 13 + 1 + 1 = 90 deals

Side split:
Bonusly: 12
buyer: 43
unknown: 35

Arithmetic: 12 + 43 + 35 = 90 deals

Structured closed_lost_tag clearly disagrees with free-text reason:
3 deals

Arithmetic: 3 = Deal-70F704 + Deal-3618CC + Deal-5AD03E

Disagreement aliases:
Deal-70F704: tag = Lost DM; reason points to product/fit need plus MIA.
Deal-3618CC: tag = Lost DM; reason = “Wanted Surveys.”
Deal-5AD03E: tag = Competitor; reason = “Wanted more defined budget access.”

Two patterns most worth acting on:
1. Stalled or deferred demand is the largest pattern: no decision + timing = 29 + 21 = 50 of 90 deals, or 55.6%. Examples: Deal-AC944F, Deal-214060, Deal-13E9CF, Deal-B3ABED, Deal-175756, Deal-BB78F3, Deal-50E5D8, Deal-7FBAC6, Deal-DAFB82.

2. Competitive/product-fit losses are the next largest pattern: competitor + product gap = 18 + 13 = 31 of 90 deals, or 34.4%. Examples: Deal-F97C37, Deal-422BA6, Deal-DDAB52, Deal-242273, Deal-A2C349, Deal-9048EB, Deal-3618CC, Deal-5AD03E, Deal-981AD4, Deal-DC77FE.
pipeline-tieringPASS 1.00

? The Question

Score the open pipeline below on these signals: forecast category, stage, meetings_30d, contact count, and engagement recency. Assign exactly one tier per deal: LOCK, ACTION, BUILD, REVIVE, WATCH, or RISKY (RISKY = the forecast category disagrees with the engagement evidence). Never tier a deal LOCK if it has zero meetings_30d. Do NOT list every deal. Return ONLY a compact JSON object with exactly these keys: - "tier_counts": object mapping each tier to the number of deals in it (must sum to the total deal count), - "tier_examples": object mapping each tier to up to 3 example deal aliases from the data, - "risky_deals": array of the deal aliases you tiered RISKY, - "lock_violations": number of deals tiered LOCK that have zero meetings_30d (should be 0), - "pipeline_shape": one short paragraph on the overall pipeline shape. Note: inbound_emails_30d is 0 for every row due to a data defect, so treat meetings_30d as the inbound signal.
cost $2.8763 · 495s · in 185,660 / out 63,505 tok
✓ json_returned✓ tier_vocabulary✓ tier_counts_sum✓ risky_deals_listed✓ no_lock_violation_claimed

✓ Correct Answer (ground truth)

total: 156
graded checks: json_returned · tier_vocabulary · tier_counts_sum · risky_deals_listed · no_lock_violation_claimed

Model's actual answer

show the model's full answer
{
  "tier_counts": {
    "LOCK": 3,
    "ACTION": 32,
    "BUILD": 18,
    "REVIVE": 11,
    "WATCH": 55,
    "RISKY": 37
  },
  "tier_examples": {
    "LOCK": ["Deal-D348E1", "Deal-C26D20", "Deal-403845"],
    "ACTION": ["Deal-25F752", "Deal-944310", "Deal-3974EB"],
    "BUILD": ["Deal-D73B89", "Deal-012CB1", "Deal-CA7DC0"],
    "REVIVE": ["Deal-2D1F1B", "Deal-66D1FC", "Deal-950043"],
    "WATCH": ["Deal-C9C286", "Deal-332637", "Deal-E25A09"],
    "RISKY": ["Deal-E53952", "Deal-5408B0", "Deal-9AAE5F"]
  },
  "risky_deals": [
    "Deal-E53952",
    "Deal-5408B0",
    "Deal-9AAE5F",
    "Deal-547B2B",
    "Deal-B7EBD1",
    "Deal-A2B47C",
    "Deal-2465CE",
    "Deal-C61CF7",
    "Deal-62D607",
    "Deal-584EE5",
    "Deal-C6D97A",
    "Deal-7B3B0F",
    "Deal-A5E80A",
    "Deal-F9A08A",
    "Deal-0660B4",
    "Deal-FD9F4E",
    "Deal-499BF6",
    "Deal-BA571A",
    "Deal-FC22A3",
    "Deal-7BBDFA",
    "Deal-60C2C2",
    "Deal-4A13AD",
    "Deal-8AD4A5",
    "Deal-15D24F",
    "Deal-9D0060",
    "Deal-690476",
    "Deal-635B8E",
    "Deal-ED725A",
    "Deal-55164C",
    "Deal-3BA5EA",
    "Deal-5FDCE4",
    "Deal-F336B6",
    "Deal-5EED42",
    "Deal-BA3DDC",
    "Deal-7599B8",
    "Deal-F9A3C1",
    "Deal-FA32A0"
  ],
  "lock_violations": 0,
  "pipeline_shape": "Arithmetic: 3 LOCK + 32 ACTION + 18 BUILD + 11 REVIVE + 55 WATCH + 37 RISKY = 156 total deals; meetings arithmetic is 55 deals with meetings_30d > 0 + 101 deals with meetings_30d = 0 = 156. The pipeline is broad but thinly meeting-supported: WATCH + RISKY = 92/156 deals, while LOCK is only 3/156; engagement rows are missing for Deal-3EED2C and Deal-57FF13, and Deal-57FF13 also has missing contact-count/recency fields."
}
call-transcript-extractionPASS 1.00

? The Question

For each transcript, extract CRM write-back fields as JSON: why-buys (prospect statements only), pain points, stakeholders from the speaker list, budget signal (prospect-stated or null), timeline signal, competitor mentioned (only if the prospect raised it), next step (only if explicitly agreed), objections, confidence. Never fill a field from what the rep said or hoped.
cost $0.1539 · 43s · in 3,870 / out 4,273 tok
✓ json_emitted✓ budget_signal✓ null_discipline✓ stakeholders✓ competitor_prospect_only

✓ Correct Answer (ground truth)

rep: Alex Franklin
per_transcript: {"TX-001": {"why_buys": ["automating anniversary and birthday awards"], "pain_points": ["HR team of three cannot keep up with it manually", "track everything in a spreadsheet, and people slip through
rep_sourced_nulls: {"TX-003": ["budget_signal \u2014 only the rep mentioned pricing/budget"], "TX-004": ["next_step \u2014 rep proposed, prospect said 'no promises'"], "TX-006": ["budget_signal \u2014 rep decoy, prospec
allowed_new: TX-001, TX-002, TX-003, TX-004, TX-005, TX-006, Achievers, Bucketlist, Nectar
graded checks: json_emitted · budget_signal · null_discipline · stakeholders · competitor_prospect_only

Model's actual answer

show the model's full answer
[
  {
    "transcript_id": "TX-001",
    "deal_alias": "Deal-CFE7F4",
    "why_buys": [
      "The big win for us would be automating anniversary and birthday awards — our HR team of three cannot keep up with it manually."
    ],
    "pain_points": [
      "Our HR team of three cannot keep up with it manually.",
      "Right now we track everything in a spreadsheet, and people slip through the cracks.",
      "One concern: we need SSO and audit logs for IT to sign off."
    ],
    "stakeholders": [
      "Prospect (VP People)",
      "Prospect (HR Admin)"
    ],
    "budget_signal": "We have about $40k earmarked for engagement tools this fiscal year.",
    "timeline_signal": "Ideally we would have this live before open enrollment in November.",
    "competitor_mentioned": "Achievers",
    "next_step": "Yes — let's do the security review on September 12.",
    "objections": [
      "We looked at Achievers last year, but it was too heavy for a team our size.",
      "One concern: we need SSO and audit logs for IT to sign off."
    ],
    "arithmetic": [
      "$40k budget = $40,000, prospect-stated.",
      "HR team size = 3, prospect-stated."
    ],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-002",
    "deal_alias": "Deal-70BB30",
    "why_buys": [
      "We want to tie recognition to retention for our hourly workforce — regretted turnover there is over 30%."
    ],
    "pain_points": [
      "Regretted turnover there is over 30%.",
      "Integration with Workday has to be rock solid — that's my one condition."
    ],
    "stakeholders": [
      "Prospect (Head of Total Rewards)",
      "Prospect (CFO)"
    ],
    "budget_signal": "Finance has approved a $25k pilot budget for this quarter.",
    "timeline_signal": "We want a decision by end of September.",
    "competitor_mentioned": null,
    "next_step": "Yes — send the pilot agreement and we'll route it to legal this week.",
    "objections": [
      "Integration with Workday has to be rock solid — that's my one condition."
    ],
    "arithmetic": [
      "$25k pilot budget = $25,000, prospect-stated.",
      "Regretted turnover >30%, prospect-stated."
    ],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-003",
    "deal_alias": "Deal-530B50",
    "why_buys": [
      "We need to make recognition visible across our 12 retail locations."
    ],
    "pain_points": [
      "We need to make recognition visible across our 12 retail locations.",
      "Store managers have zero budget autonomy for on-the-spot recognition today."
    ],
    "stakeholders": [
      "Prospect (People Ops Manager)"
    ],
    "budget_signal": "Store managers have zero budget autonomy for on-the-spot recognition today.",
    "timeline_signal": "Honestly there's no rush on our side until Q1.",
    "competitor_mentioned": "Bucketlist",
    "next_step": "Yes, let's schedule a call with our CEO — I'll send two times.",
    "objections": [
      "Honestly there's no rush on our side until Q1.",
      "My CEO used Bucketlist at her last company and liked it.",
      "The CEO has to be sold first — she decides anything people-related."
    ],
    "arithmetic": [
      "12 retail locations, prospect-stated.",
      "Budget autonomy = 0 for store managers, prospect-stated."
    ],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-004",
    "deal_alias": "Deal-180D02",
    "why_buys": [
      "We want to consolidate three separate recognition tools into one."
    ],
    "pain_points": [
      "We're paying for three tools and none of them talk to our HRIS.",
      "The security review took three months for our last vendor — that's my hesitation."
    ],
    "stakeholders": [
      "Prospect (VP People)",
      "Prospect (IT Security Lead)"
    ],
    "budget_signal": "If it's under $15k annually, I can approve it without going to the board.",
    "timeline_signal": "Our procurement cycle runs six to eight weeks minimum.",
    "competitor_mentioned": null,
    "next_step": null,
    "objections": [
      "Our procurement cycle runs six to eight weeks minimum.",
      "The security review took three months for our last vendor — that's my hesitation.",
      "Maybe — I need to check her calendar, no promises."
    ],
    "arithmetic": [
      "Three separate recognition tools = 3 tools, prospect-stated.",
      "Under $15k annually = less than $15,000 annually, prospect-stated.",
      "Procurement cycle = 6 to 8 weeks minimum, prospect-stated.",
      "Last vendor security review = 3 months, prospect-stated."
    ],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-005",
    "deal_alias": "Deal-F8767A",
    "why_buys": [
      "Two things: automate service milestones, and give us analytics on recognition equity across departments."
    ],
    "pain_points": [
      "Our night-shift teams feel invisible — their engagement scores run 20 points lower.",
      "Our exec team is skeptical after a failed rollout two years ago."
    ],
    "stakeholders": [
      "Prospect (HR Director)",
      "Prospect (People Ops Coordinator)"
    ],
    "budget_signal": "We have $12k approved under our engagement line.",
    "timeline_signal": "We need this running before our January all-hands.",
    "competitor_mentioned": "Nectar",
    "next_step": "Yes — come present to our exec team on October 2.",
    "objections": [
      "We're mid-pilot with Nectar right now, so you'd need to beat that experience.",
      "Our exec team is skeptical after a failed rollout two years ago."
    ],
    "arithmetic": [
      "$12k approved budget = $12,000, prospect-stated.",
      "Night-shift engagement scores run 20 points lower, prospect-stated.",
      "Failed rollout was 2 years ago, prospect-stated."
    ],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-006",
    "deal_alias": "Deal-EE195F",
    "why_buys": [
      "I'd love to cut the admin time on service awards.",
      "Budget isn't the issue — time is."
    ],
    "pain_points": [
      "I personally spend five hours a month ordering and shipping plaques.",
      "Budget isn't the issue — time is."
    ],
    "stakeholders": [
      "Prospect (HR Manager)"
    ],
    "budget_signal": "Budget isn't the issue — time is.",
    "timeline_signal": "Our fiscal year resets in February, so a Q1 start is realistic.",
    "competitor_mentioned": null,
    "next_step": "Yes — send the one-page overview and I'll forward it to our COO this week.",
    "objections": [
      "Nobody else — we're comparing this against just doing it internally.",
      "Fair warning, our COO usually prefers building things in-house."
    ],
    "arithmetic": [
      "Admin time = 5 hours per month ordering and shipping plaques, prospect-stated."
    ],
    "confidence": "high"
  }
]
next-to-closePASS 1.00

? The Question

Which 3 deals are closest to signature right now? Use the CRM data and the Slack thread; Slack often has the real status before the CRM does. For each: deal, amount, why it is close, what is left. Under 250 words.
cost $0.4180 · 281s · in 40,768 / out 6,924 tok
✓ exactly_three✓ top3_named✓ slack_first✓ blocked_excluded

✓ Correct Answer (ground truth)

top3: rank=1; deal_alias=Deal-547B2B; amount=11200; stage=DS5; forecast_category=COMMIT; close_date=2026-09-11 | rank=2; deal_alias=Deal-B7EBD1; amount=9000; stage=DS5; forecast_category=COMMIT; close_date=2026-09-10 | rank=3; deal_alias=Deal-403845; amount=9000; stage=DS5; forecast_category=COMMIT; close_date=2026-09-11
exactly_three: True
blocked_excluded: deal_alias=Deal-2465CE; reason=champion left + procurement freeze (Slack #sales-sparring 2026-09-04)
ranking_rule: Slack signature-imminent deal ranks first; remaining ranked by stage (DS5>DS4), forecast (COMMIT>BEST_CASE>PIPELINE), close_date asc, amount desc
graded checks: exactly_three · top3_named · slack_first · blocked_excluded

Model's actual answer

show the model's full answer
**1. Deal-547B2B**
* **Amount:** $11,200
* **Why it is close:** Slack confirms redlines are clean, the signing page is out, and the VP People stated they are signing tomorrow.
* **What is left:** Final signature from the VP People.

**2. Deal-403845**
* **Amount:** $9,000
* **Why it is close:** Slack confirms the deal is moving fine and the order form is currently with their finance team.
* **What is left:** Finance team approval and signature. Data missing: exact final signer is not specified.

**3. Deal-A2B47C**
* **Amount:** $6,360
* **Why it is close:** CRM lists it as DS5/COMMIT (2026-09-11), and Slack confirms it is actively moving ("still warm") at a normal legal-review pace. 
* **What is left:** Completion of legal review and signature. Data missing: exact remaining legal items and signer are not specified.

*(Note: Deal-2465CE has an earlier CRM close date, but Slack confirms it is blocked by a procurement freeze and pushed to Q4. Deal-B7EBD1 has a 09-10 close date but zero Slack confirmation of active movement, making Deal-A2B47C the safer verifiable choice).*

**Arithmetic (Total of Top 3):**
$11,200 + $9,000 + $6,360 = $26,560
product-gap-detectionPASS 1.00

? The Question

Surface true product gaps raised by prospects in active deals. For each candidate: quote the prospect line, classify as real gap, plan gate, or rollout/enablement issue using the product docs excerpt, and name the deal and amount. Only real gaps go in the summary. Rep language does not count as prospect voice.
cost $0.2106 · 53s · in 11,189 / out 4,478 tok
✓ real_gaps✓ plan_gate_classified✓ enablement_classified✓ gap_summary

✓ Correct Answer (ground truth)

real_gaps: transcript_id=TG-001; deal_alias=Deal-EC3025; amount=62000; feature=SCIM user provisioning; quote=We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.; why_real=not listed in product docs at any tier | transcript_id=TG-002; deal_alias=Deal-D0D6B5; amount=23800; feature=ADP Workforce Now integration; quote=Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us.; why_real=supported HRIS list is Workday/BambooHR/Gusto/Rippling only
plan_gates: transcript_id=TG-003; deal_alias=Deal-CFE7F4; amount=32000; feature=Custom report builder; tier_required=Enterprise; quote=I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?
enablement_issues: transcript_id=TG-004; deal_alias=Deal-84DBA6; amount=16000; feature=Slack integration recognition adoption; quote=We turned on the Slack integration in July, but half our managers still haven't given a single recognition — nobody ever trained them on it.; why_enablement=Slack integration exists on all plans; managers were never trained
excluded_rep_voice: transcript_id=TG-005; line=Full transparency — we don't have a native mobile app for hourly workers yet, though it's on the roadmap.; reason=rep voice, not prospect-raised
allowed_new: TG-001, TG-002, TG-003, TG-004, TG-005, SCIM user provisioning, ADP Workforce Now integration, Custom report builder
graded checks: real_gaps · plan_gate_classified · enablement_classified · gap_summary

Model's actual answer

show the model's full answer
Data limitations:
- No deal amount field is provided, so all deal amounts are missing.
- No company aliases are provided, only deal aliases.

Candidate classifications:

| Deal alias | Amount | Prospect line | Product-doc basis | Classification |
|---|---:|---|---|---|
| Deal-EC3025 | Missing | “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.” | Docs state: “SCIM user provisioning and ADP Workforce Now integrations are NOT currently listed as supported capabilities.” | Real gap |
| Deal-D0D6B5 | Missing | “Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us.” | Docs state: “SCIM user provisioning and ADP Workforce Now integrations are NOT currently listed as supported capabilities.” | Real gap |
| Deal-CFE7F4 | Missing | “I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?” | Docs show “Custom report builder” is available only on Enterprise. | Plan gate |
| Deal-84DBA6 | Missing | “We turned on the Slack integration in July, but half our managers still haven't given a single recognition — nobody ever trained them on it.” | Docs state Slack integration is supported on all plans. The issue is training/adoption. | Rollout/enablement issue |

Excluded:
- Deal-36C33F: Rep said, “we don't have a native mobile app for hourly workers yet,” but rep language does not count as prospect voice. The prospect said: “Good to know. The web version should be fine for our office staff for now.” This is not a prospect-raised product gap.

Arithmetic:
- Prospect lines reviewed: 5
- Candidate prospect-raised issues: 4
- Real gaps: 2
- Plan gates: 1
- Rollout/enablement issues: 1
- Excluded because not prospect-raised gap: 1

Real gap rate among candidate prospect-raised issues:
- 2 / 4 = 50%

Real gap rate among all prospect lines reviewed:
- 2 / 5 = 40%

Summary: true product gaps only

1. Deal-EC3025 — Amount: Missing
   - Gap: SCIM user provisioning
   - Prospect quote: “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.”

2. Deal-D0D6B5 — Amount: Missing
   - Gap: ADP Workforce Now integration
   - Prospect quote: “Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us.”
rep-performance
stale-pipeline-by-rep0.67

? The Question

The snapshot date is 2026-09-05. Using the open deals and the engagements-by-deal table, list every open deal with no logged email, call, or meeting in the last 7 days. Compute recency from the engagements table's last_email/last_call/last_meeting fields, NOT from any date field on the deal (the deal's last_contacted_field is unreliable). For each stale deal give: deal alias, owner name, stage, amount, days since last contact. Group by owner, order by amount descending within each owner. Then state, per owner, how many stale deals they carry and the total stale amount. (Do not write outreach text.)
cost $0.6343 · 172s · in 19,192 / out 17,730 tok
✓ stale_recall_ge_80✓ grouped_by_owner✓ jake_top_amount✓ kevin_stale_amt✗ jenn_stale_amt✗ stale_count

✓ Correct Answer (ground truth)

stale_count: 65
jake_amt: 626243.0
kevin_amt: 252905.03
jenn_amt: 261645.0
top_alias: Deal-2D1F1B
top_amount: 240000.0
graded checks: stale_recall_ge_80 · grouped_by_owner · jake_top_amount · kevin_stale_amt · jenn_stale_amt · stale_count

Model's actual answer

show the model's full answer
Window used: 2026-08-29 through 2026-09-05 inclusive. Stale means latest contact date from last_email/last_call/last_meeting is on or before 2026-08-28. Days since last contact = 2026-09-05 - latest contact date. Future last_meeting dates after the snapshot were not counted as logged contact as of 2026-09-05.

Bryce Harmon
- Deal-2D1F1B | stage DS1 | amount $240,000 | 81 days (2026-09-05 - 2026-06-16)
- Deal-66D1FC | stage DS1 | amount $99,000 | 16 days (2026-09-05 - 2026-08-20)
- Deal-950043 | stage DS1 | amount $70,000 | 19 days (2026-09-05 - 2026-08-17)
- Deal-B23205 | stage DS1 | amount $45,000 | 16 days (2026-09-05 - 2026-08-20)
- Deal-7BBDFA | stage DS3 | amount $37,440 | 46 days (2026-09-05 - 2026-07-21)
- Deal-332637 | stage DS2 | amount $36,000 | 9 days (2026-09-05 - 2026-08-27)
- Deal-1BEEBF | stage DS1 | amount $31,500 | 19 days (2026-09-05 - 2026-08-17)
- Deal-A414F6 | stage DS1 | amount $25,200 | 19 days (2026-09-05 - 2026-08-17)
- Deal-C5658B | stage DS1 | amount $23,400 | 16 days (2026-09-05 - 2026-08-20)
- Deal-40522D | stage DS3 | amount $21,000 | 19 days (2026-09-05 - 2026-08-17)
- Deal-C1FA6D | stage DS1 | amount $18,000 | 16 days (2026-09-05 - 2026-08-20)
- Deal-01E193 | stage DS1 | amount $12,600 | 8 days (2026-09-05 - 2026-08-28)
- Deal-F0EBBB | stage DS3 | amount $11,400 | 24 days (2026-09-05 - 2026-08-12)
- Deal-927338 | stage DS1 | amount $10,920 | 18 days (2026-09-05 - 2026-08-18)
- Deal-E25A09 | stage DS1 | amount $6,000 | 9 days (2026-09-05 - 2026-08-27)
- Deal-C9C286 | stage DS2 | amount $5,502 | 9 days (2026-09-05 - 2026-08-27)
- Deal-012CB1 | stage DS1 | amount $1 | 23 days (2026-09-05 - 2026-08-13)
- Deal-3795AD | stage DS2 | amount $1 | 8 days (2026-09-05 - 2026-08-28)

Bryce Harmon total: 18 stale deals; amount arithmetic = 240000 + 99000 + 70000 + 45000 + 37440 + 36000 + 31500 + 25200 + 23400 + 21000 + 18000 + 12600 + 11400 + 10920 + 6000 + 5502 + 1 + 1 = $692,964

Dana Mercer
- Deal-44EA29 | stage DS2 | amount $60,000 | 10 days (2026-09-05 - 2026-08-26)
- Deal-E51FB7 | stage DS2 | amount $43,875 | 12 days (2026-09-05 - 2026-08-24)
- Deal-B42F46 | stage DS1 | amount $27,000 | 19 days (2026-09-05 - 2026-08-17)
- Deal-BA3DDC | stage DS3 | amount $23,400 | 15 days (2026-09-05 - 2026-08-21)
- Deal-9DDE86 | stage DS2 | amount $20,000 | 15 days (2026-09-05 - 2026-08-21)
- Deal-215CCA | stage DS3 | amount $18,900 | 17 days (2026-09-05 - 2026-08-19)
- Deal-5EED42 | stage DS3 | amount $16,250 | 11 days (2026-09-05 - 2026-08-25)
- Deal-57887A | stage DS2 | amount $15,000 | 8 days (2026-09-05 - 2026-08-28)
- Deal-944310 | stage DS4 | amount $10,500 | 33 days (2026-09-05 - 2026-08-03)
- Deal-B7EBD1 | stage DS5 | amount $9,000 | 16 days (2026-09-05 - 2026-08-20)
- Deal-3974EB | stage DS4 | amount $9,000 | 8 days (2026-09-05 - 2026-08-28)
- Deal-F40F04 | stage DS2 | amount $8,100 | 15 days (2026-09-05 - 2026-08-21)
- Deal-7599B8 | stage DS3 | amount $7,350 | 18 days (2026-09-05 - 2026-08-18)
- Deal-87DDD1 | stage DS1 | amount $5,000 | 19 days (2026-09-05 - 2026-08-17)
- Deal-F336B6 | stage DS3 | amount $4,200 | 15 days (2026-09-05 - 2026-08-21)
- Deal-0660B4 | stage DS4 | amount $1,920 | 16 days (2026-09-05 - 2026-08-20)

Dana Mercer total: 16 stale deals; amount arithmetic = 60000 + 43875 + 27000 + 23400 + 20000 + 18900 + 16250 + 15000 + 10500 + 9000 + 9000 + 8100 + 7350 + 5000 + 4200 + 1920 = $279,495

Alex Franklin
- Deal-CC08D1 | stage DS1 | amount $24,000 | 16 days (2026-09-05 - 2026-08-20)
- Deal-E73427 | stage DS3 | amount $18,000 | 10 days (2026-09-05 - 2026-08-26)
- Deal-885F45 | stage DS2 | amount $9,300 | 12 days (2026-09-05 - 2026-08-24)
- Deal-C2FF3C | stage DS1 | amount $8,316 | 10 days (2026-09-05 - 2026-08-26)
- Deal-0D2F7A | stage DS3 | amount $5,100 | 12 days (2026-09-05 - 2026-08-24)
- Deal-6C60D4 | stage DS3 | amount $4,800 | 12 days (2026-09-05 - 2026-08-24)
- Deal-13FEBD | stage DS2 | amount $4,680 | 12 days (2026-09-05 - 2026-08-24)
- Deal-819506 | stage DS1 | amount $4,400 | 8 days (2026-09-05 - 2026-08-28)
- Deal-9D0060 | stage DS3 | amount $3,840 | 12 days (2026-09-05 - 2026-08-24)
- Deal-690476 | stage DS2 | amount $3,600 | 18 days (2026-09-05 - 2026-08-18)
- Deal-C6D97A | stage DS4 | amount $3,240 | 8 days (2026-09-05 - 2026-08-28)
- Deal-EE195F | stage DS3 | amount $3,120 | 8 days (2026-09-05 - 2026-08-28)
- Deal-278DEC | stage DS3 | amount $2,700 | 8 days (2026-09-05 - 2026-08-28)
- Deal-635B8E | stage DS3 | amount $2,600 | 18 days (2026-09-05 - 2026-08-18)
- Deal-6883F3 | stage DS1 | amount $2,400 | 16 days (2026-09-05 - 2026-08-20)
- Deal-4A13AD | stage DS3 | amount $2,160 | 26 days (2026-09-05 - 2026-08-10)
- Deal-F67D31 | stage DS2 | amount $1,800 | 8 days (2026-09-05 - 2026-08-28)
- Deal-5FDCE4 | stage DS3 | amount $1,600 | 12 days (2026-09-05 - 2026-08-24)
- Deal-BA571A | stage DS4 | amount $1,080 | 18 days (2026-09-05 - 2026-08-18)

Alex Franklin total: 19 stale deals; amount arithmetic = 24000 + 18000 + 9300 + 8316 + 5100 + 4800 + 4680 + 4400 + 3840 + 3600 + 3240 + 3120 + 2700 + 2600 + 2400 + 2160 + 1800 + 1600 + 1080 = $106,736

Cole Ingram
- Deal-D04904 | stage DS2 | amount $58,529.25 | 11 days (2026-09-05 - 2026-08-25)
- Deal-B25F40 | stage DS3 | amount $40,000 | 8 days (2026-09-05 - 2026-08-28)
- Deal-813836 | stage DS2 | amount $32,175 | 11 days (2026-09-05 - 2026-08-25)
- Deal-1BA595 | stage DS2 | amount $31,750 | 11 days (2026-09-05 - 2026-08-25)
- Deal-CFE1E8 | stage DS3 | amount $18,000 | 11 days (2026-09-05 - 2026-08-25)
- Deal-CD47A6 | stage DS2 | amount $12,168 | 11 days (2026-09-05 - 2026-08-25)
- Deal-627646 | stage DS3 | amount $11,193 | 11 days (2026-09-05 - 2026-08-25)
- Deal-FF809F | stage DS2 | amount $7,781.20 | 11 days (2026-09-05 - 2026-08-25)
- Deal-AF932D | stage DS2 | amount $7,225.40 | 11 days (2026-09-05 - 2026-08-25)
- Deal-A71728 | stage DS2 | amount $6,947.50 | 11 days (2026-09-05 - 2026-08-25)
- Deal-8BC9F5 | stage DS2 | amount $5,616 | 10 days (2026-09-05 - 2026-08-26)
- Deal-175395 | stage DS3 | amount $4,779.88 | 11 days (2026-09-05 - 2026-08-25)
- Deal-481E24 | stage DS3 | amount $4,140 | 10 days (2026-09-05 - 2026-08-26)
- Deal-C7F9BF | stage DS2 | amount $3,360 | 11 days (2026-09-05 - 2026-08-25)
- Deal-2F3A66 | stage DS3 | amount $3,334.80 | 11 days (2026-09-05 - 2026-08-25)
- Deal-342E96 | stage DS2 | amount $2,700 | 24 days (2026-09-05 - 2026-08-12)
- Deal-E568D5 | stage DS3 | amount $1,875 | 11 days (2026-09-05 - 2026-08-25)
- Deal-FD9F4E | stage DS5 | amount $1,330 | 10 days (2026-09-05 - 2026-08-26)

Cole Ingram total: 18 stale deals; amount arithmetic = 58529.25 + 40000 + 32175 + 31750 + 18000 + 12168 + 11193 + 7781.2 + 7225.4 + 6947.5 + 5616 + 4779.88 + 4140 + 3360 + 3334.8 + 2700 + 1875 + 1330 = $252,905.03

Farid Osman
- Deal-8BA24E | stage DS1 | amount $2,880 | 8 days (2026-09-05 - 2026-08-28)
- Deal-8FDCD2 | stage DS1 | amount $1 | 15 days (2026-09-05 - 2026-08-21)

Farid Osman total: 2 stale deals; amount arithmetic = 2880 + 1 = $2,881

Missing required engagement data:
- Deal-3EED2C | owner Alex Franklin | stage DS2 | amount $7,200 | days since last contact cannot be computed because no engagements_by_deal_90d.csv row was provided.
- Deal-57FF13 | owner Elena Sinclair | stage DS1 | amount $2,100 | days since last contact cannot be computed because no engagements_by_deal_90d.csv row was provided.

Those 2 missing-data deals are not included in the stale counts or stale amount totals above.
activity-mix-vs-outcomePASS 1.00

? The Question

The snapshot date is 2026-09-05. For each sales rep (owner), compute the last-30-day totals of emails, calls, and meetings from the engagements table, and the number of deals that entered DS2 in the last 30 days (t_ds2 within 30 days of the snapshot). Report per rep: the activity mix as percentages (emails/calls/meetings share of that rep's total activities), total activities per DS2 entry, and rank the reps by that efficiency ratio (lowest activities per DS2 entry = most efficient). Name the most efficient rep and the highest-volume rep, and note if they differ. Do not attribute cause.
cost $2.0030 · 4112s · in 156,495 / out 39,736 tok
✓ justin_ds2✓ justin_volume_high✓ efficient_named✓ mix_present✓ no_causal_claim

✓ Correct Answer (ground truth)

justin_ds2: 4
graded checks: justin_ds2 · justin_volume_high · efficient_named · mix_present · no_causal_claim

Model's actual answer

show the model's full answer
Window used: 2026-08-06 through 2026-09-05 inclusive.

Missing data: engagements_by_deal_90d.csv has no rows for Deal-3EED2C and Deal-57FF13. Totals below use only the provided engagement rows. Deal-3EED2C is still counted as a DS2 entry because its t_ds2 is 2026-09-03.

Rank | Owner | Emails | Calls | Meetings | Total activities | Activity mix | DS2 entries in window | Activities / DS2
1 | Alex Franklin (84342457) | 307 | 36 | 41 | 307+36+41=384 | emails 307/384=79.9%; calls 36/384=9.4%; meetings 41/384=10.7% | 18: Deal-403845, Deal-1FC049, Deal-3EED2C, Deal-7FA0C3, Deal-E531A6, Deal-5296C9, Deal-36C33F, Deal-EE195F, Deal-F436DA, Deal-317E6F, Deal-D1E6C2, Deal-D9A72E, Deal-CA5E44, Deal-4F775F, Deal-898FC5, Deal-46988D, Deal-E73427, Deal-92D97D | 384/18=21.33
2 | Bryce Harmon (119337721) | 162 | 0 | 43 | 162+0+43=205 | emails 162/205=79.0%; calls 0/205=0.0%; meetings 43/205=21.0% | 4: Deal-25F752, Deal-D73B89, Deal-CA7DC0, Deal-1CCE5C | 205/4=51.25
3 | Cole Ingram (83155924) | 96 | 14 | 1 | 96+14+1=111 | emails 96/111=86.5%; calls 14/111=12.6%; meetings 1/111=0.9% | 2: Deal-42326B, Deal-1BA595 | 111/2=55.50
4 | Farid Osman (716654662) | 38 | 0 | 34 | 38+0+34=72 | emails 38/72=52.8%; calls 0/72=0.0%; meetings 34/72=47.2% | 1: Deal-499BF6 | 72/1=72.00
5 | Dana Mercer (83155923) | 84 | 18 | 11 | 84+18+11=113 | emails 84/113=74.3%; calls 18/113=15.9%; meetings 11/113=9.7% | 1: Deal-57887A | 113/1=113.00

Unranked because DS2 entries = 0:
- Elena Sinclair (701163055): provided engagement rows total = unavailable/incomplete because Deal-57FF13 is missing from engagements_by_deal_90d.csv; DS2 entries = 0; activities per DS2 = not computable.
- Gavin Porter (1520255671): 0 provided deals, 0 provided engagement rows; DS2 entries = 0; activities per DS2 = not computable.
- Hugo Lindqvist (77260721): 0 provided deals, 0 provided engagement rows; DS2 entries = 0; activities per DS2 = not computable.

Most efficient rep: Alex Franklin, 384/18=21.33 provided activities per DS2 entry.

Highest-volume rep: Alex Franklin, 18 DS2 entries.

They do not differ.
ae-qtd-scorecardPASS 1.00

? The Question

Build a QTD scorecard for the named AE as of 2026-09-05: bookings vs quota with attainment percent, new vs expansion split, active pipeline by stage with amount, rolling 90-day DS2-to-won rate, win and loss counts with top loss reason, activity volume by type in the last 30 days. Exclude any closed-won deal dated before the quarter. Close with three coaching observations grounded in the numbers.
cost $1.5561 · 455s · in 105,969 / out 32,964 tok
✓ bookings✓ quota✓ attainment✓ new_expansion_split✓ top_loss_reason✓ coaching_obs

✓ Correct Answer (ground truth)

owner: Alex Franklin
quarter: 2026-Q3
snapshot_date: 2026-09-05
bookings: 150000
quota: 200000
attainment_pct: 75.0
new_bookings: 113500
new_count: 5
expansion_bookings: 36500
expansion_count: 3
pipeline_by_stage: {"DS1": {"count": 20, "amount": 284621}, "DS2": {"count": 28, "amount": 353760}, "DS3": {"count": 67, "amount": 552705}, "DS4": {"count": 5, "amount": 23574}, "DS5": {"count": 5, "amount": 45730}}
open_deals_count: 125
ds2_to_won: window_start=2026-06-07; won_in_window=8; closed_in_window=35; rate=0.2286
wins_qtd: 8
losses_qtd: 27
top_loss_reason: reason=Lost- Timing (1 year or more); count=13
activity_30d_totals: emails_30d=807; calls_30d=112; meetings_30d=128; notes_30d=50
prior_quarter_excluded: deal_alias=Deal-B3E6F1; close_date=2026-06-20; amount=24000
allowed_new: 18 items — e.g. Deal-A1C3E5, Deal-B7D2F4, Deal-C9E1A6, Deal-D4B8C2
graded checks: bookings · quota · attainment · new_expansion_split · top_loss_reason · coaching_obs

Model's actual answer

show the model's full answer
QTD scorecard — Alex Franklin as of 2026-09-05

Data missing: no company_alias field was provided, so only deal aliases can be cited.

1. Bookings vs quota

Quota:
$200,000

Excluded closed-won deal before quarter:
Deal-B3E6F1 = $24,000, close_date 2026-06-20

Included QTD closed-won deals:
Deal-A1C3E5 = $40,000
Deal-F2C7D8 = $20,000
Deal-B7D2F4 = $35,000
Deal-C9E1A6 = $21,000
Deal-A8B4D6 = $12,000
Deal-D4B8C2 = $11,000
Deal-E6F3A9 = $6,500
Deal-C5D9E2 = $4,500

Arithmetic:
$40,000 + $20,000 + $35,000 + $21,000 + $12,000 + $11,000 + $6,500 + $4,500 = $150,000

QTD bookings:
$150,000

Quota attainment:
$150,000 / $200,000 = 75.0%

Remaining gap:
$200,000 - $150,000 = $50,000

2. New vs expansion split

New bookings:
Deal-A1C3E5 = $40,000
Deal-B7D2F4 = $35,000
Deal-C9E1A6 = $21,000
Deal-D4B8C2 = $11,000
Deal-E6F3A9 = $6,500

Arithmetic:
$40,000 + $35,000 + $21,000 + $11,000 + $6,500 = $113,500

Expansion bookings:
Deal-F2C7D8 = $20,000
Deal-A8B4D6 = $12,000
Deal-C5D9E2 = $4,500

Arithmetic:
$20,000 + $12,000 + $4,500 = $36,500

Split:
New = $113,500 / $150,000 = 75.7%
Expansion = $36,500 / $150,000 = 24.3%

3. Active pipeline by stage

Using status = open deals.

DS1:
20 deals = $284,621

DS2:
28 deals = $353,760

DS3:
67 deals = $552,705

DS4:
5 deals = $23,574

DS5:
5 deals = $45,730

Total active pipeline arithmetic:
$284,621 + $353,760 + $552,705 + $23,574 + $45,730 = $1,260,390

4. Rolling 90-day DS2-to-won rate

Window used:
2026-06-08 through 2026-09-05

Deals with entered_ds2 in rolling 90-day window:
111

Closed-won deals from that cohort:
8

Won deal aliases:
Deal-A1C3E5, Deal-F2C7D8, Deal-B7D2F4, Deal-C9E1A6, Deal-A8B4D6, Deal-D4B8C2, Deal-E6F3A9, Deal-C5D9E2

Arithmetic:
8 / 111 = 7.2%

Rolling 90-day DS2-to-won rate:
7.2%

5. Win and loss counts with top loss reason

QTD wins:
8

QTD losses:
27

Win/loss arithmetic:
8 wins + 27 losses = 35 QTD closed outcomes

Top loss reason:
Lost- Timing (1 year or more) = 13 losses

Top loss reason aliases:
Deal-55867E, Deal-D1A623, Deal-69CF3D, Deal-ECBF89, Deal-15DA99, Deal-79B7A1, Deal-F4AF5D, Deal-B038F0, Deal-E6E80A, Deal-B3ABED, Deal-39E25C, Deal-29326C, Deal-831B7B

Top loss reason share:
13 / 27 = 48.1% of QTD losses

6. Activity volume by type in last 30 days

Excluded pre-quarter closed-won activity:
Deal-B3E6F1 = 10 emails, 2 calls, 2 meetings, 3 notes

Activity totals after exclusion:

Emails:
807 total - 10 from Deal-B3E6F1 = 797

Calls:
112 total - 2 from Deal-B3E6F1 = 110

Meetings:
128 total - 2 from Deal-B3E6F1 = 126

Notes:
50 total - 3 from Deal-B3E6F1 = 47

Total activity:
797 + 110 + 126 + 47 = 1,080

7. Coaching observations

1. Alex is 75.0% to quota with $150,000 booked against a $200,000 quota, leaving a $50,000 gap. The active pipeline is $1,260,390, so the immediate issue is not total open pipeline volume.

2. The rolling 90-day DS2-to-won rate is low: 8 wins from 111 DS2-entered deals = 7.2%. Even with 1,080 last-30-day activities, conversion from DS2 to won is limited.

3. Losses are concentrated in timing: Lost- Timing (1 year or more) is 13 of 27 QTD losses, or 48.1%. That is more than MIA and Competitor combined if each has 5 losses.
multithreading-gapPASS 1.00

? The Question

Find every open deal that is single-threaded (fewer than 2 active contacts) or under-threaded (fewer than 3, or all contacts in one persona). Active means engaged in the last 60 days and not marked former. Personas: economic buyer, champion, HR admin, IT security, finance. For each flagged deal: amount, stage, active contact count, personas present, personas missing, the most valuable persona to add given the stage, and any on-file unengaged contact at that company who fits; otherwise say none on file.
cost $0.0874 · 23s · in 3,846 / out 2,059 tok
✓ flagged_recall✓ persona_language✓ single_thread_term✓ on_file_fit

✓ Correct Answer (ground truth)

active_window_start: 2026-07-07
persona_universe: economic buyer, champion, HR admin, IT security, finance
flag_rule: flag if active_contacts < 2 (single-threaded) or active_contacts < 3 or all active contacts share one persona (under-threaded); active = engaged within 60 days and not former
best_persona_rule: DS2/DS3: economic buyer > IT security > finance > HR admin > champion; DS4/DS5: economic buyer > finance > IT security > HR admin > champion; first persona not present among active contacts
flagged: deal_alias=Deal-36C33F; amount=15000; stage=DS2; active_count=1; reason=single-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-50D386; amount=36000; stage=DS2; active_count=2; reason=under-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-5408B0; amount=14850; stage=DS4; active_count=2; reason=under-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-5BFE3B; amount=18000; stage=DS2; active_count=2; reason=under-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-885F45; amount=9300; stage=DS2; active_count=2; reason=under-threaded; best_persona_to_add=IT security | deal_alias=Deal-92D97D; amount=60000; stage=DS2; active_count=1; reason=single-threaded; best_persona_to_add=economic buyer … (+5 more)
healthy_not_flagged: Deal-4B0BEB, Deal-84DBA6, Deal-D348E1
allowed_new: 59 items — e.g. C-077A0E, C-0D15DF, C-1BDFE0, C-2AE3AA
graded checks: flagged_recall · persona_language · single_thread_term · on_file_fit

Model's actual answer

show the model's full answer
Open status, amount, and stage are not provided in the data, so I cannot verify which deals are open or report amount/stage. Below are all deals in deal_contacts.csv flagged by the provided threading rules.

Active-contact arithmetic:
Active = last engaged in last 60 days and is_former=false.
Inactive/excluded contacts here are former contacts and June engagement dates.

1) Deal-EC3025 / C-FDD0C7
Amount: missing
Stage: missing
Active contact count: 1
Arithmetic: 2 total contacts - 1 former = 1 active
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Flag reason: single-threaded; under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: CT-6827DB, Chief People Officer, economic buyer

2) Deal-92D97D / C-E23238
Amount: missing
Stage: missing
Active contact count: 1
Arithmetic: 2 total contacts - 1 contact engaged 2026-06-01 outside last 60 days = 1 active
Personas present: HR admin
Personas missing: economic buyer, champion, IT security, finance
Flag reason: single-threaded; under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: none on file

3) Deal-50D386 / C-EB10E4
Amount: missing
Stage: missing
Active contact count: 2
Arithmetic: 2 total contacts - 0 former - 0 outside last 60 days = 2 active
Personas present: champion, HR admin
Personas missing: economic buyer, IT security, finance
Flag reason: under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: CT-A1C4B3, Chief People Officer, economic buyer

4) Deal-D0D6B5 / C-32918E
Amount: missing
Stage: missing
Active contact count: 3
Arithmetic: 3 total contacts - 0 former - 0 outside last 60 days = 3 active
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Flag reason: under-threaded because all active contacts are one persona
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: CT-1FA4DB, Chief People Officer, economic buyer

5) Deal-5BFE3B / C-535D36
Amount: missing
Stage: missing
Active contact count: 2
Arithmetic: 2 total contacts - 0 former - 0 outside last 60 days = 2 active
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Flag reason: under-threaded; all active contacts are one persona
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: none on file

6) Deal-36C33F / C-077A0E
Amount: missing
Stage: missing
Active contact count: 1
Arithmetic: 3 total contacts - 2 former = 1 active
Personas present: IT security
Personas missing: economic buyer, champion, HR admin, finance
Flag reason: single-threaded; under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: CT-1DB73E, Chief People Officer, economic buyer

7) Deal-885F45 / C-5E8EFB
Amount: missing
Stage: missing
Active contact count: 2
Arithmetic: 2 total contacts - 0 former - 0 outside last 60 days = 2 active
Personas present: economic buyer, champion
Personas missing: HR admin, IT security, finance
Flag reason: under-threaded
Most valuable persona to add given stage: stage missing; IT security is the most valuable on-file missing persona based on available data
On-file unengaged fit: CT-B3F25D, IT Security Lead, IT security

8) Deal-FCBE5B / C-737030
Amount: missing
Stage: missing
Active contact count: 1
Arithmetic: 1 total contact - 0 former - 0 outside last 60 days = 1 active
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Flag reason: single-threaded; under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: none on file

9) Deal-5408B0 / C-2AE3AA
Amount: missing
Stage: missing
Active contact count: 2
Arithmetic: 2 total contacts - 0 former - 0 outside last 60 days = 2 active
Personas present: champion, HR admin
Personas missing: economic buyer, IT security, finance
Flag reason: under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: CT-07FA76, Chief People Officer, economic buyer

10) Deal-C6D97A / C-5A8FC2
Amount: missing
Stage: missing
Active contact count: 3
Arithmetic: 3 total contacts - 0 former - 0 outside last 60 days = 3 active
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Flag reason: under-threaded because all active contacts are one persona
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: none on file

11) Deal-F9A08A / C-0D15DF
Amount: missing
Stage: missing
Active contact count: 1
Arithmetic: 2 total contacts - 1 contact engaged 2026-06-20 outside last 60 days = 1 active
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Flag reason: single-threaded; under-threaded
Most valuable persona to add given stage: stage missing; economic buyer is the most valuable missing persona based on available data
On-file unengaged fit: CT-697541, Chief People Officer, economic buyer

Not flagged:
Deal-84DBA6: 3 active contacts, personas present champion, economic buyer, IT security.
Deal-4B0BEB: 4 active contacts, personas present champion, economic buyer, HR admin, finance.
Deal-D348E1: 5 active contacts, personas present champion, economic buyer, IT security, finance, HR admin.
talk-track-from-transcriptsPASS 1.00

? The Question

From this rep's last 10 calls: what they lead with in the first five minutes, how they handle the three most common objections, how often a concrete next step is agreed (rate), and every competitor a prospect raised. Quote at most one line per finding and only lines that appear in the transcripts. End with two coaching notes.
cost $0.4926 · 291s · in 32,416 / out 10,590 tok
✓ objection_count✓ next_step_rate✓ competitors✓ coaching✓ quote_used

✓ Correct Answer (ground truth)

rep: Alex Franklin
n_transcripts: 10
opener_theme: theme=opens with a customer recognition win story (400-person retailer, 18% turnover reduction); count=8; total=10; quote=Quick one to kick off: a 400-person retailer we work with cut regretted turnover 18% in two quarters after automating milestone awards, and I wanted to walk you through exactly how they did it.; transcript_id=TT-001
objections: objection=budget; count=4; quote=Honestly, budget is locked until next fiscal year — I can't add a new line item right now.; transcript_id=TT-001 | objection=timing; count=3; quote=This is good, but can we revisit it next quarter? Open enrollment starts in October and we're underwater.; transcript_id=TT-002 | objection=in-house; count=3; quote=We already do recognition with a spreadsheet and quarterly gift cards — why would we change?; transcript_id=TT-004
objection_count: 3
next_step: agreed=7; total=10; rate=0.7
competitors_prospect_raised: Awardco, Kudos
competitor_quotes: Awardco=We're also in late talks with Awardco — their rewards catalog looks bigger than yours.; Kudos=How are you different from Kudos? Our CEO used them at her last company.
rep_raised_competitors_excluded: Workhuman
allowed_new: 13 items — e.g. TT-001, TT-002, TT-003, TT-004
graded checks: objection_count · next_step_rate · competitors · coaching · quote_used

Model's actual answer

show the model's full answer
Lead in first five minutes:
- Main pattern: Alex Franklin leads with the 400-person retailer proof story in 8 of 10 calls: Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-EDC141, Deal-D9A12F, Deal-84DBA6.
- Arithmetic: 8 / 10 = 80%.
- Quote: “Quick one to kick off: a 400-person retailer we work with cut regretted turnover 18% in two quarters after automating milestone awards, and I wanted to walk you through exactly how they did it.”
- Exceptions: Deal-403845 leads with security/pricing agenda; Deal-1E2498 leads with straight pricing. Arithmetic: 2 / 10 = 20%.

Three most common objections and handling:

1. Budget locked until next fiscal year
- Deals: Deal-D348E1, Deal-547B2B, Deal-60C2C2, Deal-84DBA6.
- Arithmetic: 4 / 10 = 40%.
- Handling: reframes spend as fundable from turnover savings, citing $210k in avoided backfills.
- Quote: “Totally fair. Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off.”

2. Revisit next quarter / timing pressure
- Deals: Deal-5408B0, Deal-C61CF7, Deal-D9A12F.
- Arithmetic: 3 / 10 = 30%.
- Handling: proposes a 90-day one-department pilot to create internal data before planning.
- Quote: “Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?”

3. Existing spreadsheet / quarterly gift card process
- Deals: Deal-403845, Deal-EDC141, Deal-1E2498.
- Arithmetic: 3 / 10 = 30%.
- Handling: contrasts manual process with automated milestones and recognition analytics.
- Quote: “Spreadsheets work until they scale — the difference is automation: milestones fire without HR lifting a finger, and you get analytics on who is being recognized.”

Concrete next step agreed:
- Agreed in 7 calls: Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-D9A12F, Deal-1E2498.
- Not agreed in 3 calls: Deal-403845, Deal-EDC141, Deal-84DBA6.
- Arithmetic: 7 / 10 = 70%.
- Quote: “Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager.”

Competitors prospects raised:
- Awardco: Deal-547B2B.
  Quote: “We're also in late talks with Awardco — their rewards catalog looks bigger than yours.”
- Kudos: Deal-EDC141.
  Quote: “How are you different from Kudos? Our CEO used them at her last company.”
- Workhuman is not counted because it was raised by Alex Franklin, not by a prospect, in Deal-C61CF7.

Coaching notes:
1. Keep leading with the retailer proof story: it appears in 8 / 10 calls and is present in 6 of the 7 calls with agreed next steps.
2. Improve late-stage next-step control: committee/no-urgency stalls in Deal-403845, Deal-EDC141, and Deal-84DBA6 produced 0 / 3 agreed next steps.
reporting-analytics
q3-weighted-forecastPASS 1.00

? The Question

Below are the open deals in the default sales pipeline with a close date between 2026-07-01 and 2026-10-15, pulled from the CRM warehouse on 2026-09-05. Stages: DS1 (discovery) through DS5 (contract). Build the Q3 2026 forecast (quarter = 2026-07-01 to 2026-09-30). Weighting rule: 100 percent of COMMIT plus 35 percent of BEST_CASE. PIPELINE deals count zero. Only deals with a close date inside the quarter count. Report: COMMIT total, BEST_CASE total, weighted forecast, count of deals in each category inside the quarter, the deals you excluded for being outside the quarter (count and total amount), and the top 5 BEST_CASE deals by amount inside the quarter. Show arithmetic. Then, in a final '## Data quality' section of no more than four sentences, name the data quality problems in this extract that would make the forecast unreliable if it were run unattended.
cost $0.9497 · 158s · in 78,667 / out 17,836 tok
✓ commit_total_44729✓ best_case_total_203565✓ weighted_115976.75✓ commit_count_7✓ best_case_count_24✓ excluded_count_32✓ excluded_amount_227575✓ top5_aliases✓ flags_blank_owner✓ flags_missing_why_buys

✓ Correct Answer (ground truth)

graded checks: commit_total_44729 · best_case_total_203565 · weighted_115976.75 · commit_count_7 · best_case_count_24 · excluded_count_32 · excluded_amount_227575 · top5_aliases · flags_blank_owner · flags_missing_why_buys

Model's actual answer

show the model's full answer
Q3 2026 filter applied: 2026-07-01 through 2026-09-30 inclusive.

## COMMIT total

COMMIT total: $44,729

Arithmetic:
$11,200 Deal-547B2B
+ $9,000 Deal-B7EBD1
+ $9,000 Deal-403845
+ $6,360 Deal-A2B47C
+ $5,400 Deal-2465CE
+ $2,520 Deal-A5E80A
+ $1,249 Deal-499BF6
= $44,729

## BEST_CASE total

BEST_CASE total: $203,565

Arithmetic:
$38,935 Deal-2D7423
+ $24,000 Deal-25F752
+ $19,656 Deal-E53952
+ $16,250 Deal-5EED42
+ $11,116 Deal-FA32A0
+ $10,800 Deal-FC22A3
+ $10,500 Deal-944310
+ $9,890 Deal-5195DB
+ $9,720 Deal-180D02
+ $9,000 Deal-3974EB
+ $7,200 Deal-5D8CEE
+ $3,840 Deal-9D0060
+ $3,780 Deal-46988D
+ $3,600 Deal-357C30
+ $3,240 Deal-C6D97A
+ $3,150 Deal-DAF1D9
+ $3,120 Deal-EE195F
+ $3,060 Deal-55164C
+ $2,916 Deal-001FF4
+ $2,760 Deal-7B3B0F
+ $2,484 Deal-F9A08A
+ $2,100 Deal-8952F0
+ $1,920 Deal-1FC049
+ $528 Deal-87412C
= $203,565

## Weighted forecast

Weighted forecast: $115,976.75

Arithmetic:
100% of COMMIT + 35% of BEST_CASE
= $44,729 + 35% × $203,565
= $44,729 + $71,247.75
= $115,976.75

PIPELINE contribution: $0

## Count of deals inside Q3 by category

COMMIT: 7 deals
BEST_CASE: 24 deals
PIPELINE: 23 deals

## Deals excluded for being outside Q3

Excluded count: 32 deals

Excluded total amount: $227,575

Arithmetic:
$43,875 Deal-E51FB7
+ $18,000 Deal-B936FE
+ $17,000 Deal-D9A12F
+ $13,770 Deal-D348E1
+ $10,800 Deal-4062CF
+ $9,000 Deal-293AF3
+ $9,000 Deal-034D49
+ $7,920 Deal-E0ADD8
+ $7,690 Deal-9F2E43
+ $7,500 Deal-FCBE5B
+ $7,200 Deal-712010
+ $5,700 Deal-6691E0
+ $5,400 Deal-C61CF7
+ $5,400 Deal-600CD9
+ $5,400 Deal-A92065
+ $5,400 Deal-1D532E
+ $5,160 Deal-48B656
+ $4,800 Deal-E531A6
+ $4,400 Deal-D1E6C2
+ $4,300 Deal-D9E112
+ $4,000 Deal-5AD94B
+ $3,600 Deal-901332
+ $3,600 Deal-47AE31
+ $3,600 Deal-15D24F
+ $3,300 Deal-766C74
+ $2,400 Deal-ED725A
+ $1,800 Deal-8AD4A5
+ $1,800 Deal-D7E999
+ $1,680 Deal-ED13B0
+ $1,600 Deal-5FDCE4
+ $1,400 Deal-7FA0C3
+ $1,080 Deal-F5A622
= $227,575

Excluded deals:
1. Deal-E51FB7: $43,875, PIPELINE, close_date 2026-10-01
2. Deal-B936FE: $18,000, PIPELINE, close_date 2026-10-09
3. Deal-D9A12F: $17,000, PIPELINE, close_date 2026-10-15
4. Deal-D348E1: $13,770, COMMIT, close_date 2026-10-15
5. Deal-4062CF: $10,800, PIPELINE, close_date 2026-10-15
6. Deal-293AF3: $9,000, PIPELINE, close_date 2026-10-09
7. Deal-034D49: $9,000, PIPELINE, close_date 2026-10-15
8. Deal-E0ADD8: $7,920, PIPELINE, close_date 2026-10-15
9. Deal-9F2E43: $7,690, PIPELINE, close_date 2026-10-08
10. Deal-FCBE5B: $7,500, PIPELINE, close_date 2026-10-07
11. Deal-712010: $7,200, PIPELINE, close_date 2026-10-15
12. Deal-6691E0: $5,700, PIPELINE, close_date 2026-10-15
13. Deal-C61CF7: $5,400, BEST_CASE, close_date 2026-10-09
14. Deal-600CD9: $5,400, PIPELINE, close_date 2026-10-02
15. Deal-A92065: $5,400, PIPELINE, close_date 2026-10-15
16. Deal-1D532E: $5,400, PIPELINE, close_date 2026-10-15
17. Deal-48B656: $5,160, BEST_CASE, close_date 2026-10-15
18. Deal-E531A6: $4,800, PIPELINE, close_date 2026-10-15
19. Deal-D1E6C2: $4,400, PIPELINE, close_date 2026-10-09
20. Deal-D9E112: $4,300, PIPELINE, close_date 2026-10-09
21. Deal-5AD94B: $4,000, PIPELINE, close_date 2026-10-15
22. Deal-901332: $3,600, BEST_CASE, close_date 2026-10-15
23. Deal-47AE31: $3,600, BEST_CASE, close_date 2026-10-09
24. Deal-15D24F: $3,600, BEST_CASE, close_date 2026-10-09
25. Deal-766C74: $3,300, PIPELINE, close_date 2026-10-14
26. Deal-ED725A: $2,400, BEST_CASE, close_date 2026-10-08
27. Deal-8AD4A5: $1,800, BEST_CASE, close_date 2026-10-07
28. Deal-D7E999: $1,800, PIPELINE, close_date 2026-10-15
29. Deal-ED13B0: $1,680, PIPELINE, close_date 2026-10-09
30. Deal-5FDCE4: $1,600, BEST_CASE, close_date 2026-10-01
31. Deal-7FA0C3: $1,400, PIPELINE, close_date 2026-10-01
32. Deal-F5A622: $1,080, BEST_CASE, close_date 2026-10-08

## Top 5 BEST_CASE deals by amount inside Q3

1. Deal-2D7423: $38,935, DS3, close_date 2026-09-30
2. Deal-25F752: $24,000, DS4, close_date 2026-09-25
3. Deal-E53952: $19,656, DS4, close_date 2026-09-30
4. Deal-5EED42: $16,250, DS3, close_date 2026-09-30
5. Deal-FA32A0: $11,116, DS3, close_date 2026-09-25

## Data quality

Owner is missing for all but one deal, so rep accountability and owner-level rollups are unreliable. Many why_buys_chars values are 0, including large COMMIT and BEST_CASE deals, so buyer rationale is missing for much of the forecast. Forecast category and stage are not consistently aligned: Deal-A5E80A is COMMIT at DS1, and Deal-499BF6 is COMMIT at DS2. The extract includes non-Q3 close dates, so an unattended forecast must enforce the quarter filter to avoid overstating Q3.
aha-moment-2x20.83

? The Question

Test the activation hypothesis on the company cohort below: companies with 5+ unique givers (m1_users >= 5) AND 1+ successful redemption (m1_redemptions >= 1) in their first calendar month retain better at 24 months than those with one signal or neither. Every company in this extract is already 25+ months old, so current_status = 'active' means retained at 24 months. Report the full 2x2 (cohort size and 24-month retention rate for: both signals, givers-only, redemption-only, neither), state how many companies were excluded from the denominator and why (if none, say so), name the single signal with the largest retention lift, and state what this does and does not prove.
cost $1.4215 · 232s · in 118,685 / out 26,560 tok
✓ both_66✓ givers_47✓ redemp_31✓ neither_40✓ excluded_0✗ largest_lift_givers

✓ Correct Answer (ground truth)

graded checks: both_66 · givers_47 · redemp_31 · neither_40 · excluded_0 · largest_lift_givers

Model's actual answer

show the model's full answer
Retention definition used: current_status = active = retained at 24 months.

2x2 activation cohorts:

Cohort                         Definition                                      Companies  Retained  Arithmetic        Retention
Both signals                   m1_users >= 5 and m1_redemptions >= 1          47         31        31 / 47           65.96%
Givers-only                    m1_users >= 5 and m1_redemptions = 0           49         23        23 / 49           46.94%
Redemption-only                m1_users < 5 and m1_redemptions >= 1           29         9         9 / 29            31.03%
Neither                        m1_users < 5 and m1_redemptions = 0            95         38        38 / 95           40.00%

Denominator check:
47 + 49 + 29 + 95 = 220 companies.

Excluded from denominator:
0 companies excluded. All 220 rows had usable current_status, m1_users, and m1_redemptions values.

Activation hypothesis result:
Supported in this extract. Companies with both first-month signals retained better than companies with one signal or neither.

Arithmetic:
- Both vs givers-only: 65.96% - 46.94% = +19.02 percentage points
- Both vs redemption-only: 65.96% - 31.03% = +34.93 percentage points
- Both vs neither: 65.96% - 40.00% = +25.96 percentage points

Single signal with largest retention lift:
5+ unique givers is the stronger single signal.

One-signal lift vs neither:
- Givers-only: 46.94% - 40.00% = +6.94 percentage points
- Redemption-only: 31.03% - 40.00% = -8.97 percentage points

Marginal cross-check:
- m1_users >= 5: 54 retained / 96 = 56.25%
- m1_users < 5: 47 retained / 124 = 37.90%
- Lift = 56.25% - 37.90% = +18.35 percentage points

- m1_redemptions >= 1: 40 retained / 76 = 52.63%
- m1_redemptions = 0: 61 retained / 144 = 42.36%
- Lift = 52.63% - 42.36% = +10.27 percentage points

What this proves:
In this provided company extract, companies with both activation signals had the highest observed 24-month retention rate.

What this does not prove:
It does not prove causality. It does not prove that increasing m1_users or m1_redemptions causes retention. The data does not control for other variables such as product_tier, ARR, industry_group, country, integrations, company size, acquisition source, or any other missing factors.
arr-rollforward-reconciliationPASS 1.00

? The Question

Reconcile ARR between CRM company records and billing subscriptions as of 2026-09-05. Billing ARR is MRR x 12. Report both totals, the variance, and a decomposition into buckets (status mismatch, rounding, missing records, other) that sums exactly to the variance. List each mismatched account with a suggested owner. Business rule: any subscription with a term other than 12 months must have cf_agreement_end_date populated; list violations.
cost $0.5049 · 268s · in 42,244 / out 9,098 tok
✓ billing_total✓ crm_total✓ variance✓ buckets_sum✓ violations_listed

✓ Correct Answer (ground truth)

as_of: 2026-09-05
billing_arr_total: 604739.28
crm_arr_total: 603581.76
variance: 1157.52
variance_definition: billing_arr_total - crm_arr_total (billing ARR = sum of MRR x 12 over status=active subscriptions)
buckets: {"status_mismatch": {"amount": "-13158.48", "accounts": [{"company_alias": "C-0C8323BF", "billing_arr": "0.00", "hubspot_arr": "4905.24", "diff": "-4905.24", "suggested_owner": "Dana Mercer"}, {"compa
bucket_sum_equals_variance: True
n_mismatched_accounts: 7
rule: term_months != 12 requires cf_agreement_end_date
violations: subscription_id=SUB-0002; company_alias=C-1794A52C; term_months=24 | subscription_id=SUB-0019; company_alias=C-22170CA1; term_months=36
n_companies: 40
graded checks: billing_total · crm_total · variance · buckets_sum · violations_listed

Model's actual answer

show the model's full answer
Totals as of 2026-09-05:
- Billing ARR: $604,739.28
  - Arithmetic: active billing MRR $50,394.94 x 12 = $604,739.28
  - Cancelled subscriptions treated as $0 active Billing ARR.
- CRM ARR: $603,581.76
  - Arithmetic: sum(company_arr.hubspot_arr) = $603,581.76
- Variance: $1,157.52 Billing ARR higher
  - Arithmetic: $604,739.28 - $603,581.76 = $1,157.52

Variance decomposition:
- Status mismatch: -$13,158.48
  - C-0C8323BF: billing status cancelled, Billing ARR $0.00 vs CRM ARR $4,905.24 = -$4,905.24
  - C-0DC4FB8C: billing status cancelled, Billing ARR $0.00 vs CRM ARR $8,253.24 = -$8,253.24
  - Arithmetic: -$4,905.24 + -$8,253.24 = -$13,158.48

- Rounding: -$36.00
  - C-0D66DF9E: $1,932.00 x 12 = $23,184.00 vs CRM ARR $23,200.00 = -$16.00
  - C-14D70CE0: $1,515.00 x 12 = $18,180.00 vs CRM ARR $18,200.00 = -$20.00
  - Arithmetic: -$16.00 + -$20.00 = -$36.00

- Missing records: $11,952.00
  - C-21629AA4: in billing, missing from CRM ARR file; $2,370.77 x 12 = $28,449.24 vs CRM ARR $0.00 = $28,449.24
  - C-0D5BBE3A: in CRM ARR file, missing from billing subscriptions; Billing ARR $0.00 vs CRM ARR $16,497.24 = -$16,497.24
  - Arithmetic: $28,449.24 + -$16,497.24 = $11,952.00

- Other: $2,400.00
  - C-0F7269D7: $2,233.00 x 12 = $26,796.00 vs CRM ARR $24,396.00 = $2,400.00
  - Arithmetic: $2,400.00

Decomposition check:
- -$13,158.48 + -$36.00 + $11,952.00 + $2,400.00 = $1,157.52

Mismatched accounts with suggested owner:
- C-0C8323BF: variance -$4,905.24; suggested owner: RevOps / CRM owner to remove or validate CRM ARR for cancelled billing subscription.
- C-0DC4FB8C: variance -$8,253.24; suggested owner: RevOps / CRM owner to remove or validate CRM ARR for cancelled billing subscription.
- C-0D66DF9E: variance -$16.00; suggested owner: RevOps / CRM owner to confirm rounding policy.
- C-14D70CE0: variance -$20.00; suggested owner: RevOps / CRM owner to confirm rounding policy.
- C-21629AA4: variance $28,449.24; suggested owner: RevOps / CRM owner to create or map missing CRM ARR record.
- C-0D5BBE3A: variance -$16,497.24; suggested owner: Billing Ops to locate missing billing subscription, or RevOps to remove CRM ARR if no billing record exists.
- C-0F7269D7: variance $2,400.00; suggested owner: RevOps + Billing Ops to determine authoritative ARR.

Owner data note:
- No named account owner field was provided, so owners above are suggested functional owners only.

Business rule violations:
Rule: any subscription with term_months other than 12 must have cf_agreement_end_date populated.

Violations:
- SUB-0002, C-1794A52C: term_months 24, cf_agreement_end_date missing.
- SUB-0019, C-22170CA1: term_months 36, cf_agreement_end_date missing.
kvm-month-over-monthPASS 1.00

? The Question

Report the four core KVMs for 2026-08 against 2026-07: giving rate, redemptions per user, 1:1 meetings engagement, pulse check engagement. For each: value, prior value, absolute and relative change, direction. Name the KVM with the largest relative move and the segment (plan_tier or size_band) driving it if the data supports that; otherwise say the data does not. Under 200 words plus one table.
cost $0.5070 · 268s · in 43,367 / out 8,963 tok
✓ four_kvms✓ biggest_mover_named✓ direction_correct✓ segment_named✓ word_cap

✓ Correct Answer (ground truth)

aggregation: simple mean of company-level values per month
kvms: {"giving_rate": {"2026-07": 0.6023, "2026-08": 0.6027, "abs_change": 0.0004, "rel_change_pct": 0.07, "direction": "up"}, "redemptions_per_user": {"2026-07": 1.73, "2026-08": 1.7302, "abs_change": 0.00
biggest_mover: pulse_engagement
driving_segment: size_band=enterprise; 2026-07=0.55; 2026-08=0.2743; rel_change_pct=-50.13
segment_detail: {"smb": {"2026-07": 0.6588, "2026-08": 0.6573, "rel_change_pct": -0.23}, "mid_market": {"2026-07": 0.593, "2026-08": 0.5942, "rel_change_pct": 0.2}, "enterprise": {"2026-07": 0.55, "2026-08": 0.2743,
n_company_rows_per_month: 30
graded checks: four_kvms · biggest_mover_named · direction_correct · segment_named · word_cap

Model's actual answer

show the model's full answer
Arithmetic: no user counts supplied, so monthly value = unweighted average across 30 company rows. Absolute change = 2026-08 − 2026-07. Relative change = absolute change ÷ 2026-07.

| KVM | 2026-08 value | 2026-07 prior | Absolute change | Relative change | Direction |
|---|---:|---:|---:|---:|---|
| Giving rate | 0.6027 | 0.6023 | +0.0004 | +0.07% | Up |
| Redemptions per user | 1.7302 | 1.7300 | +0.0002 | +0.01% | Up |
| 1:1 meetings engagement | 0.4472 | 0.4469 | +0.0003 | +0.06% | Up |
| Pulse check engagement | 0.5086 | 0.6006 | -0.0920 | -15.31% | Down |

Largest relative move: pulse check engagement, down -15.31%. Segment driver supported: size_band = enterprise, where pulse check fell from 0.5500 to 0.2743, or -0.2757 / 0.5500 = -50.13%. plan_tier does not explain it because all rows are tier_three.
rewards-ytd-sectionPASS 1.00

? The Question

Produce the redemption section of the weekly rewards report through the last completed month (2026-08): redemption count, spend, unique redeemers, redemptions per redeemer, provider mix as percent of spend, top 5 countries by redemptions. Say which month is the last completed month. Provider shares must sum to 100.
cost $1.9221 · 449s · in 201,991 / out 27,792 tok
✓ count✓ spend✓ unique_redeemers✓ month_named✓ provider_mix✓ top_country

✓ Correct Answer (ground truth)

redemption_count: 378
total_spend_usd: 27846.00
unique_redeemers: 235
redemptions_per_redeemer: 1.61
provider_mix_pct_of_spend: TangoCard=11.6; Tremendous=30.54; custom=39.05; Snappy=18.81
top5_countries_by_count: country=US; count=244 | country=CA; count=24 | country=AU; count=21 | country=GB; count=17 | country=NL; count=17
graded checks: count · spend · unique_redeemers · month_named · provider_mix · top_country

Model's actual answer

show the model's full answer
Last completed month: 2026-08

Redemption section through 2026-08:
- Redemption count: 378
- Spend: $27,846.00
- Unique redeemers: 236
- Redemptions per redeemer: 378 / 236 = 1.6017 = 1.60

Spend arithmetic:
- TangoCard: $3,230.00
- Tremendous: $8,505.00
- custom: $10,873.00
- Snappy: $5,238.00
- Total spend: $3,230.00 + $8,505.00 + $10,873.00 + $5,238.00 = $27,846.00

Provider mix, percent of spend:
- custom: $10,873.00 / $27,846.00 = 39.05%
- Tremendous: $8,505.00 / $27,846.00 = 30.54%
- Snappy: $5,238.00 / $27,846.00 = 18.81%
- TangoCard: $3,230.00 / $27,846.00 = 11.60%

Provider share sum: 39.05% + 30.54% + 18.81% + 11.60% = 100.00%

Top 5 countries by redemptions:
1. US: 244
2. CA: 24
3. AU: 21
4. GB: 17
5. NL: 17
customer-success
churn-save-eligibilityPASS 1.00

? The Question

Which at-risk accounts qualify for a churn-save offer under the documented eligibility rules, what amount is at stake per account and in total, and which play fits each (usage revival, executive touch, commercial concession)? Cite the signal that justifies each play. List accounts that look at risk but do not qualify and why.
cost $0.7437 · 185s · in 40,561 / out 17,339 tok
✓ eligible_set✓ total_at_stake✓ plays_cited✓ noneligible_named✓ rules_applied

✓ Correct Answer (ground truth)

snapshot_date: 2026-09-05
rules: health_score < 60, churn_save_eligible_amount > 0, renewal within 120 days of snapshot
eligible: account_alias=C-0F6C0F34; amount_at_stake=49707.00; play=executive touch; justifying_signal=champion_active is false - no executive sponsor engaged | account_alias=C-0B827671; amount_at_stake=25365.00; play=usage revival; justifying_signal=usage_trend_3m=declining over the last 3 months | account_alias=C-0B360C78; amount_at_stake=35748.00; play=commercial concession; justifying_signal=usage stable/growing with seat utilization 75% - risk is commercial, not adoption | account_alias=C-0B0F1BAB; amount_at_stake=5494.00; play=executive touch; justifying_signal=champion_active is false - no executive sponsor engaged | account_alias=C-0CA21961; amount_at_stake=16829.00; play=usage revival; justifying_signal=seat utilization 26% is below 50% | account_alias=C-0E9C27D1; amount_at_stake=41235.00; play=commercial concession; justifying_signal=usage stable/growing with seat utilization 85% - risk is commercial, not adoption … (+2 more)
total_amount_at_stake: 224601.00
non_eligible_at_risk: account_alias=C-0BC71BDD; health_score=55 | account_alias=C-0BA71F12; health_score=52 | account_alias=C-0F6694C3; health_score=43 | account_alias=C-0BE96399; health_score=54 | account_alias=C-0F876796; health_score=47 | account_alias=C-0FCCD2DF; health_score=43 … (+1 more)
n_accounts: 30
graded checks: eligible_set · total_at_stake · plays_cited · noneligible_named · rules_applied

Model's actual answer

show the model's full answer
Eligibility used:
R1: health_score < 60
R2: churn_save_eligible_amount > 0
R3: renewal_date within 120 days of 2026-09-05, so renewal_date <= 2027-01-03

Amount at stake is not explicitly defined in the rules. I am treating arr as revenue at stake, and also showing churn_save_eligible_amount because it is the offer-eligibility amount used in R2.

Qualifying at-risk accounts

| account_alias | Eligibility arithmetic | ARR at stake | Churn-save eligible amount | Play | Signal |
|---|---:|---:|---:|---|---|
| C-0F6C0F34 | 51 < 60; $49,707 > $0; 2026-10-03 is 28 days out | $86,741.00 | $49,707.00 | executive touch | champion_active=false; usage is growing and seat utilization is 308/395 = 78.0%, so the clearest risk signal is lack of active champion |
| C-0B827671 | 56 < 60; $25,365 > $0; 2026-11-14 is 70 days out | $72,088.00 | $25,365.00 | usage revival | usage_trend_3m=declining; seat utilization is 113/202 = 55.9% |
| C-0B360C78 | 57 < 60; $35,748 > $0; 2026-10-28 is 53 days out | $60,427.00 | $35,748.00 | commercial concession | usage_trend_3m=growing, champion_active=true, and seat utilization is 246/327 = 75.2%; risk appears commercial rather than usage/champion-driven |
| C-0B0F1BAB | 38 < 60; $5,494 > $0; 2026-09-23 is 18 days out | $15,391.00 | $5,494.00 | executive touch | champion_active=false; renewal is also near-term at 18 days |
| C-0CA21961 | 58 < 60; $16,829 > $0; 2026-12-28 is 114 days out | $31,501.00 | $16,829.00 | usage revival | very low seat utilization: 84/325 = 25.8%; usage_trend_3m=flat |
| C-0E9C27D1 | 39 < 60; $41,235 > $0; 2026-09-24 is 19 days out | $75,093.00 | $41,235.00 | commercial concession | champion_active=true and seat utilization is 134/157 = 85.4%; risk appears commercial rather than usage/champion-driven |
| C-0CEF69FD | 53 < 60; $32,621 > $0; 2026-11-21 is 77 days out | $79,324.00 | $32,621.00 | executive touch | champion_active=false; usage is growing and seat utilization is 97/136 = 71.3%, so the clearest risk signal is lack of active champion |
| C-0D3278C7 | 54 < 60; $17,602 > $0; 2026-11-12 is 68 days out | $33,815.00 | $17,602.00 | usage revival | usage_trend_3m=declining and low seat utilization: 126/380 = 33.2% |

Total arithmetic

ARR at stake:
$86,741 + $72,088 + $60,427 + $15,391 + $31,501 + $75,093 + $79,324 + $33,815 = $454,380.00

Churn-save eligible amount:
$49,707 + $25,365 + $35,748 + $5,494 + $16,829 + $41,235 + $32,621 + $17,602 = $224,601.00

At-risk accounts that do not qualify

| account_alias | Why it looks at risk | Why it does not qualify |
|---|---:|---|
| C-0BC71BDD | health_score 55 < 60 | Fails R2: churn_save_eligible_amount = $0.00. Renewal is within window: 2026-10-27 is 52 days out. |
| C-0BA71F12 | health_score 52 < 60 | Fails R3: 2027-04-11 is 218 days out, which is > 120. |
| C-0F6694C3 | health_score 43 < 60 | Fails R2: churn_save_eligible_amount = $0.00. Fails R3: 2027-03-21 is 197 days out, which is > 120. |
| C-0BE96399 | health_score 54 < 60 | Fails R2: churn_save_eligible_amount = $0.00. Renewal is within window: 2026-10-29 is 54 days out. |
| C-0F876796 | health_score 47 < 60 | Fails R3: 2027-02-06 is 154 days out, which is > 120. |
| C-0FCCD2DF | health_score 43 < 60 | Fails R2: churn_save_eligible_amount = $0.00. Fails R3: 2027-04-23 is 230 days out, which is > 120. |
| C-10A56B0F | health_score 54 < 60 | Fails R2: churn_save_eligible_amount = $0.00. Renewal is within window: 2026-12-12 is 98 days out. |
expansion-kitPASS 1.00

? The Question

A customer replied to outreach (reply included). Build the expansion kit: seat coverage (licensed over headcount), two lines on usage health, headroom in seats and ARR at the current per-seat rate, who replied and whether they can buy, the right buyer from our contacts, and a reply email under 150 words that moves toward the right person without being pushy and cites one real usage fact.
cost $0.0454 · 19s · in 2,460 / out 890 tok
✓ coverage_pct✓ headroom_arr✓ right_buyer✓ replier_not_buyer✓ usage_fact✓ email_under_150

✓ Correct Answer (ground truth)

company_alias: C-0DDFC9A7
coverage_pct: 37.5
headroom_seats: 250
per_seat_annual_rate: 60.00
headroom_arr: 15000.00
replier: Maria S.
replier_can_buy: False
right_buyer: name=Dana R.; title=VP People
usage_facts: active_users_2026_08=126; active_users_2026_03=88; growth_pct_6m=43.2; licensed_seat_utilization_pct=84.0
usage_health_lines: Monthly active users grew from 88 (2026-03) to 126 (2026-08), +43.2% over 6 months., Last month 126 of 150 licensed seats were active (84.0% utilization), approaching the seat cap.
graded checks: coverage_pct · headroom_arr · right_buyer · replier_not_buyer · usage_fact · email_under_150

Model's actual answer

show the model's full answer
Expansion kit — C-0DDFC9A7

Seat coverage:
Licensed over headcount = 150 / 400 = 37.5%

Usage health:
March to August active users grew from 88 to 126: 126 - 88 = +38 users; 38 / 88 = 43.2% growth.
August seat utilization = 126 / 150 = 84.0%, leaving limited room before licensed seats are full.

Headroom:
Current per-seat ARR = $9,000 / 150 = $60 per seat/year.
Seat headroom to full headcount coverage = 400 - 150 = 250 seats.
ARR headroom at current rate = 250 * $60 = $15,000 incremental ARR.
Full-headcount ARR at current rate = 400 * $60 = $24,000.

Who replied / buying authority:
Maria S., People Operations Coordinator, replied on 2026-09-02.
She explicitly said she is not the right person for purchasing decisions.

Right buyer:
Dana R., VP People, last_engaged 2026-05-18.
Maria S. said budget and seat expansion sit with Dana R.

Reply email:
Hi Maria,

Thanks — really glad to hear the team loves Bonusly, and I appreciate the context.

The usage trend backs up what you’re seeing: monthly active users grew from 88 in March to 126 in August, which puts you at 84% of your 150 licensed seats.

If Dana has been asking about usage numbers, I’d be happy to send over a concise view of current adoption and what seat headroom could look like. No pressure — if helpful, would you be open to introducing me to Dana, or should I send you a short note you can forward?

Best,
Cole
onboarding-statusPASS 1.00

? The Question

Prep the CSM for the mid-onboarding call: what is complete (integrations connected, allowance set, admins added, first recognition given, first redemption), what is not, early engagement signals, and the three things to cover on the call. Mark nothing complete without a data field that shows it.
cost $0.3174 · 65s · in 25,641 / out 5,880 tok
✓ complete_items✓ incomplete_items✓ three_items✓ grounded

✓ Correct Answer (ground truth)

company_alias: C-0D284E42
days_live: 25
checklist: {"slack_integration_connected": {"complete": true, "field": "integration_slack", "value": "2026-08-12"}, "hris_integration_connected": {"complete": false, "field": "integration_hris", "value": ""}, "a
engagement_signals: avg_active_givers_week1=4.3; avg_active_givers_last_week=13.0; latest_active_givers=15; days_with_activity=25
call_items: Connect the HRIS integration (integration_hris is empty) to automate user provisioning and offboarding., Get to first redemption (first_redemption_at is empty): walk admins through the rewards catalog and confirm allowance funding., Build the giving habit: daily active givers averaged 4.3 in week 1 vs 13.0 last week - agree on manager nudges and a recognition cadence.
graded checks: complete_items · incomplete_items · three_items · grounded

Model's actual answer

show the model's full answer
CSM mid-onboarding prep for C-0D284E42

Complete:
- Slack integration connected: integration_slack = 2026-08-12
  - Arithmetic: 2026-08-12 - signup_date 2026-08-11 = 1 day after signup
- Allowance set: allowance_set = 2026-08-13
  - Arithmetic: 2026-08-13 - 2026-08-11 = 2 days after signup
- Admins added: admins_added = 2
- First recognition given: first_recognition_at = 2026-08-15 14:22
  - Arithmetic: 2026-08-15 - 2026-08-11 = 4 days after signup

Not complete:
- HRIS integration: integration_hris is blank
- First redemption: first_redemption_at is blank

Early engagement signals:
- Usage data covers 2026-08-11 through 2026-09-04 = 25 daily rows
- Active givers increased from 3 to 15
  - Arithmetic: 15 - 3 = 12 more active givers
  - Growth: 12 / 3 = 4.00 = 400% increase
  - Ending level: 15 / 3 = 5.0x starting level
- Total active-giver days:
  - 3+3+4+4+5+4+7+5+7+6+9+8+9+9+9+11+10+10+11+13+11+13+13+15+15 = 214
  - Average: 214 / 25 = 8.56 active givers per day
- First 7 days average:
  - 3+3+4+4+5+4+7 = 30
  - 30 / 7 = 4.29 active givers per day
- Last 7 days average:
  - 11+13+11+13+13+15+15 = 91
  - 91 / 7 = 13.00 active givers per day
- Change in 7-day average:
  - 13.00 - 4.29 = 8.71 more active givers per day
  - 8.71 / 4.29 = 203% increase

Three things to cover on the call:
1. HRIS integration: integration_hris is blank, so confirm blocker, owner, and target date.
2. First redemption: first_redemption_at is blank, so confirm what is preventing the first redemption and what action is needed.
3. Engagement expansion: active givers rose from 3 to 15, with the last 7-day average at 13.00 vs. first 7-day average of 4.29; discuss what drove early adoption and how C-0D284E42 will sustain or expand it.
renewal-risk-conflicting-datesPASS 1.00

? The Question

Produce a 90-day renewal risk brief. Two systems hold renewal dates and disagree on some accounts; decide which to trust per account and say why (multi-year contracts are known to be wrong in ChurnZero). For every renewal: company, CSM, ARR, date used, seat utilization, 3-month usage trend, risk rating with one sentence of evidence. Flag every disagreement. Close with total ARR renewing and ARR at risk.
cost $1.0382 · 176s · in 72,303 / out 21,601 tok
✓ total_renewing✓ arr_at_risk✓ disagreements_flagged✓ trust_rule

✓ Correct Answer (ground truth)

snapshot_date: 2026-09-05
window: 2026-09-05 to 2026-12-04
trust_rule: multi-year contracts: Chargebee is authoritative (ChurnZero known wrong); otherwise systems agree or Chargebee wins
accounts: 20 items — e.g. account_alias=C-0B144C78; csm=Cole Ingram; arr=30899.00; trusted_renewal_date=2026-11-02; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=75.4; usage_3m_ratio=1.03; risk=low; evidence=3-month usage ratio 1.03 (last3 avg 103 vs prior3 100), seat utilization 75% | account_alias=C-0B20DB64; csm=Dana Mercer; arr=21770.00; trusted_renewal_date=2026-10-07; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=56.6; usage_3m_ratio=1.0; risk=medium; evidence=3-month usage ratio 1.00 (last3 avg 295 vs prior3 295), seat utilization 57% | account_alias=C-0B344485; csm=Elena Sinclair; arr=64384.00; trusted_renewal_date=2026-11-16; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=78.0; usage_3m_ratio=1.04; risk=low; evidence=3-month usage ratio 1.04 (last3 avg 241 vs prior3 231), seat utilization 78% | account_alias=C-0B369871; csm=Dana Mercer; arr=85128.00; trusted_renewal_date=2026-10-29; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=75.1; usage_3m_ratio=1.04; risk=low; evidence=3-month usage ratio 1.04 (last3 avg 330 vs prior3 316), seat utilization 75%
disagreements: account_alias=C-0B7D2C30; cz_renewal_date=2026-09-10; cb_renewal_date=2026-09-15; is_multi_year=True; trusted=2026-09-15 | account_alias=C-0BBE3E60; cz_renewal_date=2027-09-26; cb_renewal_date=2026-09-26; is_multi_year=True; trusted=2026-09-26 | account_alias=C-0BCDB8C2; cz_renewal_date=2027-09-18; cb_renewal_date=2026-09-18; is_multi_year=True; trusted=2026-09-18 | account_alias=C-0D2AB865; cz_renewal_date=2026-09-10; cb_renewal_date=2026-09-22; is_multi_year=True; trusted=2026-09-22 | account_alias=C-0F5D2323; cz_renewal_date=2026-09-10; cb_renewal_date=2026-09-29; is_multi_year=True; trusted=2026-09-29
n_disagreements: 5
total_arr_renewing_90d: 1048715.00
arr_at_risk_90d: 359409.00
n_accounts: 20
graded checks: total_renewing · arr_at_risk · disagreements_flagged · trust_rule

Model's actual answer

show the model's full answer
90-day renewal risk brief

Data missing:
- No formal risk-rating rubric was provided.
- No formal definition of “ARR at risk” was provided.

Rules used:
- Renewal date: use Chargebee when ChurnZero disagrees on a multi-year contract, because multi-year contracts are known to be wrong in ChurnZero.
- Risk rating: High = utilization below 50% or 3-month active-user decline of 10%+; Medium = utilization 50.0%-69.9% or decline of 5.0%-9.9%; Low = utilization 70%+ and usage not down 5%+.
- ARR at risk = High-risk ARR + Medium-risk ARR.

1. C-0B7D2C30
CSM: Dana Mercer
ARR: $65,901
Date used: 2026-09-15
Disagreement: ChurnZero = 2026-09-10; Chargebee = 2026-09-15; used Chargebee because term is 36 months and multi-year contracts are known to be wrong in ChurnZero.
Seat utilization: 274 / 476 = 57.6%
3-month usage trend: 97 -> 94 -> 84; change = 84 - 97 = -13; -13 / 97 = -13.4%
Risk rating: High — usage declined 13.4%, crossing the 10%+ decline threshold.

2. C-0BCDB8C2
CSM: Cole Ingram
ARR: $54,427
Date used: 2026-09-18
Disagreement: ChurnZero = 2027-09-18; Chargebee = 2026-09-18; used Chargebee because term is 36 months and multi-year contracts are known to be wrong in ChurnZero.
Seat utilization: 232 / 424 = 54.7%
3-month usage trend: 127 -> 118 -> 110; change = 110 - 127 = -17; -17 / 127 = -13.4%
Risk rating: High — usage declined 13.4%, crossing the 10%+ decline threshold.

3. C-0D2AB865
CSM: Elena Sinclair
ARR: $38,022
Date used: 2026-09-22
Disagreement: ChurnZero = 2026-09-10; Chargebee = 2026-09-22; used Chargebee because term is 24 months and multi-year contracts are known to be wrong in ChurnZero.
Seat utilization: 250 / 407 = 61.4%
3-month usage trend: 125 -> 117 -> 109; change = 109 - 125 = -16; -16 / 125 = -12.8%
Risk rating: High — usage declined 12.8%, crossing the 10%+ decline threshold.

4. C-0BBE3E60
CSM: Dana Mercer
ARR: $30,993
Date used: 2026-09-26
Disagreement: ChurnZero = 2027-09-26; Chargebee = 2026-09-26; used Chargebee because term is 24 months and multi-year contracts are known to be wrong in ChurnZero.
Seat utilization: 74 / 114 = 64.9%
3-month usage trend: 39 -> 35 -> 33; change = 33 - 39 = -6; -6 / 39 = -15.4%
Risk rating: High — usage declined 15.4%, crossing the 10%+ decline threshold.

5. C-0F5D2323
CSM: Cole Ingram
ARR: $90,647
Date used: 2026-09-29
Disagreement: ChurnZero = 2026-09-10; Chargebee = 2026-09-29; used Chargebee because term is 24 months and multi-year contracts are known to be wrong in ChurnZero.
Seat utilization: 111 / 390 = 28.5%
3-month usage trend: 20 -> 21 -> 18; change = 18 - 20 = -2; -2 / 20 = -10.0%
Risk rating: High — utilization is only 28.5% and usage declined 10.0%.

6. C-0EC6999D
CSM: Elena Sinclair
ARR: $79,419
Date used: 2026-10-03
Disagreement: none; ChurnZero = 2026-10-03 and Chargebee = 2026-10-03.
Seat utilization: 31 / 112 = 27.7%
3-month usage trend: 17 -> 16 -> 15; change = 15 - 17 = -2; -2 / 17 = -11.8%
Risk rating: High — utilization is only 27.7% and usage declined 11.8%.

7. C-0B20DB64
CSM: Dana Mercer
ARR: $21,770
Date used: 2026-10-07
Disagreement: none; ChurnZero = 2026-10-07 and Chargebee = 2026-10-07.
Seat utilization: 214 / 378 = 56.6%
3-month usage trend: 294 -> 298 -> 294; change = 294 - 294 = 0; 0 / 294 = 0.0%
Risk rating: Medium — usage is flat, but utilization is only 56.6%.

8. C-0BBC4E7A
CSM: Cole Ingram
ARR: $56,374
Date used: 2026-10-10
Disagreement: none; ChurnZero = 2026-10-10 and Chargebee = 2026-10-10.
Seat utilization: 228 / 337 = 67.7%
3-month usage trend: 142 -> 141 -> 139; change = 139 - 142 = -3; -3 / 142 = -2.1%
Risk rating: Medium — utilization is below 70% at 67.7%, with a slight 2.1% usage decline.

9. C-0FD551AB
CSM: Elena Sinclair
ARR: $48,815
Date used: 2026-10-14
Disagreement: none; ChurnZero = 2026-10-14 and Chargebee = 2026-10-14.
Seat utilization: 210 / 376 = 55.9%
3-month usage trend: 123 -> 122 -> 126; change = 126 - 123 = 3; 3 / 123 = 2.4%
Risk rating: Medium — usage increased 2.4%, but utilization is only 55.9%.

10. C-0F9F8F13
CSM: Dana Mercer
ARR: $46,230
Date used: 2026-10-18
Disagreement: none; ChurnZero = 2026-10-18 and Chargebee = 2026-10-18.
Seat utilization: 199 / 352 = 56.5%
3-month usage trend: 185 -> 185 -> 182; change = 182 - 185 = -3; -3 / 185 = -1.6%
Risk rating: Medium — utilization is only 56.5%, while usage is roughly flat with a 1.6% decline.

11. C-0BC34584
CSM: Cole Ingram
ARR: $16,740
Date used: 2026-10-22
Disagreement: none; ChurnZero = 2026-10-22 and Chargebee = 2026-10-22.
Seat utilization: 327 / 494 = 66.2%
3-month usage trend: 104 -> 104 -> 106; change = 106 - 104 = 2; 2 / 104 = 1.9%
Risk rating: Medium — usage increased 1.9%, but utilization is below 70% at 66.2%.

12. C-0B7A7546
CSM: Elena Sinclair
ARR: $35,062
Date used: 2026-10-25
Disagreement: none; ChurnZero = 2026-10-25 and Chargebee = 2026-10-25.
Seat utilization: 182 / 205 = 88.8%
3-month usage trend: 64 -> 65 -> 63; change = 63 - 64 = -1; -1 / 64 = -1.6%
Risk rating: Low — utilization is strong at 88.8% and usage declined only 1.6%.

13. C-0B369871
CSM: Dana Mercer
ARR: $85,128
Date used: 2026-10-29
Disagreement: none; ChurnZero = 2026-10-29 and Chargebee = 2026-10-29.
Seat utilization: 317 / 422 = 75.1%
3-month usage trend: 326 -> 330 -> 333; change = 333 - 326 = 7; 7 / 326 = 2.1%
Risk rating: Low — utilization is 75.1% and usage increased 2.1%.

14. C-0B144C78
CSM: Cole Ingram
ARR: $30,899
Date used: 2026-11-02
Disagreement: none; ChurnZero = 2026-11-02 and Chargebee = 2026-11-02.
Seat utilization: 169 / 224 = 75.4%
3-month usage trend: 101 -> 101 -> 106; change = 106 - 101 = 5; 5 / 101 = 5.0%
Risk rating: Low — utilization is 75.4% and usage increased 5.0%.

15. C-0FC4DBB8
CSM: Elena Sinclair
ARR: $94,732
Date used: 2026-11-05
Disagreement: none; ChurnZero = 2026-11-05 and Chargebee = 2026-11-05.
Seat utilization: 356 / 464 = 76.7%
3-month usage trend: 189 -> 191 -> 193; change = 193 - 189 = 4; 4 / 189 = 2.1%
Risk rating: Low — utilization is 76.7% and usage increased 2.1%.

16. C-0D5BBE3A
CSM: Dana Mercer
ARR: $39,740
Date used: 2026-11-09
Disagreement: none; ChurnZero = 2026-11-09 and Chargebee = 2026-11-09.
Seat utilization: 85 / 102 = 83.3%
3-month usage trend: 88 -> 90 -> 91; change = 91 - 88 = 3; 3 / 88 = 3.4%
Risk rating: Low — utilization is 83.3% and usage increased 3.4%.

17. C-0FB9D5AF
CSM: Cole Ingram
ARR: $63,158
Date used: 2026-11-13
Disagreement: none; ChurnZero = 2026-11-13 and Chargebee = 2026-11-13.
Seat utilization: 144 / 199 = 72.4%
3-month usage trend: 173 -> 173 -> 176; change = 176 - 173 = 3; 3 / 173 = 1.7%
Risk rating: Low — utilization is 72.4% and usage increased 1.7%.

18. C-0B344485
CSM: Elena Sinclair
ARR: $64,384
Date used: 2026-11-16
Disagreement: none; ChurnZero = 2026-11-16 and Chargebee = 2026-11-16.
Seat utilization: 224 / 287 = 78.0%
3-month usage trend: 238 -> 240 -> 244; change = 244 - 238 = 6; 6 / 238 = 2.5%
Risk rating: Low — utilization is 78.0% and usage increased 2.5%.

19. C-0CB2C1B4
CSM: Dana Mercer
ARR: $40,628
Date used: 2026-11-20
Disagreement: none; ChurnZero = 2026-11-20 and Chargebee = 2026-11-20.
Seat utilization: 386 / 473 = 81.6%
3-month usage trend: 47 -> 48 -> 49; change = 49 - 47 = 2; 2 / 47 = 4.3%
Risk rating: Low — utilization is 81.6% and usage increased 4.3%.

20. C-22170CA1
CSM: Cole Ingram
ARR: $45,646
Date used: 2026-11-24
Disagreement: none; ChurnZero = 2026-11-24 and Chargebee = 2026-11-24.
Seat utilization: 251 / 294 = 85.4%
3-month usage trend: 143 -> 148 -> 146; change = 146 - 143 = 3; 3 / 143 = 2.1%
Risk rating: Low — utilization is 85.4% and usage increased 2.1%.

Disagreements flagged:
- C-0B7D2C30: ChurnZero 2026-09-10 vs Chargebee 2026-09-15; used Chargebee due to 36-month multi-year term.
- C-0BCDB8C2: ChurnZero 2027-09-18 vs Chargebee 2026-09-18; used Chargebee due to 36-month multi-year term.
- C-0D2AB865: ChurnZero 2026-09-10 vs Chargebee 2026-09-22; used Chargebee due to 24-month multi-year term.
- C-0BBE3E60: ChurnZero 2027-09-26 vs Chargebee 2026-09-26; used Chargebee due to 24-month multi-year term.
- C-0F5D2323: ChurnZero 2026-09-10 vs Chargebee 2026-09-29; used Chargebee due to 24-month multi-year term.

Totals:
Total ARR renewing:
$65,901 + $54,427 + $38,022 + $30,993 + $90,647 + $79,419 + $21,770 + $56,374 + $48,815 + $46,230 + $16,740 + $35,062 + $85,128 + $30,899 + $94,732 + $39,740 + $63,158 + $64,384 + $40,628 + $45,646 = $1,048,715

High-risk ARR:
$65,901 + $54,427 + $38,022 + $30,993 + $90,647 + $79,419 = $359,409

Medium-risk ARR:
$21,770 + $56,374 + $48,815 + $46,230 + $16,740 = $189,929

ARR at risk:
$359,409 + $189,929 = $549,338
ticket-theme-synthesis0.80

? The Question

Synthesize the quarter's support tickets into 4 to 7 themes. Do not trust existing tags; read the text. Per theme: name, count, share, distinct accounts, ARR affected, two ticket ids, one-line recommendation. Separate broad patterns from single-account noise and rank by ARR exposure, not volume.
cost $0.6862 · 411s · in 42,920 / out 14,995 tok
✗ theme_count_range✓ counts_verifiable✓ single_account_flagged✓ arr_ranked✓ ticket_ids

✓ Correct Answer (ground truth)

quarter_window: 2026-06-01 through 2026-08-31
total_tickets: 80
themes: {"points_not_posting": {"count": 20, "share_pct": 25.0, "distinct_accounts": 9, "arr_affected": "31100.00", "example_ticket_ids": ["IC-460001", "IC-460002"], "single_account": false}, "slack_sync": {"
ranking_by_arr_exposure: hris_provisioning, redemption_failures, billing_dispute, points_not_posting, slack_sync
single_account_noise_theme: billing_dispute
note: existing tags are noisy/unreliable; classify by text
sample_ticket_ids: 80 items — e.g. IC-460004, IC-460016, IC-460001, IC-460041
graded checks: theme_count_range · counts_verifiable · single_account_flagged · arr_ranked · ticket_ids

Model's actual answer

show the model's full answer
Total tickets: 80
ARR affected calculation: sum each distinct account’s ARR once per theme.

Broad patterns ranked by ARR exposure:

1. HRIS provisioning / sync failures
- Count: 12
- Share: 12 / 80 = 15.0%
- Distinct accounts: 3 — C-0B2213A9, C-0F6C0F34, C-0DDFC9A7
- ARR affected: $36,000 + $30,000 + $48,000 = $114,000
- Ticket ids: IC-460059, IC-460062
- Recommendation: Prioritize HRIS sync/provisioning fixes and add alerting for silent skipped-new-hire failures.

2. Redemption / gift card checkout failures
- Count: 18
- Share: 18 / 80 = 22.5%
- Distinct accounts: 7 — C-0CEF69FD, C-0B827671, C-0FCCD2DF, C-0F876796, C-14264ABD, C-0D9CA315, C-0B0F1BAB
- ARR affected: $8,900 + $10,700 + $9,600 + $8,700 + $11,000 + $9,600 + $10,300 = $68,800
- Ticket ids: IC-460025, IC-460024
- Recommendation: Treat failed redemptions with deducted points as a cross-account product incident and add automated refund/retry handling.

3. Recognition points not posting / balances not updating
- Count: 20
- Share: 20 / 80 = 25.0%
- Distinct accounts: 9 — C-0D3278C7, C-0BF20542, C-0D0B047C, C-0BE96399, C-0D284E42, C-0D6CC8E3, C-21FEBCBB, C-0DD0626C, C-0B2895EF
- ARR affected: $3,500 + $4,500 + $4,500 + $2,700 + $3,400 + $4,200 + $2,900 + $2,500 + $2,900 = $31,100
- Ticket ids: IC-460004, IC-460016
- Recommendation: Investigate the recognition-to-points posting pipeline and proactively reconcile missing balances for affected accounts.

4. Slack integration / sync / auth / command failures
- Count: 14
- Share: 14 / 80 = 17.5%
- Distinct accounts: 4 — C-0B843542, C-10A56B0F, C-0BA71F12, C-8C2E8F00
- ARR affected: $4,400 + $5,400 + $3,900 + $5,200 = $18,900
- Ticket ids: IC-460041, IC-460047
- Recommendation: Fix Slack auth persistence, recognition sync, and slash-command reliability before asking admins to re-authenticate.

Single-account noise:

5. Billing invoice / seat-count / tier-price errors
- Count: 16
- Share: 16 / 80 = 20.0%
- Distinct accounts: 1 — C-0E9C27D1
- ARR affected: $52,000 = $52,000
- Ticket ids: IC-460071, IC-460069
- Recommendation: Escalate C-0E9C27D1 to Finance/RevOps for account-specific billing reconciliation, but do not treat it as a broad product pattern without more affected accounts.
marketing
case-study-matchPASS 1.00

? The Question

Given the prospect, rank the three most similar existing customers with public case studies for use as social proof. Similarity on industry, size band, use case, region. Cite the fields that drove each match. Do not name any customer without a case study and never include billing data or contact names.
cost $0.2732 · 245s · in 24,941 / out 4,522 tok
✓ top3✓ decoys_excluded✓ cites_fields✓ no_billing

✓ Correct Answer (ground truth)

top3: company_alias=C-11C31562; similarity_score=3 | company_alias=C-64171065; similarity_score=3 | company_alias=C-A13C193D; similarity_score=3
decoys_excluded: company_alias=C-D6217CAA; similarity_score=4; reason=no_case_study | company_alias=C-C153868F; similarity_score=4; reason=no_case_study
constraints: no_billing_data, no_contact_names, only_customers_with_has_case_study_true_named
prospect_fields_used: industry, size_band, use_case, region
prospect_alias: C-82AF3719
graded checks: top3 · decoys_excluded · cites_fields · no_billing

Model's actual answer

show the model's full answer
Prospect C-82AF3719:
industry=Technology, size_band=Mid-Market, use_case=employee_recognition, region=NA-West

Top 3 existing customers with public case studies:

1. C-11C31562 — 3/4 match
Arithmetic: 0 industry + 1 size_band + 1 use_case + 1 region = 3
Fields:
industry=Manufacturing does not match Technology
size_band=Mid-Market matches Mid-Market
use_case=employee_recognition matches employee_recognition
region=NA-West matches NA-West
has_case_study=true

2. C-64171065 — 3/4 match
Arithmetic: 1 industry + 1 size_band + 1 use_case + 0 region = 3
Fields:
industry=Technology matches Technology
size_band=Mid-Market matches Mid-Market
use_case=employee_recognition matches employee_recognition
region=NA-East does not match NA-West
has_case_study=true

3. C-A13C193D — 3/4 match
Arithmetic: 1 industry + 1 size_band + 0 use_case + 1 region = 3
Fields:
industry=Technology matches Technology
size_band=Mid-Market matches Mid-Market
use_case=retention does not match employee_recognition
region=NA-West matches NA-West
has_case_study=true

All three are tied at 3/4 similarity. No provided weighting distinguishes industry, size_band, use_case, and region, so there is no data-backed tie-breaker.
channel-attribution-mathPASS 1.00

? The Question

Compute channel performance for the trailing 6 months. Paid: spend, SQMs, SQOs, cost per SQM, cost per SQO, SQM-to-SQO rate, pipeline amount, pipeline per dollar. Organic: volume, SQO rate, pipeline. Report a channel with spend and zero SQMs as undefined, not zero. Flag rows where SQO date precedes SQM date. Finish with a reallocation recommendation and your confidence given sample sizes.
cost $0.8310 · 635s · in 69,551 / out 14,756 tok
✓ undefined_channel✓ undefined_not_zero✓ flagged_rows✓ best_channel✓ reallocation

✓ Correct Answer (ground truth)

months: 2026-03, 2026-04, 2026-05, 2026-06, 2026-07, 2026-08
per_channel: {"linkedin_ads": {"spend_usd": 24000, "sqms": 25, "sqos": 8, "pipeline_amount": 96000, "cost_per_sqm": 960.0, "cost_per_sqo": 3000.0, "sqm_to_sqo_rate": 0.32, "pipeline_per_dollar": 4.0}, "organic_sea
undefined_channels: paid_social
flagged_rows_sqo_before_sqm: CT-000041, CT-000044
best_pipeline_per_dollar_channel: paid_search
reallocation_recommendation: from=paid_social; to=paid_search; rationale=paid_social has spend but zero SQMs (cost per SQM undefined, not zero); paid_search has the highest pipeline per dollar.
confidence_note: webinars and referral have small SQM samples (<20); treat rates as directional.
graded checks: undefined_channel · undefined_not_zero · flagged_rows · best_channel · reallocation

Model's actual answer

show the model's full answer
Trailing 6 months analyzed: 2026-03 through 2026-08.

PAID CHANNELS

channel         spend     SQMs  SQOs  cost/SQM              cost/SQO              SQM→SQO rate        pipeline                  pipeline/$
paid_search     $36,000   40    18    $36,000 / 40 = $900   $36,000 / 18 = $2,000 18 / 40 = 45.0%     18 x $40,000 = $720,000  $720,000 / $36,000 = $20.00
linkedin_ads    $24,000   25    8     $24,000 / 25 = $960   $24,000 / 8 = $3,000  8 / 25 = 32.0%      8 x $12,000 = $96,000    $96,000 / $24,000 = $4.00
paid_social     $18,000   0     0     undefined             undefined              undefined           $0                        $0 / $18,000 = $0.00
webinars        $9,000    12    5     $9,000 / 12 = $750    $9,000 / 5 = $1,800   5 / 12 = 41.7%      5 x $12,000 = $60,000    $60,000 / $9,000 = $6.67

Notes:
- paid_social has spend and zero SQMs, so cost/SQM, cost/SQO, and SQM→SQO rate are undefined, not zero.
- pipeline/$ for paid_social is $0.00 because spend is nonzero and pipeline is $0.

ORGANIC / NON-SPEND CHANNELS

channel          volume  SQOs  SQO rate           pipeline
organic_search   30      10    10 / 30 = 33.3%    10 x $9,000 = $90,000
referral         15      6     6 / 15 = 40.0%     6 x $8,000 = $48,000

ROWS WHERE SQO DATE PRECEDES SQM DATE

1. CT-000044
   channel: linkedin_ads
   SQM date: 2026-07-23
   SQO date: 2026-07-18
   pipeline_amount: $12,000

2. CT-000041
   channel: linkedin_ads
   SQM date: 2026-06-14
   SQO date: 2026-06-09
   pipeline_amount: $12,000

REALLOCATION RECOMMENDATION

Reallocate away from paid_social first. It spent $18,000 and produced 0 SQMs, 0 SQOs, and $0 pipeline in the provided data.

Priority for reallocated paid budget:

1. Increase paid_search.
   - Best pipeline efficiency: $20.00 pipeline per $1.
   - Largest paid sample: 40 SQMs and 18 SQOs.
   - Strongest SQM→SQO rate among paid channels: 45.0%.

2. Maintain or modestly increase webinars.
   - Best cost per SQO: $1,800.
   - Good pipeline efficiency: $6.67 pipeline per $1.
   - But sample size is smaller: 12 SQMs and 5 SQOs, so scale cautiously.

3. Hold or reduce linkedin_ads until data quality is fixed.
   - Lower pipeline efficiency: $4.00 pipeline per $1.
   - Higher cost per SQO: $3,000.
   - 2 of 8 SQOs have SQO dates before SQM dates, representing $24,000 of $96,000 pipeline.

Organic note:
- organic_search and referral generated $138,000 combined pipeline with no spend rows provided.
- No paid reallocation is possible directly from organic data, but these channels should be protected because they show meaningful SQO volume: 16 SQOs across 45 contacts.

Confidence: medium.

- paid_search recommendation confidence: high within this dataset, because it has the largest paid sample size and strongest economics.
- paid_social cut confidence: medium-high, because $18,000 produced no tracked SQMs, but this could also indicate missing attribution data.
- webinars scale-up confidence: medium-low, because performance is strong but based on only 12 SQMs and 5 SQOs.
- linkedin_ads caution confidence: medium, because it has 25 SQMs and 8 SQOs, but data-quality issues affect 2 SQO rows.
competitor-battlecard-updatePASS 1.00

? The Question

Update the battlecard for the competitor. Sections: one-line positioning, pricing with source and date (newer source wins, note the conflict), where they win, where we win, objections and responses, recent changes, our 12-month win/loss record against them. Cite a snippet id for every factual claim. Rep opinion on a call is not a fact about the competitor. Anything from the old card you cannot re-source gets marked unverified.
cost $0.5067 · 105s · in 32,617 / out 11,026 tok
✓ competitor_named✓ pricing✓ win_loss✓ unverified_marked✓ citations

✓ Correct Answer (ground truth)

competitor: Rivally
pricing: value_per_user_per_month=7; source_snippet=S17; source_date=2026-08-12
win_loss_12mo: wins=13; losses=7
unverified_old_claims: Rivally lacks a Slack integration., Rivally was acquired by WorkHuman in 2025.
rep_opinion_snippet_ids_not_facts: S09, S21
citation_ids_available: 25 items — e.g. S01, S02, S03, S04
graded checks: competitor_named · pricing · win_loss · unverified_marked · citations

Model's actual answer

show the model's full answer
Battlecard: Rivally

1. One-line positioning

Rivally is a points-based recognition competitor with an engaging recognition feed and expanding EU capabilities, but sourced reviews show limited analytics, basic reporting, SCIM/admin gaps, CSV-only analytics exports, and thinner EMEA rewards coverage. [S02, S07, S10, S12, S14, S15, S16, S20, S24]

2. Pricing with source and date

Current sourced pricing:
- 2026-08-12 pricing page: Rivally Recognition Starter is now $7 per user/month, annual billing required. [S17]

Conflict / older pricing:
- 2026-01-20 pricing page: Rivally Recognition was listed at $5 per user/month, annual billing required. [S03]
- 2026-04-01 pricing page: Rivally pricing page still showed $5 per user/month for Recognition Starter tier. [S08]
- Newer source wins, so the battlecard should use $7/user/month annual billing as the current sourced list price, while noting the prior $5/user/month conflict. [S03, S08, S17]

Deal-level pricing mentions:
- 2026-06-02 call notes: Rivally quoted $6.50/user/month to a 500-seat prospect on an annual term. [S13]
- 2026-08-14 call notes: prospect said Rivally quoted $7/user/month list and offered a 15% discount for a 3-year term. [S18]

Add-on pricing:
- Rivally Pulse exited beta and is priced as an add-on, not bundled, as of 2026-09-01. [S23]

3. Where they win

- Recognition engagement: reviewers praise Rivally’s points-based recognition feed and describe the recognition feed as engaging. [S02, S16]
- Fast setup and Slack: a mid-market reviewer said setup took under a week and Slack integration worked out of the box. [S04]
- EU story: Rivally pitched EU data residency in a prospect evaluation, opened a Dublin office, and announced EU data residency generally available. [S05, S15]
- Distributed EU teams: an EU enterprise reviewer said Rivally is strong for distributed EU teams and praised multi-language support. [S12]
- Support responsiveness: a G2 review praised Rivally support response time as under 4 hours. [S22]
- Product expansion: Rivally launched Rivally Pulse as a lightweight engagement survey add-on, announced Microsoft Teams app v2 in public preview, and later moved Pulse out of beta as a separately priced add-on. [S06, S19, S23]

4. Where we win

- Analytics depth: Rivally has limited analytics, basic reporting dashboards, and CSV-only analytics exports; one 800-seat prospect picked Bonusly over Rivally citing analytics depth. [S02, S07, S20, S25]
- Enterprise admin / IT readiness: Rivally lacks SCIM provisioning, manual user management is painful, admin tooling lags peers, and the admin console lacks bulk recognition editing. [S10, S16, S24]
- EMEA rewards coverage: Rivally’s EMEA rewards catalog is thinner than its US catalog. [S14]

5. Objections and responses

Objection: “Rivally is cheaper.”
Response: Use the newest sourced pricing. Rivally’s current pricing page says Recognition Starter is $7/user/month with annual billing required as of 2026-08-12, which supersedes older $5/user/month pricing from 2026-01-20 and 2026-04-01. [S03, S08, S17] If a prospect cites discounts, note that one prospect reported $7/user/month list with a 15% discount only for a 3-year term. [S18]

Objection: “Rivally is better for EU teams.”
Response: Acknowledge the sourced strengths: Rivally pitched EU data residency, opened a Dublin office, announced EU data residency generally available, and received praise from an EU enterprise reviewer for distributed EU teams and multi-language support. [S05, S12, S15] Then test the operational fit: sourced reviews also say Rivally lacks SCIM provisioning, has painful manual user management, and has a thinner EMEA rewards catalog than its US catalog. [S10, S14]

Objection: “Rivally has Slack; that neutralizes Bonusly.”
Response: Do not claim Rivally lacks Slack. The old card’s Slack claim is contradicted by a 2026-02-02 review saying Slack integration worked out of the box. [S04]

Objection: “Rivally has strong analytics.”
Response: The sourced data does not support that. Reviews say Rivally has limited analytics, basic reporting dashboards, and CSV-only analytics exports; one 800-seat prospect picked Bonusly over Rivally citing analytics depth. [S02, S07, S20, S25]

Objection: “Rivally is enterprise-ready.”
Response: Separate EU presence from enterprise IT readiness. Rivally has EU data residency and multi-language support evidence, but reviews also cite lack of SCIM provisioning, painful manual user management, lagging admin tooling, and no bulk recognition editing. [S10, S12, S15, S16, S24]

6. Recent changes

- 2025-11-04: Rivally announced a $40M Series C led by Northgate Ventures. [S01]
- 2026-03-05: Rivally launched Rivally Pulse, a lightweight engagement survey add-on. [S06]
- 2026-05-09: Rivally hired an ex-Workday VP EMEA to lead European expansion. [S11]
- 2026-07-01: Rivally opened a Dublin office and announced EU data residency generally available. [S15]
- 2026-08-12: Rivally pricing page updated Recognition Starter to $7/user/month, annual billing required. [S17]
- 2026-08-20: Rivally announced Microsoft Teams app v2 in public preview. [S19]
- 2026-09-01: Rivally Pulse exited beta and is priced as an add-on, not bundled. [S23]

7. Our 12-month win/loss record against Rivally

Data note: deals_with_competitor.csv has deal aliases, months, outcomes, and competitor name, but no snippet IDs. The deal aliases below are cited exactly as provided.

Timeframe:
- 2025-09 through 2026-08.

Arithmetic:
- Total Rivally deals = 20.
- Wins = 13.
- Losses = 7.
- Win rate = 13 wins / 20 total deals = 0.65 = 65%.
- Loss rate = 7 losses / 20 total deals = 0.35 = 35%.
- Win/loss ratio = 13 wins / 7 losses = 1.86 wins per loss.

Wins:
- Deal-A9FD43, 2025-10
- Deal-7AA785, 2025-11
- Deal-44C524, 2025-12
- Deal-0D0CD6, 2026-01
- Deal-D5B790, 2026-02
- Deal-5C636E, 2026-03
- Deal-67BE14, 2026-06
- Deal-1B6969, 2026-07
- Deal-F03E7B, 2026-08
- Deal-072E31, 2025-09
- Deal-F65C8F, 2025-10
- Deal-E46EAB, 2026-01
- Deal-1D2392, 2026-02

Losses:
- Deal-7767F5, 2025-09
- Deal-5645A5, 2026-04
- Deal-C6FFAA, 2026-05
- Deal-D263E0, 2025-11
- Deal-935746, 2025-12
- Deal-9066A6, 2026-03
- Deal-72A02F, 2026-04

Monthly record:
- 2025-09: 1 win, 1 loss.
- 2025-10: 2 wins, 0 losses.
- 2025-11: 1 win, 1 loss.
- 2025-12: 1 win, 1 loss.
- 2026-01: 2 wins, 0 losses.
- 2026-02: 2 wins, 0 losses.
- 2026-03: 1 win, 1 loss.
- 2026-04: 0 wins, 2 losses.
- 2026-05: 0 wins, 1 loss.
- 2026-06: 1 win, 0 losses.
- 2026-07: 1 win, 0 losses.
- 2026-08: 1 win, 0 losses.

8. Old battlecard claims marked updated / unverified

- “Positioning: points-based recognition for mid-market.” Partially sourced. Points-based recognition is sourced, but “mid-market” as overall positioning is not fully sourced; the only mid-market source is a reviewer describing setup and Slack integration. [S02, S04]
- “Pricing: starts at $5 per user/month, annual billing (as of 2026-01).” Outdated. It was sourced in January and still shown in April, but the newer 2026-08-12 pricing page says $7/user/month annual billing required. [S03, S08, S17]
- “Rivally lacks a Slack integration.” Contradicted. A 2026-02-02 G2 review says Slack integration worked out of the box. [S04]
- “Rivally was acquired by WorkHuman in 2025.” Unverified. No provided snippet supports a WorkHuman acquisition; the provided 2025 corporate event is a $40M Series C led by Northgate Ventures. [S01]
- “Strong in EU enterprise with multi-language support.” Sourced. An EU enterprise reviewer said Rivally is strong for distributed EU teams and praised multi-language support. [S12]

Excluded as competitor facts:
- AE opinion that Rivally’s UI feels clunky is not verified against the product, so it should not be treated as a competitor fact. [S09]
- AE opinion that Rivally is discounting aggressively is rep opinion and not confirmed, so it should not be treated as a competitor fact. [S21]
nurture-sequence-diagnosisPASS 1.00

? The Question

Review the sequences. Per sequence: sent, open rate, reply rate, meeting rate, weakest step. Identify tracking errors (opened above sent), audience overlap between sequences, and the failure mode for anything under 2 percent reply. One change per weak sequence and which to fix first. Under 350 words.
cost $0.6538 · 106s · in 60,264 / out 11,289 tok
✓ tracking_error✓ overlap_pair✓ weakest_step✓ fix_priority

✓ Correct Answer (ground truth)

per_sequence: {"New Logo Nurture": {"sent": 1386, "opened": 490, "replied": 90, "meetings": 27, "open_rate": 0.3535, "reply_rate": 0.0649, "meeting_rate": 0.0195, "weakest_step": 3}, "Expansion Nurture": {"sent": 8
tracking_error: sequence=Expansion Nurture; step=2; sent=300; opened=340; issue=opened exceeds sent
audience_overlap_pair: Cold Outbound - HR Leaders, Cold Outbound - People Ops
all_pairwise_overlaps: ['Cold Outbound - HR Leaders', 'Cold Outbound - People Ops'], ['Expansion Nurture', 'New Logo Nurture']
under_2pct_reply: Cold Outbound - HR Leaders
failure_mode: Cold Outbound - HR Leaders=opens healthy (~37%) but replies near zero from step 1 -> body/CTA not landing, not a deliverability or subject-line problem
fix_priority_first: Cold Outbound - HR Leaders
graded checks: tracking_error · overlap_pair · weakest_step · fix_priority

Model's actual answer

show the model's full answer
Sequence metrics:
- New Logo Nurture: sent 500+458+428=1,386; open 490/1,386=35.4%; reply 90/1,386=6.5%; meeting 27/1,386=1.9%. Weakest step: step 3, 18/428=4.2% replies.
- Expansion Nurture: sent 300+300+275=875; open 565/875=64.6% invalid; reply 59/875=6.7%; meeting 12/875=1.4%. Weakest step: step 3, 12/275=4.4% replies.
- Cold Outbound - HR Leaders: sent 600+595+590=1,785; open 545/1,785=30.5%; reply 8/1,785=0.4%; meeting 0/1,785=0.0%. Weakest step: step 3, 1/590=0.2% replies.
- Cold Outbound - People Ops: sent 400+386+377=1,163; open 340/1,163=29.2%; reply 29/1,163=2.5%; meeting 6/1,163=0.5%. Weakest step: step 3, 6/377=1.6% replies.

Tracking errors:
- Expansion Nurture step 2: opened 340 > sent 300; impossible, so open-rate reporting is unreliable.

Audience overlap:
- New Logo Nurture + Expansion Nurture: CT-000301, CT-000624.
- Cold Outbound - HR Leaders + Cold Outbound - People Ops: CT-000849, CT-000884, CT-000890, CT-000908, CT-001033, CT-001097, CT-001101, CT-001103, CT-001105, CT-001130, CT-001153, CT-001159, CT-001217, CT-001227, CT-001236, CT-001255, CT-001258, CT-001277, CT-001285, CT-001311, CT-001345.

Under-2% reply failure modes:
- Cold Outbound - HR Leaders: 8/1,785=0.4%; opens exist, but replies and meetings do not. Failure is post-open conversion/offer fit.
- Cold Outbound - People Ops step 3: 6/377=1.6%; late-step drop-off.

Changes:
- Expansion Nurture: fix step 2 open tracking.
- Cold Outbound - HR Leaders: rewrite offer/CTA and suppress overlapping People Ops contacts.
- Cold Outbound - People Ops: replace or cut step 3.

Fix first: Cold Outbound - HR Leaders; largest send volume and 0 meetings.
weekly-marketing-goals-rollupPASS 1.00

? The Question

Produce the weekly marketing goals update for the active quarter: SQMs, SQOs, DS2s, closed-lost MIA rate, same-quarter close count, active pipeline coverage against target. For each: QTD actual, target, delta, pace (on/behind/ahead given days elapsed). One paragraph on what moved this week.
cost $0.2548 · 70s · in 21,785 / out 4,401 tok
✓ metrics_present✓ deltas✓ coverage_ratio✓ pace✓ paragraph

✓ Correct Answer (ground truth)

days_elapsed: 66
days_in_quarter: 92
elapsed_fraction: 0.7174
metrics: {"SQMs": {"qtd_actual": 230, "target": 300, "delta": -70, "expected_at_day_elapsed": 215.22, "pace": "ahead"}, "SQOs": {"qtd_actual": 84, "target": 120, "delta": -36, "expected_at_day_elapsed": 86.09,
coverage_ratio_active_pipeline: 0.75
pace_rule: expected = target * days_elapsed/days_in_quarter; within +/-5% of expected = on, above = ahead, below = behind; lower_better metrics invert.
this_week_paragraph_required: True
graded checks: metrics_present · deltas · coverage_ratio · pace · paragraph

Model's actual answer

show the model's full answer
Quarter: Q3-2026. Days elapsed: 66 / 92 = 71.7%.

| Metric | QTD actual | Target | Delta vs target | Pace |
|---|---:|---:|---:|---|
| SQMs | 230 | 300 | -70 | ahead |
| SQOs | 84 | 120 | -36 | behind |
| DS2s | 40 | 75 | -35 | behind |
| Closed-lost MIA rate | 5 / 25 = 20.0% | 10.0% | +10.0 pp | behind |
| Same-quarter closes | 10 | 20 | -10 | behind |
| Active pipeline coverage against target | $3,000,000 / $4,000,000 = 75.0% | 100.0% | -25.0 pp; -$1,000,000 | ahead |

Arithmetic:
SQMs: 230 / 300 = 76.7%; 76.7% vs 71.7% elapsed = ahead.
SQOs: 84 / 120 = 70.0%; 70.0% vs 71.7% elapsed = behind.
DS2s: 40 / 75 = 53.3%; 53.3% vs 71.7% elapsed = behind.
Closed-lost MIA rate: 5 / 25 = 20.0%; target is 10.0%, lower is better, so 20.0% - 10.0% = +10.0 pp = behind.
Same-quarter closes: 10 / 20 = 50.0%; 50.0% vs 71.7% elapsed = behind.
Active pipeline coverage: $3,000,000 / $4,000,000 = 75.0%; 75.0% vs 71.7% elapsed = ahead.

What moved this week: The provided data includes only QTD actuals, targets, and quarter timing. It does not include prior-week values or week-over-week changes, so what moved this week cannot be calculated from the data provided.
communication
ceo-slack-compressionPASS 1.00

? The Question

Compress the forecast analysis below into a single Slack message for the CEO. Rules: at most three sentences; under 80 words; lead with the decision or the so-what; keep every distinct number that matters and the one caveat that changes the conclusion; cut any sentence that does not carry a claim, a number, or a directive. No em dashes, no throat-clearing phrases.
cost $0.0386 · 1410s · in 2,625 / out 637 tok
✓ max_3_sentences✓ under_80_words✓ weighted_present✓ caveat_present✓ no_em_dash

✓ Correct Answer (ground truth)

graded checks: max_3_sentences · under_80_words · weighted_present · caveat_present · no_em_dash

Model's actual answer

show the model's full answer
Use $115,976.75 as Q3 forecast: $44,729 COMMIT from 7 deals + 35% x $203,565 BEST_CASE from 24 deals = $44,729 + $71,247.75. Caveat: 32 deals worth $227,575 close after 9/30, including COMMIT Deal-D348E1 at $13,770; owner is blank on 85/86 and why-buys empty on 71/86, including all 7 COMMIT, so treat as unvalidated.
stalled-deal-followup-emailPASS 1.00

? The Question

Write a follow-up email for this stalled deal. Under 120 words. Reference one specific prior touch from the engagement history, make one clear ask, and match the tone of the prior thread. No invented details.
cost $0.3868 · 268s · in 34,508 / out 6,716 tok
✓ word_cap✓ references_touch✓ single_ask

✓ Correct Answer (ground truth)

deal_alias: Deal-0D2F7A
amount: 5100
stage: DS3
owner: Alex Franklin
days_since_last_engagement: 31
word_cap: 120
must_reference: engagement_id=ENG-00002; date=2026-07-28; type=meeting; why=most substantive prior touch; concrete prospect reactions to milestone awards and points catalog
single_cta: True
tone: warm, concise, professional (matches prior thread)
allowed_facts: 14 items — e.g. Deal-0D2F7A, $5,100, DS3, Alex Franklin
allowed_new: ENG-00001, ENG-00002, ENG-00003, ENG-00004, ENG-00005
graded checks: word_cap · references_touch · single_ask

Model's actual answer

show the model's full answer
Arithmetic: 49 words < 120

Subject: Following up on 150-seat pricing

Hi,

I wanted to follow up on the pricing I sent on August 5 for 150 seats — I haven’t heard back and want to make sure it reached you.

Would you have 20 minutes this week to walk through the numbers and answer any questions?

Best,
Alex
funnel-digest-paragraphPASS 1.00

? The Question

Write the weekly GTM digest: one paragraph per team (Marketing, Sales, CS, PLG) in Bonusly brand voice. Every number must trace to the extracts. No customer contact names, no employee performance commentary, no compensation. Four paragraphs, under 400 words total.
cost $0.2539 · 68s · in 23,129 / out 4,183 tok
✓ four_paragraphs✓ word_cap✓ teams

✓ Correct Answer (ground truth)

required_paragraphs: Marketing, Sales, CS, PLG
allowed_numbers: 16 items — e.g. 2, 3, 9, 08
word_cap: 400
banned: customer contact names, employee performance commentary, compensation
graded checks: four_paragraphs · word_cap · teams

Model's actual answer

show the model's full answer
Marketing: Kudos to Marketing for driving 46 SQMs against a 52 target; the gap was 52 - 46 = 6 SQMs, with attainment at 46 / 52 = 88.5%. The webinar channel delivered 18 of the 46 SQMs, or 18 / 46 = 39.1% of weekly SQM volume, while paid search held steady at $150 cost per SQM.

Sales: Big recognition to Sales for converting 14 SQOs and setting 9 DS2 meetings this week. New pipeline created was $310,000, which works out to $310,000 / 14 = $22,142.86 per converted SQO. Same-quarter close count was 3, adding momentum to the week’s GTM progress.

CS: Shoutout to CS for saving 2 renewals this week and moving Team NPS to 61. There are 3 open red-flag accounts heading into next week, so the immediate customer-risk focus is clearly visible from the extract: 3 open red-flag accounts to address after 2 saved renewals.

PLG: High fives to PLG for adding 412 new signups with activation at 31%; estimated activated signups were 412 × 31% = 127.72. Also, 38 companies reached the aha moment of 10 recognition gives, representing at least 38 × 10 = 380 recognition gives at that threshold.
partner-digest-sectionPASS 1.00

? The Question

Write the partner digest for the period. Every partner in the roster appears once: active plays get status with numbers, quiet partners get one line. Partner-sourced pipeline count and amount must match the deal data. Nothing omitted, nothing added.
cost $0.2951 · 67s · in 24,431 / out 5,338 tok
✓ all_partners✓ pipeline_amount✓ quiet_one_line

✓ Correct Answer (ground truth)

roster: partner_name=Apex Rewards Co; status=active | partner_name=HRCloud Partners; status=active | partner_name=CultureBridge; status=active | partner_name=WorkWell Group; status=active | partner_name=Recogniq; status=quiet | partner_name=KudosWave; status=quiet … (+2 more)
per_partner_pipeline: {"Apex Rewards Co": {"count": 2, "amount": 275000}, "HRCloud Partners": {"count": 1, "amount": 140000}, "CultureBridge": {"count": 2, "amount": 135000}}
partner_sourced_pipeline: count=5; amount=550000
quiet_partners: Recogniq, KudosWave, PeopleFirst Advisors, TotalPerk
active_no_deals: WorkWell Group
rule: every roster partner named exactly once; quiet partners get one line; no partners outside roster.
graded checks: all_partners · pipeline_amount · quiet_one_line

Model's actual answer

show the model's full answer
Partner Digest: 2026-08-24 to 2026-09-04

Apex Rewards Co (active)
Status: Co-webinar locked for 09-15. They brought two sourced opps this week, both in DS1; both logged with UTM Source = Partner.
Partner-sourced pipeline: 2 deals, $275,000.
Arithmetic: Deal-DDAAF2 $180,000 + Deal-2CF33E $95,000 = $275,000.

HRCloud Partners (active)
Status: Integration referral closed the security review; opp moved to DS2. One sourced opp this period.
Partner-sourced pipeline: 1 deal, $140,000.
Arithmetic: Deal-F1CDA5 $140,000 = $140,000.

CultureBridge (active)
Status: Lunch-and-learn produced two sourced opps; both early stage.
Partner-sourced pipeline: 2 deals, $135,000.
Arithmetic: Deal-096E1D $60,000 + Deal-067213 $75,000 = $135,000.

WorkWell Group (active)
Status: Wants to restart the joint playbook in Q4; no sourced deals this period; planning call booked for 09-09.
Partner-sourced pipeline: 0 deals, $0.
Arithmetic: no deal rows = $0.

Recogniq (quiet): 0 partner-sourced deals, $0 pipeline. No Slack activity or deal rows provided.

KudosWave (quiet): 0 partner-sourced deals, $0 pipeline. No Slack activity or deal rows provided.

PeopleFirst Advisors (quiet): 0 partner-sourced deals, $0 pipeline. No Slack activity or deal rows provided.

TotalPerk (quiet): 0 partner-sourced deals, $0 pipeline. No Slack activity or deal rows provided.

Total partner-sourced pipeline: 5 deals, $550,000.
Arithmetic: 2 + 1 + 2 + 0 + 0 + 0 + 0 + 0 = 5 deals; $275,000 + $140,000 + $135,000 + $0 + $0 + $0 + $0 + $0 = $550,000.
rfp-answer-from-policyPASS 1.00

? The Question

Answer the 10 questionnaire items from the policy excerpts only. Cite the excerpt id for every answer. Where the excerpts do not answer the question, mark it unanswerable and say what document would; do not guess. Tone: vendor response, direct.
cost $0.3098 · 52s · in 34,782 / out 3,857 tok
✓ answered_count✓ unanswerable_flagged✓ citations✓ no_guess

✓ Correct Answer (ground truth)

answered_count: 7
answer_map: {"Q1": ["P1"], "Q2": ["P1"], "Q3": ["P2"], "Q4": ["P3"], "Q5": ["P4"], "Q6": ["P5"], "Q7": ["P6"]}
unanswerable: Q8, Q9, Q10
valid_citation_ids: P1, P2, P3, P4, P5, P6, P7, P8
rule: unanswerable items must be flagged and the document that would answer them named; do not guess.
graded checks: answered_count · unanswerable_flagged · citations · no_guess

Model's actual answer

show the model's full answer
| item_id | Vendor response |
|---|---|
| Q1 | Yes. Customer data is encrypted at rest using AES-256. [P1] |
| Q2 | Yes. Data in transit is encrypted with TLS 1.2 or higher. [P1] |
| Q3 | Yes. Bonusly maintains a SOC 2 Type II report, renewed annually. The report is available to prospects under NDA. [P2] |
| Q4 | Customer data is retained for the duration of the contract plus 90 days, then deleted from production systems. Arithmetic: contract termination date + 90 days = production deletion date. [P3] |
| Q5 | The current subprocessor list is maintained at trust.bonusly.com. Customers receive 30 days notice before a new subprocessor is added. [P4] |
| Q6 | Yes. SAML 2.0 single sign-on is available on the Enterprise plan. [P5] |
| Q7 | Production databases are backed up daily. Backups are encrypted and retained for 35 days. Arithmetic: 1 backup cadence per day × 35 days retention = 35-day backup retention window. [P6] |
| Q8 | Unanswerable from the provided excerpts. None of [P1]-[P8] states whether Bonusly holds ISO 27001 certification. An ISO 27001 certificate or compliance certifications document would answer this. |
| Q9 | Unanswerable from the provided excerpts. None of [P1]-[P8] states a contractual uptime SLA percentage. A Service Level Agreement or Master Services Agreement would answer this. |
| Q10 | Unanswerable from the provided excerpts. None of [P1]-[P8] states whether Bonusly will sign a HIPAA Business Associate Agreement. A HIPAA/BAA policy, BAA template, or contracting/legal terms document would answer this. |
ops-maintenance
skill-file-reconciliationPASS 1.00

? The Question

Reconcile the skill set below against its manifest. Find and report (with severity CRITICAL/WARNING/INFO and an action type TRIM_DESC, UPDATE_BODY, DELETE_SKILL, MERGE, or REVIEW): (1) any two skills whose ALWAYS-trigger phrases overlap/duplicate, (2) any circular delegation chain between skills (name it), (3) any delegation target that does not exist (dangling, name it), (4) any version conflict and which skill should survive, (5) how many manifest descriptions exceed 1,024 characters, (6) any hardcoded page ids, dates, or person names in skill bodies, (7) manifest drift in BOTH directions (files with no manifest row, and manifest rows with no file). Make one proposal per finding; rewrite nothing.
cost $2.0987 · 453s · in 242,037 / out 26,393 tok
✓ duplicate_trigger_found✓ circular_chain✓ dangling_target✓ oversized_desc_count✓ hardcoded_values✓ manifest_drift✓ severity_and_action

✓ Correct Answer (ground truth)

graded checks: duplicate_trigger_found · circular_chain · dangling_target · oversized_desc_count · hardcoded_values · manifest_drift · severity_and_action

Model's actual answer

show the model's full answer
Scope arithmetic:
- Manifest rows: 14
- Provided SKILL.md files: 14
- Matching aliases: 14
- Files with no manifest row: 14 - 14 = 0
- Manifest rows with no file: 14 - 14 = 0

Description length arithmetic:
- Limit: 1,024 characters
- Manifest description_chars values: 656, 897, 996, 792, 965, 676, 945, 1004, 1006, 962, 1006, 708, 762, 656
- Max observed: 1,006
- Margin under limit: 1,024 - 1,006 = 18
- Descriptions exceeding 1,024: 0 / 14

Dangling target arithmetic:
- Distinct missing skill/delegation targets found: 11
- Count: 1 `bonusly-brand` + 1 `prospect-research-multithreading` + 1 `signalforge-reports` + 8 specialist skills = 11

Findings:

| # | Category | Severity | Action | Finding | Proposal |
|---:|---|---|---|---|---|
| 1 | ALWAYS-trigger overlap | WARNING | MERGE | `comms-drafter` and `email-drafter` duplicate customer/prospect email triggers: "write me an email," "draft a follow-up," "help me reply," "what should I say," "bump email," "contract nudge," and pasted-message review/rewrite requests. | Merge ownership into one canonical external/email drafting skill, or narrow `comms-drafter` to non-email external communications only. |
| 2 | ALWAYS-trigger overlap | WARNING | UPDATE_BODY | `pipeline-intelligence-report` and `weekly-pipeline-report` overlap on pipeline report/update triggers: `pipeline-intelligence-report` triggers on "run the pipeline report," "pipeline review," "pipeline update," and "what's the pipeline look like"; `weekly-pipeline-report` triggers on "run the pipeline update," "weekly pipeline report," "generate the pipeline report," "update the pipeline," and "what does pipeline look like." | Separate the triggers explicitly: `pipeline-intelligence-report` owns full scored/tiered active-deal intelligence; `weekly-pipeline-report` owns weekly SQM/SQO/DS2/bookings performance reporting. |
| 3 | ALWAYS-trigger overlap | WARNING | UPDATE_BODY | `pipeline-intelligence-report` and `sales-forecast` overlap on forecast/pipeline health language. `pipeline-intelligence-report` triggers when "Alaina or any VP asks for pipeline health or forecast context"; `sales-forecast` triggers on "pipeline forecast," "forecast update," "deal-level confidence," "COMMIT vs BEST CASE breakdown," and current-quarter revenue outlook. | Make `sales-forecast` the owner for current-quarter forecast numbers and COMMIT/BEST CASE revenue outlook; keep `pipeline-intelligence-report` for scored active-deal tiering. |
| 4 | ALWAYS-trigger overlap | WARNING | UPDATE_BODY | `next-to-close` and `sales-forecast` overlap on "what will close" language: `next-to-close` triggers on "which deals are most likely to close" and "what's closing this week"; `sales-forecast` triggers on "what do we think we're going to close" and deal-level confidence. | Route shortlists of specific near-signature deals to `next-to-close`; route current-quarter revenue forecast and forecast-category rollups to `sales-forecast`. |
| 5 | Circular delegation chain | CRITICAL | UPDATE_BODY | Circular chain: `deal-strategy-coach` → `email-drafter` → `deal-strategy-coach`. `deal-strategy-coach` says manager-to-prospect emails should use `email-drafter`; `email-drafter` says deal strategy, diagnosis, coaching, multithreading plans, and forecast risk should use `deal-strategy-coach`. | Break the loop by assigning final ownership for mixed strategy + email requests. Example policy: `deal-strategy-coach` owns diagnosis and strategy, then drafts inline without handing back. |
| 6 | Dangling delegation target | CRITICAL | REVIEW | `bonusly-brand` is referenced but not present in the manifest or provided files. Referenced by `comms-drafter`, `email-drafter`, `sales-forecast`, `signalforge-claim-compressor`, and `weekly-pipeline-report`. | Confirm whether `bonusly-brand` exists outside this manifest; if not, add it to the manifest/file set or remove/replace the dependency. |
| 7 | Dangling delegation target | CRITICAL | REVIEW | `prospect-research-multithreading` is referenced but not present in the manifest or provided files. Referenced by `comms-drafter`, `deal-strategy-coach`, and `email-drafter`. | Confirm whether `prospect-research-multithreading` exists outside this manifest; if not, add it or replace the handoff with an available contact-lookup workflow. |
| 8 | Dangling delegation target | CRITICAL | REVIEW | `signalforge-reports` is referenced but not present in the manifest or provided files. Referenced by `pipeline-intelligence-report`, `weekly-pipeline-report`, and implied by report design-system paths. | Confirm whether `signalforge-reports` is an external org skill; if this manifest is meant to be complete, add the missing row/file or remove the dependency. |
| 9 | Dangling delegation targets | WARNING | REVIEW | `analysis-validator` references 8 specialist skills absent from the manifest/files: `bonusly-data-questions`, `bonusly-product-questions`, `bonusly-business-reporting-questions`, `bonusly-rewards-questions`, `bonusly-ppp-questions`, `bonusly-feature-flag-questions`, `bonusly-deal-desk-questions`, `bonusly-datadog-questions`. Arithmetic: 8 missing specialist targets. | Confirm whether the 8 specialist skills exist outside this manifest; if not, add them, remove the delegation language, or mark those paths unavailable. |
| 10 | Version conflict | WARNING | UPDATE_BODY | `analysis-validator` has conflicting version references. Header says Version 3.6, Last Updated says v3.6, footer says `analysis-validator v3.6`, but the validation trail template still says `analysis-validator v3.2`. Its changelog also lists both v3.6 and v3.5 on May 9, 2026. | Keep `analysis-validator` v3.6 as the surviving version. Update stale body references so v3.2 is not shown as the validator version, and mark v3.5 as superseded if retained in changelog. |
| 11 | Description length >1,024 | INFO | REVIEW | 0 manifest descriptions exceed 1,024 characters. Max = 1,006 for `pipeline-intelligence-report` and `signalforge-claim-compressor`; 1,024 - 1,006 = 18 characters under limit. | No TRIM_DESC action needed. |
| 12 | Hardcoded IDs, dates, person names | WARNING | UPDATE_BODY | Hardcoded IDs, dates, and names appear across skill bodies. Page/folder/space IDs include `2257879045`, `2286616609`, `2286321666`, `2265382925`, `2236940297`, `2237825028`, `2239365136`, `2238283777`, `2232582148`, `2295136266`, `2232811524`, `2234417154`, `2247295002`, `1958248479`, and cloud ID `73fe98de-a4a3-4869-9f8a-bb1eeed4cf7f`. Dates include `April 26, 2026`, `May 9, 2026`, `May 4, 2026`, `March 28, 2023`, `May 2026`, `2026-05-19`, `April 14, 2026`, `May 19, 2026`, `June 2, 2026`, `May 16, 2026`, `2026-05-17`, `April 1 – June 30, 2026`, `Q1 2026`, `April 27, 2026`, `2026-05-09`, and `2026-06-10`. Person names include `Amani Phipps`, `Amani`, `Manish`, `Alaina Loori`, `Alaina`, `Shealagh Coughlin`, `Bryce Harmon`, `Bryce`, `Hugo Lindqvist`, `Dana Mercer`, `Alex Franklin`, `Cole Ingram`, `Gavin Porter`, `Colleen Perry`, `Ellie Barton`, `Ashley Reyer`, `Ashley Le`, `Megan Franz`, `Elena Sinclair`, `Tracy`, `Youssef Elkhateeb`, `Amanda Czenkus`, `Ben Castelli`, `John Thomas`, `Yasmin Wahid`, `Farid`, `Kelli`, `Jen Lee`, `Hani`, `Sara`, `Ben Lavin`, `Ben`, and `Elena`. Company/deal aliases hardcoded as examples include `Softheon`, `Estee Lauder`, `MinIO`, `LIFTOFF`, `Nestlé`, `Ozinga`, `Aurora Innovation`, `GCash`, `Ethos Cannabis`, `StickerYou`, `Panopto`, `Schneider Downs`, `Felix Construction`, and `Acme`. | Replace dynamic operational anchors with live lookup language, or explicitly label retained constants as static. For dates and rosters, add update/verification instructions instead of fixed values where current state matters. |
| 13 | Manifest drift: files with no manifest row | INFO | REVIEW | None. Provided files = 14; manifest rows = 14; matching aliases = 14; files with no manifest row = 14 - 14 = 0. | No action. |
| 14 | Manifest drift: manifest rows with no file | INFO | REVIEW | None. Manifest rows = 14; provided files = 14; matching aliases = 14; manifest rows with no file = 14 - 14 = 0. | No action. |
runbook-from-slack-thread0.50

? The Question

Turn the resolved incident thread into a runbook: ordered steps with the exact command or action taken, who ran it, how success was verified, and rollback for each step that changed state. Every step must trace to a message in the thread. Add nothing the thread does not contain; where the thread is unclear, mark the step as needing confirmation.
cost $0.3782 · 79s · in 28,263 / out 7,154 tok
✗ ordered_steps✓ rollback✓ needs_confirmation✗ sourced

✓ Correct Answer (ground truth)

steps: order=1; msg=M01; actor=Bryce Harmon; action=acknowledge PagerDuty alert, take IC; state_change=False; verified_by=M01 | order=2; msg=M02; actor=Farid Osman; action=check queue depth; command=bundle exec rake sidekiq:queue_depth; state_change=False; verified_by=M02 (48,213 pending) | order=3; msg=M04; actor=Farid Osman; action=pause auto-enqueue via feature flag; command=bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'; state_change=True; rollback=bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'; verified_by=M07 (queue depth falling) | order=4; msg=M05; actor=Elena Sinclair; action=cleared the dead set; state_change=True; needs_confirmation=thread gives no command or method for clearing the dead set | order=5; msg=M06; actor=Bryce Harmon; action=scale reward-worker to 6 replicas; command=kubectl scale deployment/reward-worker --replicas=6; state_change=True; rollback=kubectl scale deployment/reward-worker --replicas=3; verified_by=M07/M08 | order=6; msg=M08; actor=Cole Ingram; action=verify queue drained and error rate baseline; command=bundle exec rake sidekiq:queue_depth; state_change=False; verified_by=M08 (returns 0) … (+2 more)
ambiguous_step: order=4; msg=M05; mark=needs-confirmation
rule: no steps beyond what the thread contains; every step traces to a message id.
graded checks: ordered_steps · rollback · needs_confirmation · sourced

Model's actual answer

show the model's full answer
| Step | Trace | Who ran it | Exact command or action taken | Success verification / arithmetic | Rollback for state change |
|---:|---|---|---|---|---|
| 1 | M01 | Bryce Harmon | Acknowledged PagerDuty alert and took IC. | Alert fired for reward-worker queue depth > 10k. No separate success verification stated; needs confirmation. | Not applicable; no rollback stated. |
| 2 | M02 | Farid Osman | `bundle exec rake sidekiq:queue_depth` | Reward queue was 48,213 pending jobs. Normal is under 500. Arithmetic: 48,213 - 500 = 47,713 jobs over the stated normal ceiling. | Not applicable; read-only check. |
| 3 | M03 | Farid Osman | Checked dead set. Exact command not provided; needs confirmation. | Dead set had 112 jobs, all `Redis::TimeoutError` from around 13:58. | Not applicable; read-only check. |
| 4 | M04 | Farid Osman | Paused enqueue to stop the bleed: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'` | No direct success verification stated in M04; needs confirmation. | `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` |
| 5 | M05 | Elena Sinclair | Cleared out the dead set while in the console. Exact command not provided; needs confirmation. | No success verification stated; needs confirmation. | Rollback not stated; needs confirmation. |
| 6 | M06 | Bryce Harmon | Scaled workers up: `kubectl scale deployment/reward-worker --replicas=6` | Previous replica count was 3. Arithmetic: 6 - 3 = 3 additional replicas. No direct success verification stated in M06; needs confirmation. | `kubectl scale deployment/reward-worker --replicas=3` |
| 7 | M07 | Farid Osman | Checked queue depth progress. Exact command not provided; needs confirmation. | Queue depth was down to 9,400 and falling ~1,200/min. Arithmetic from M02: 48,213 - 9,400 = 38,813 fewer pending jobs. | Not applicable; read-only check. |
| 8 | M08 | Cole Ingram | Verified with `bundle exec rake sidekiq:queue_depth`; checked Datadog error rate. | Queue depth returned 0. Error rate in Datadog was back to baseline. Arithmetic from M07: 9,400 - 0 = 9,400 more jobs cleared. Arithmetic from M02: 48,213 - 0 = 48,213 total pending jobs cleared. | Not applicable; read-only verification. |
| 9 | M09 | Bryce Harmon | Re-enabled enqueue: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` | Verified 40 new jobs processed cleanly in the next 3 minutes. Arithmetic: 40 / 3 = 13.33 jobs per minute. | Rollback not stated for this step; needs confirmation. |
| 10 | M10 | Bryce Harmon | Scaled workers back down: `kubectl scale deployment/reward-worker --replicas=3` | Queue stable at 0. Incident resolved. | Rollback not stated for this step; needs confirmation. |
datadog-incident-timelinePASS 1.00

? The Question

From the log slice, sequence the failure: first error with timestamp, the cascade in order, the service and job involved, and the Datadog query that would confirm the first error. State what the logs do not show.
cost $0.4183 · 81s · in 30,968 / out 8,355 tok
✓ first_error_ts✓ service_named✓ cascade_ordered✓ query✓ gaps_stated

✓ Correct Answer (ground truth)

first_error: timestamp=2026-09-03T14:01:12Z; service=reward-service; message=Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s
cascade_order: service=reward-service; first_error_at=2026-09-03T14:01:12Z | service=sidekiq; first_error_at=2026-09-03T14:01:40Z | service=api-gateway; first_error_at=2026-09-03T14:03:05Z | service=web-app; first_error_at=2026-09-03T14:03:30Z
job_class_involved: RewardGiveJob
confirming_query: service:reward-service status:error "@message:Redis::TimeoutError"
logs_do_not_show: root cause of the Redis timeout, redis-server's own logs, infrastructure metrics (CPU/memory/network), any deploy or config change preceding the incident, who applied mitigation or when (no actor fields in logs)
clean_services: postgres
graded checks: first_error_ts · service_named · cascade_ordered · query · gaps_stated

Model's actual answer

show the model's full answer
First error:
2026-09-03T14:01:12Z — reward-service — ERROR — Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s

Cascade in order:
1. 2026-09-03T13:59:30Z — reward-service logged “job enqueued”.
2. 2026-09-03T14:01:12Z — reward-service hit the first error: Redis timeout to redis-primary:6379.
3. 2026-09-03T14:01:20Z, 14:01:30Z, 14:01:40Z — reward-service logged “Redis::TimeoutError: retry exhausted for RewardGiveJob”.
4. 2026-09-03T14:01:40Z — sidekiq logged “RewardGiveJob failed: Redis::TimeoutError; retrying in 60s”.
5. 2026-09-03T14:01:46Z–14:01:57Z — sidekiq_jobs.csv shows 6 RewardGiveJob failures:
   6 = J-00005, J-00001, J-00003, J-00006, J-00002, J-00004.
6. 2026-09-03T14:02:28Z — sidekiq logged another RewardGiveJob failure.
7. 2026-09-03T14:02:30Z — sidekiq warned “Queue reward depth above 10,000”.
8. 2026-09-03T14:02:36Z — sidekiq_jobs.csv shows RecognitionDigestJob beginning to fail with Redis::TimeoutError.
9. 2026-09-03T14:02:51Z–14:02:58Z — sidekiq_jobs.csv shows 6 more RewardGiveJob failures.
   Arithmetic: 6 earlier RewardGiveJob failures + 6 later RewardGiveJob failures = 12 RewardGiveJob failures.
10. 2026-09-03T14:03:05Z — api-gateway began returning “502 upstream timeout calling reward-service /gives”.
    Arithmetic: 14:03:05 - 14:01:12 = 1 minute 53 seconds after first Redis error.
11. 2026-09-03T14:03:30Z — web-app logged “Give form submission failed: upstream 502 from api-gateway”.
    Arithmetic: 14:03:30 - 14:01:12 = 2 minutes 18 seconds after first Redis error.
12. 2026-09-03T14:03:15Z–14:05:50Z — sidekiq_jobs.csv shows 3 more RecognitionDigestJob failures.
    Arithmetic: 1 earlier RecognitionDigestJob failure + 3 later RecognitionDigestJob failures = 4 RecognitionDigestJob failures.
13. 2026-09-03T14:03:48Z–14:06:52Z — api-gateway continued logging 502 upstream timeouts.
    Arithmetic: 5 api-gateway 502 errors total = 14:03:05, 14:03:48, 14:04:13, 14:05:16, 14:06:52.
14. 2026-09-03T14:04:45Z–14:06:49Z — web-app continued logging give form submission failures.
    Arithmetic: 4 web-app failures total = 14:03:30, 14:04:45, 14:05:42, 14:06:49.
15. 2026-09-03T14:22:10Z — reward-service logged “Redis connection restored; resuming job processing”.
    Arithmetic: 14:22:10 - 14:01:12 = 20 minutes 58 seconds from first Redis error to Redis restoration.
16. 2026-09-03T14:24:45Z — sidekiq logged “Queue reward depth below 500”.
    Arithmetic: 14:24:45 - 14:02:30 = 22 minutes 15 seconds from queue depth above 10,000 to below 500.

Service and job involved:
- First failing service: reward-service.
- Queue worker service involved: sidekiq.
- User-facing cascade services: api-gateway, then web-app.
- Primary job involved: RewardGiveJob.
- Additional affected job shown in sidekiq_jobs.csv: RecognitionDigestJob.

Job failure arithmetic:
- RewardGiveJob failures: 12.
- RecognitionDigestJob failures: 4.
- Total job failures in sidekiq_jobs.csv: 12 + 4 = 16.

Datadog query to confirm the first error:
service:reward-service status:error "Redis::TimeoutError" "redis-primary:6379"

What the logs do not show:
- They do not show the root cause of the Redis timeout.
- They do not show Redis CPU, memory, connection count, latency, saturation, failover, or availability metrics.
- They do not show network metrics between reward-service and redis-primary:6379.
- They do not show deploys, infrastructure changes, or incident annotations.
- They do not show affected customer, deal, company, account, user, or revenue impact.
- They do not contain any deal/company aliases to cite.
- They do not show successful versus failed total job volume beyond the listed failures.
- They do not show when api-gateway or web-app fully recovered; only Redis restoration and queue-depth recovery are shown.
feature-flag-state-summaryPASS 1.00

? The Question

Summarize the state of the listed feature flags: what each controls per the code excerpt, which companies or segments have it on, targeting rules, and any flag with no code reference or no targets. Company counts must match the export. Do not describe a flag that is not in the export.
cost $0.2761 · 53s · in 25,115 / out 4,590 tok
✓ orphans✓ no_targets✓ counts_match✓ no_invented

✓ Correct Answer (ground truth)

flags: {"recognition_streaks_v2": {"state": "on", "targeting_rules": "segment:beta_companies", "company_count": 42}, "points_budget_guardrails": {"state": "on", "targeting_rules": "all_companies", "company_c
code_referenced: recognition_streaks_v2, points_budget_guardrails, slack_dm_nudges, redeem_flow_redesign, analytics_dashboard_v3, ms_teams_app_v2
orphan_flags_no_code_reference: legacy_give_modal, survey_boosters_q3, paused_offboard_cleanup
flags_with_no_targets: paused_offboard_cleanup
rule: company counts must equal the export; do not describe flags absent from the export.
graded checks: orphans · no_targets · counts_match · no_invented

Model's actual answer

show the model's full answer
Feature flag state summary, using only the export and code excerpt:

| flag_key | state | what it controls per code excerpt | targeting_rules | companies/segments with it on | company_count |
|---|---:|---|---|---|---:|
| recognition_streaks_v2 | on | Records recognition streaks via `StreakTracker.record(give)` | segment:beta_companies | segment:beta_companies | 42 |
| points_budget_guardrails | on | Enforces budget guardrails via `BudgetService.new(company).enforce!(giver, points)` | all_companies | all_companies | 220 |
| slack_dm_nudges | on | Sends Slack DM nudges via `SlackDm.send_nudge(user)` | segment:region_na | segment:region_na | 87 |
| redeem_flow_redesign | off | Renders `RedeemV2Component.new(company)` when enabled; otherwise renders `RedeemV1Component.new(company)` | targeted_list | Not on; targeted company aliases are not provided | 12 |
| analytics_dashboard_v3 | on | Uses `AnalyticsV3.new(company)` for the dashboard via `@dashboard = AnalyticsV3.new(company)` | segment:tier_three | segment:tier_three | 65 |
| ms_teams_app_v2 | off | Installs Teams app v2 via `TeamsAppV2.install(company)` | targeted_list | Not on; targeted company aliases are not provided | 9 |
| legacy_give_modal | off | No code reference provided | segment:legacy_plan | Not on | 14 |
| survey_boosters_q3 | on | No code reference provided | segment:legacy_plan | segment:legacy_plan | 7 |
| paused_offboard_cleanup | off | No code reference provided | missing / blank | Not on; no targets | 0 |

Flags with no code reference:
- legacy_give_modal: 14 companies, targeting_rules = segment:legacy_plan
- survey_boosters_q3: 7 companies, targeting_rules = segment:legacy_plan
- paused_offboard_cleanup: 0 companies, targeting_rules = missing / blank

Flags with no targets:
- paused_offboard_cleanup: targeting_rules is blank, company_count = 0

Arithmetic:
- ON flag company_count total: 42 + 220 + 87 + 65 + 7 = 421
- OFF flag company_count total: 12 + 9 + 14 + 0 = 35
- Total company_count across all exported flag rows: 421 + 35 = 456

Company aliases are not provided anywhere in the data, so targeted_list companies cannot be named.
nda-triagePASS 1.00

? The Question

Triage each NDA as GREEN (standard approval), YELLOW (counsel review), or RED (full legal review). Cite the clause that drives each classification by quoting it. Catch embedded non-solicits, non-competes, missing carve-outs, and unusual term or governing law. One line of reasoning per NDA.
cost $0.2866 · 55s · in 23,755 / out 5,167 tok
✓ green✓ yellow✓ red✓ non_solicit_caught✓ clause_quoted✓ correct_labels

✓ Correct Answer (ground truth)

classifications: {"NDA-1": {"classification": "GREEN", "driving_reason": "standard mutual NDA: 2-year term, standard carve-outs, Delaware law", "driving_clause_quote": "Carve-outs: information that (a) is or becomes p
non_solicit_in: NDA-2
checks: classification_per_nda, clause_quotes_exist_in_document, non_solicit_caught, carveouts_checked
graded checks: green · yellow · red · non_solicit_caught · clause_quoted · correct_labels

Model's actual answer

show the model's full answer
NDA-1 — [PARTY A] and Bonusly — GREEN: “Carve-outs: information that (a) is or becomes publicly available through no breach, (b) was known prior to disclosure, (c) is received from a third party without duty of confidence, (d) is independently developed, or (e) must be disclosed by law or court order”; standard mutual NDA with standard carve-outs, Delaware law, no exclusivity, and term arithmetic of 2 years + 3-year survival = 5 years maximum if terminated at end of term.

NDA-2 — [PARTY B] and Bonusly — YELLOW: “During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement”; counsel review needed because the NDA embeds a non-solicit/no-hire restriction, with arithmetic of 3-year term + 18-month tail = 4.5 years.

NDA-3 — [PARTY C] and Bonusly — RED: “For a period of three (3) years following the Effective Date, Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser’s business”; full legal review needed because it includes a 3-year non-compete, one-way confidentiality favoring [PARTY C], “No confidentiality carve-outs are stated in this Agreement,” and governing law/jurisdiction is the “Republic of Ireland.”