home · ← back to all models
openai

openai/gpt-5.5-pro

Mean 0.956 · 32/40 perfect tests · $123.62 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 $4.8940 · 176s · in 67,704 / out 15,905 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 = why_buys is blank, under 15 characters, or placeholder; LONG(n) counts as present/substantive.
- No DS1 timestamp = blank t_ds1.
- Regressed = any populated earlier-stage timestamp is later than a populated later-stage timestamp.

Why-buys non-compliance:
- Overall: 101 / 124 DS2+ deals = 81.5%

By owner:
- Bryce Harmon: 15 / 18 = 83.3%
- Dana Mercer: 18 / 22 = 81.8%
- Alex Franklin: 48 / 61 = 78.7%
- Cole Ingram: 19 / 22 = 86.4%
- Farid Osman: 1 / 1 = 100.0%

Timestamp hygiene:
- No DS1 timestamp: 0 / 156 deals = 0
- Regressed: 0 / 156 deals = 0

Three process fixes:
1. Add a DS2+ stage-gate rule requiring why_buys to be 15+ characters and blocking blanks/placeholders.
2. Auto-stamp t_ds1 and each later stage timestamp on first entry; restrict manual edits to admin correction.
3. Run a recurring owner-level hygiene report for DS2+ why_buys gaps and timestamp-order anomalies before forecast reviews.
owner-resolution0.83

? 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 $3.6366 · 284s · in 56,510 / out 10,785 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 of 156  
Arithmetic: 35 + 24 + 67 + 22 + 7 + 1 = 156

Deals whose owner_id has no match in owners table: none

Open-deal owner_ids that map to archived/deactivated owners: none  
Note: 1520255671 / Gavin Porter and 77260721 / Hugo Lindqvist are archived in owners.csv, but neither owner_id appears on any open deal.

Total pipeline amount per resolved owner:

Bryce Harmon — owner_id 119337721 — 35 deals  
24,000 + 19,656 + 13,500 + 7,000 + 2,520 + 240,000 + 99,000 + 72,000 + 70,000 + 63,600 + 45,000 + 1 + 21,000 + 23,400 + 13,680 + 5,502 + 8,160 + 1 + 11,400 + 1 + 36,000 + 31,500 + 6,000 + 10,800 + 30,275 + 17,400 + 12,600 + 18,000 + 37,440 + 18,828 + 2,880 + 36,000 + 20,880 + 10,920 + 25,200 = 1,054,144

Dana Mercer — owner_id 83155923 — 24 deals  
11,250 + 10,500 + 9,000 + 9,000 + 5,400 + 4,800 + 4,600 + 1,920 + 15,000 + 4,200 + 18,900 + 27,000 + 43,875 + 20,000 + 60,000 + 8,100 + 16,250 + 3,150 + 5,000 + 2,100 + 23,400 + 5,400 + 7,350 + 25,000 = 341,195

Alex Franklin — owner_id 84342457 — 67 deals  
14,850 + 13,770 + 11,200 + 9,000 + 6,360 + 5,400 + 3,240 + 2,484 + 1,920 + 1,080 + 7,200 + 19,000 + 2,880 + 1,400 + 4,800 + 1,632 + 10,000 + 9,300 + 2,700 + 2,160 + 1,800 + 3,600 + 3,840 + 15,000 + 1,968 + 4,000 + 3,600 + 4,800 + 3,120 + 2,520 + 9,000 + 2,400 + 62,000 + 5,400 + 5,100 + 16,700 + 4,400 + 1,620 + 2,600 + 7,200 + 18,000 + 17,000 + 8,316 + 8,100 + 18,000 + 12,600 + 24,000 + 15,000 + 9,000 + 7,200 + 3,780 + 16,200 + 7,200 + 4,680 + 1,800 + 18,000 + 2,730 + 2,400 + 3,060 + 18,000 + 12,000 + 1,800 + 4,400 + 31,200 + 7,200 + 1,600 + 60,000 = 624,310

Cole Ingram — owner_id 83155924 — 22 deals  
2,760 + 1,330 + 7,225.4 + 3,360 + 5,616 + 2,700 + 7,781.2 + 6,947.5 + 40,000 + 12,168 + 2,480.4 + 11,116 + 11,193 + 1,875 + 31,750 + 32,175 + 4,779.88 + 3,334.8 + 58,529.25 + 4,140 + 18,000 + 18,900 = 288,161.43

Farid Osman — owner_id 716654662 — 7 deals  
1,249 + 1 + 1 + 1 + 2,880 + 1 + 1 = 4,134

Elena Sinclair — owner_id 701163055 — 1 deal  
2,100 = 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 $5.4109 · 196s · in 76,257 / out 17,351 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) Orphans: 30 gong rows have hs_deal_id with no matching deal_id in deals_open.

Arithmetic: 67 gong rows - 37 matched gong rows = 30 orphan rows.

Sample orphan aliases: Deal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42.

(b) Duplicate conversation keys: 0 rows where calls_90d exceeds distinct_conversation_keys.

Arithmetic: rows with calls_90d > distinct_conversation_keys = 0.

(c) DS3+ open deals with at least one logged call: 25 of 85 = 29.4%.

Arithmetic:
DS3+ open deals = DS3 61 + DS4 14 + DS5 10 = 85
DS3+ open deals with at least one gong row = 25
Share = 25 / 85 = 29.4118% ≈ 29.4%
snowflake-sql-trapped-catalogPASS 1.00

? 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 $1.6381 · 139s · in 15,197 / out 6,568 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
SELECT
    -- Required company identifier/alias column is not provided in the catalog excerpt; the source table is documented as one row per self-serve company, so each output row is one customer company but cannot be labeled without inventing a column.
    DATE_TRUNC('MONTH', FIRST_SUB_PAYMENT_DATE) AS FIRST_CUSTOMER_MONTH,
    -- Arithmetic: UNIQUE_GIVERS = M1_USERS, the only provided first-month user/giver metric; no deleted-giver exclusion is applied.
    M1_USERS AS UNIQUE_GIVERS,
    -- Arithmetic: RECOGNITION_COUNT = M1_GIVES.
    M1_GIVES AS RECOGNITION_COUNT,
    -- Arithmetic: SUCCESSFUL_REDEMPTION_COUNT = M1_REDEMPTIONS.
    M1_REDEMPTIONS AS SUCCESSFUL_REDEMPTION_COUNT
-- Table choice: PRODUCTION.PLG.COMPANY_COHORT_SUMMARY is the only provided populated source with one row per self-serve company and documented first-month metrics; stale/unpopulated HubSpot tables are avoided.
FROM PRODUCTION.PLG.COMPANY_COHORT_SUMMARY
WHERE FIRST_SUB_PAYMENT_DATE IS NOT NULL;
```
crm-completeness-enrichment0.80

? 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 $4.1142 · 259s · in 41,650 / out 15,915 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
Input scope:
- companies.csv: 34 company rows
- contacts.csv: 52 contact rows
- zoominfo_enrichment.csv: 25 enrichment rows
- Deals extract: not provided, so deal completeness and pipeline amount at stake are not computable.

Completeness by required field:

Deals:
- owner: not computable; no deals file provided
- stage: not computable; no deals file provided
- amount: not computable; no deals file provided
- close date: not computable; no deals file provided
- why-buys: not computable; no deals file provided

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

Contacts:
- email populated: 52/52 = 100.0%
- valid email: 48/52 = 92.3%
- title: 39/52 = 75.0%
- persona: 37/52 = 71.2%

Duplicate company clusters:
- Shared domain acme-corp.com:
  - aliases: C-0A092931, C-0A092932
  - survivor: C-0A092931
  - conflicts: industry Technology vs tech; employee_count 500 vs 510; hq_country US vs USA
  - enrichment match: none provided

- Shared domain globex.io:
  - aliases: C-0A092933, C-0A092934
  - survivor: C-0A092933
  - conflicts: industry SaaS vs Technology
  - enrichment match: none provided

No company name field was provided, so duplicate detection is based only on shared domain and alias variants.

Company fields to fill from matching enrichment rows:
- 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 after those fills:
- employee_count would improve from 25/34 = 73.5% to 33/34 = 97.1%
- hq_country has 0 fillable blanks from enrichment, so remains 28/34 = 82.4%

Company missing fields not fillable from provided enrichment:
- C-2D1F1B, 2d1f1b.com: hq_country blank; enrichment hq_country blank
- C-D73B89, d73b89.com: hq_country blank; enrichment hq_country blank
- C-44EA29, 44ea29.com: hq_country blank; enrichment hq_country blank
- C-D04904, d04904.com: hq_country blank; enrichment hq_country blank
- C-2C60E5, 2c60e5.com: hq_country blank; enrichment hq_country blank
- C-93C8BF, 93c8bf.com: employee_count blank; no matching enrichment row
- C-EE9FFB, ee9ffb.com: hq_country blank; no matching enrichment row

CRM vs enrichment disagreements:
Recommend source for all rows below: zoominfo_enrichment.csv.

- C-66D1FC, 66d1fc.com, industry: CRM tech; enrichment Computer Software
- C-66D1FC, 66d1fc.com, hq_country: CRM US; enrichment United States
- C-950043, 950043.com, hq_country: CRM US; enrichment United States
- C-EC3025, ec3025.com, industry: CRM Technology; enrichment Computer Software
- C-EC3025, ec3025.com, hq_country: CRM USA; enrichment United States
- C-96039F, 96039f.com, hq_country: CRM USA; enrichment United States
- C-44EA29, 44ea29.com, industry: CRM tech; enrichment Computer Software
- C-92D97D, 92d97d.com, industry: CRM Technology; enrichment Computer Software
- C-D04904, d04904.com, industry: CRM Technology; enrichment Computer Software
- C-77A95A, 77a95a.com, industry: CRM Technology; enrichment Computer Software
- C-77A95A, 77a95a.com, hq_country: CRM US; enrichment United States
- C-AA8DDA, aa8dda.com, industry: CRM Technology; enrichment Computer Software
- C-B23205, b23205.com, hq_country: CRM US; enrichment United States
- C-E51FB7, e51fb7.com, hq_country: CRM USA; enrichment United States
- C-D0662E, d0662e.com, hq_country: CRM US; enrichment United States
- C-B25F40, b25f40.com, industry: CRM Technology; enrichment Computer Software
- C-60C75F, 60c75f.com, industry: CRM tech; enrichment Computer Software
- C-425E2A, 425e2a.com, industry: CRM "Tech "; enrichment Computer Software
- C-425E2A, 425e2a.com, hq_country: CRM USA; enrichment United States
- C-2D7423, 2d7423.com, hq_country: CRM USA; enrichment United States

Invalid emails:
- CT-0010, C-66D1FC: email user0@; expected domain 66d1fc.com
- CT-0080, C-92D97D: email user0@; expected domain 92d97d.com
- CT-0081, C-92D97D: email user1@; expected domain 92d97d.com
- CT-0192, C-425E2A: email user2@; expected domain 425e2a.com

Domain mismatches:
- CT-0011, C-66D1FC: email user1@other-domain.com has email domain other-domain.com; contact/company domain is 66d1fc.com

Contact domain vs company domain mismatches:
- None found.

Missing contact titles:
- CT-0000, C-2D1F1B
- CT-0022, C-C6FE92
- CT-0072, C-44EA29
- CT-0080, C-92D97D
- CT-0081, C-92D97D
- CT-0092, C-D04904
- CT-0120, C-AA8DDA
- CT-0121, C-AA8DDA
- CT-0122, C-AA8DDA
- CT-0132, C-B23205
- CT-0141, C-E51FB7
- CT-0162, C-D0662E
- CT-0170, C-B25F40

Missing contact personas:
- CT-0000, C-2D1F1B
- CT-0022, C-C6FE92
- CT-0041, C-D73B89
- CT-0060, C-96039F
- CT-0070, C-44EA29
- CT-0081, C-92D97D
- CT-0082, C-92D97D
- CT-0092, C-D04904
- CT-0110, C-77A95A
- CT-0132, C-B23205
- CT-0162, C-D0662E
- CT-0171, C-B25F40
- CT-0172, C-B25F40
- CT-0180, C-60C75F
- CT-0181, C-60C75F

Proposed fixes:
- Merge duplicate company cluster acme-corp.com into survivor C-0A092931; manually resolve conflicting employee_count because enrichment has no matching row.
- Merge duplicate company cluster globex.io into survivor C-0A092933; manually resolve conflicting industry because enrichment has no matching row.
- Apply the 8 employee_count fills from matching enrichment rows.
- Do not fill the 7 remaining missing company fields; provided enrichment is blank or missing.
- Replace CRM values with zoominfo_enrichment.csv where CRM and enrichment disagree, as listed above.
- Validate or replace invalid emails CT-0010, CT-0080, CT-0081, CT-0192; do not auto-complete them from domain because full verified emails are not provided.
- Investigate CT-0011 domain mismatch; either correct the email or reassign the contact, but provided data does not prove which is correct.
- Backfill missing contact titles from a verified source; no title enrichment source was provided.
- Backfill missing contact personas from a verified source; no persona enrichment source was provided.
- Add a deals extract with owner, stage, amount, close date, and why-buys to complete the deal audit.

10 fixes with the most pipeline amount at stake:
Not computable from the provided data. No deals extract was provided, and no deal amount values were provided. Arithmetic: 0 provided deal amount records and 0 provided deal-to-company/contact mappings; therefore pipeline amount at stake cannot be ranked without inventing numbers.
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 $8.1820 · 546s · in 62,450 / out 35,047 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
Missing data: no company aliases were provided; only deal_alias values are cited. “unknown” side means the tag/text did not clearly identify Bonusly or buyer as the side.

Classifications:

| deal_alias | primary category | side |
|---|---:|---|
| Deal-DB0AAC | timing | buyer |
| Deal-F7F635 | competitor | unknown |
| Deal-AC944F | no decision | buyer |
| Deal-214060 | no decision | buyer |
| 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 | buyer |
| Deal-B3ABED | timing | buyer |
| Deal-422BA6 | product gap | Bonusly |
| Deal-ED9AE7 | timing | buyer |
| Deal-988493 | no decision | buyer |
| Deal-381C8C | competitor | unknown |
| Deal-F308CA | no decision | buyer |
| Deal-F1E8A6 | competitor | unknown |
| Deal-B6AC09 | timing | buyer |
| Deal-70F704 | product gap | Bonusly |
| Deal-E6E80A | timing | buyer |
| Deal-B038F0 | timing | buyer |
| Deal-4664E1 | no decision | buyer |
| 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 | buyer |
| Deal-15DA99 | timing | buyer |
| Deal-F4AF5D | timing | buyer |
| Deal-79B7A1 | timing | buyer |
| Deal-583ADB | no decision | buyer |
| Deal-8E27DA | no decision | buyer |
| Deal-2D2F8D | competitor | unknown |
| Deal-E0441F | no decision | unknown |
| Deal-7CB44D | no decision | buyer |
| 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 | buyer |
| Deal-C7156E | competitor | unknown |
| Deal-C33D91 | pricing | buyer |
| Deal-9048EB | product gap | Bonusly |
| Deal-5E64CE | timing | 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 | buyer |
| Deal-FEDBCB | timing | buyer |
| Deal-1E7DA9 | competitor | unknown |
| Deal-2BBA21 | no decision | buyer |
| Deal-286F9C | product gap | Bonusly |
| Deal-7FBAC6 | no decision | buyer |
| Deal-369281 | competitor | buyer |
| Deal-386F6E | no decision | buyer |
| Deal-9FCD0D | competitor | buyer |
| Deal-55867E | no decision | unknown |
| Deal-DAFB82 | pricing | buyer |
| Deal-2FEDDB | timing | buyer |
| Deal-64B19A | competitor | unknown |
| Deal-3F86A0 | no decision | buyer |
| Deal-096750 | no decision | buyer |
| Deal-F325A5 | champion left | buyer |
| Deal-ABD14C | no decision | buyer |
| Deal-79E61A | no decision | buyer |
| Deal-8A119B | pricing | buyer |
| Deal-AE7C4E | no decision | buyer |
| Deal-DAB4F1 | no decision | buyer |
| Deal-B4B50F | no decision | buyer |
| Deal-981AD4 | product gap | Bonusly |
| Deal-DC77FE | product gap | Bonusly |
| Deal-5885B9 | no decision | buyer |

Category counts:
- pricing: 5
- competitor: 18
- no decision: 31
- timing: 22
- product gap: 12
- champion left: 1
- other: 1

Arithmetic: 5 + 18 + 31 + 22 + 12 + 1 + 1 = 90

Side split:
- Bonusly: 13
- buyer: 62
- unknown: 15

Arithmetic: 13 + 62 + 15 = 90

Structured tag/free-text clear disagreements:
- Count: 4
- Arithmetic: 1 + 1 + 1 + 1 = 4
- Deals: Deal-70F704, Deal-8E27DA, Deal-3618CC, Deal-5AD03E

Two patterns most worth acting on:
1. Buyer-side stall dominates: no decision + timing = 31 + 22 = 53 of 90, and buyer-side losses = 62 of 90.
2. Product/competitive leakage is the next-largest block: product gap + competitor = 12 + 18 = 30 of 90, with explicit product-gap themes in Deal-F97C37, Deal-422BA6, Deal-242273, Deal-A2C349, Deal-3618CC, Deal-5AD03E, Deal-981AD4, and 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 $7.2010 · 250s · in 87,039 / out 25,499 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":39,"BUILD":54,"REVIVE":15,"WATCH":28,"RISKY":17},"tier_examples":{"LOCK":["Deal-D348E1","Deal-C26D20","Deal-403845"],"ACTION":["Deal-25F752","Deal-E53952","Deal-5408B0"],"BUILD":["Deal-523604","Deal-CA7DC0","Deal-483B2D"],"REVIVE":["Deal-2D1F1B","Deal-66D1FC","Deal-950043"],"WATCH":["Deal-C9C286","Deal-332637","Deal-E25A09"],"RISKY":["Deal-547B2B","Deal-B7EBD1","Deal-6787C2"]},"risky_deals":["Deal-547B2B","Deal-B7EBD1","Deal-6787C2","Deal-A2B47C","Deal-2465CE","Deal-584EE5","Deal-A5E80A","Deal-0660B4","Deal-1FC049","Deal-FD9F4E","Deal-499BF6","Deal-BA571A","Deal-7BBDFA","Deal-4A13AD","Deal-690476","Deal-635B8E","Deal-215CCA"],"lock_violations":0,"pipeline_shape":"Arithmetic: 3 LOCK + 39 ACTION + 54 BUILD + 15 REVIVE + 28 WATCH + 17 RISKY = 156 total deals. Shape is BUILD/ACTION-heavy with only 3 LOCK deals, 17 forecast/evidence mismatches, and 43 lower-confidence WATCH/REVIVE deals; engagement data is missing for Deal-3EED2C and Deal-57FF13, and contact count is missing for Deal-57FF13."}
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 $2.0393 · 154s · in 16,059 / out 8,653 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
{
  "arithmetic": "No derived arithmetic performed; all numeric values are direct transcript values.",
  "crm_writebacks": [
    {
      "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."
      ],
      "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": [
        "One concern: we need SSO and audit logs for IT to sign off."
      ],
      "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%."
      ],
      "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."
      ],
      "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": [
        "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.",
        "The CEO has to be sold first — she decides anything people-related.",
        "My CEO used Bucketlist at her last company and liked it."
      ],
      "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."
      ],
      "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": [
        "The security review took three months for our last vendor — that's my hesitation.",
        "Maybe — I need to check her calendar, no promises."
      ],
      "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."
      ],
      "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."
      ],
      "confidence": "high"
    },
    {
      "transcript_id": "TX-006",
      "deal_alias": "Deal-EE195F",
      "why-buys": [
        "I'd love to cut the admin time on service awards."
      ],
      "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": "doing it internally",
      "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."
      ],
      "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 $1.8384 · 113s · in 32,049 / out 4,872 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 — $11,200. Why close: CRM has DS5/COMMIT, close_date 2026-09-11; Slack says redlines are clean, signing page is out, and VP People said they are signing tomorrow. What’s left: signature.

2. Deal-403845 — $9,000. Why close: CRM has DS5/COMMIT, close_date 2026-09-11; Slack says the order form is with their finance team. What’s left: finance team completion/signature.

3. Deal-B7EBD1 — $9,000. Why close: CRM has DS5/COMMIT and the earliest non-blocked close_date, 2026-09-10. What’s left: not specified in the provided Slack/CRM data.

Arithmetic: $11,200 + $9,000 + $9,000 = $29,200.

Excluded Deal-2465CE despite CRM DS5/COMMIT because Slack says it is blocked, pulled from commit, and realistically Q4.
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 $0.7616 · 60s · in 14,983 / out 1,734 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 missing: no deal amount or active/status field was provided, so amount is “missing” and active status cannot be verified.

Candidate classifications:

| Deal | Amount | Prospect line | Classification | Basis |
|---|---:|---|---|---|
| Deal-EC3025 | missing | “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.” | Real gap | Product docs say “SCIM user provisioning” is “NOT currently listed as supported.” |
| 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.” | Real gap | Product docs list HRIS integrations as Workday, BambooHR, Gusto, Rippling; “ADP Workforce Now” is “NOT currently listed as supported.” |
| 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?” | Plan gate | “Custom report builder” exists only on Enterprise. |
| 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.” | Rollout/enablement issue | Slack integration is supported on all plans; stated issue is lack of training. |

Excluded: Deal-36C33F. The native mobile app gap was stated by Alex Franklin, not the prospect. Rep language does not count as prospect voice.

Summary — real product gaps only:

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

2. ADP Workforce Now integration
   - Deal: Deal-D0D6B5
   - Amount: missing
   - 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.”

Arithmetic:
- Prospect-raised candidates classified: 4
- Real gaps: 2
- Plan gates: 1
- Rollout/enablement issues: 1
- Real gaps in summary: 2
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 $7.8470 · 342s · in 84,231 / out 29,556 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
Basis: stale = no last_email/last_call/last_meeting dated 2026-08-29 through 2026-09-05 inclusive. Days since last contact = 2026-09-05 minus the most recent nonblank engagement date on/before 2026-09-05.

Missing engagement data, not counted in stale totals:
- Deal-3EED2C, Alex Franklin, DS2, amount 7,200: no engagements_by_deal_90d row, so days since last contact cannot be computed.
- Deal-57FF13, Elena Sinclair, DS1, amount 2,100: no engagements_by_deal_90d row, so days since last contact cannot be computed.

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

Bryce Harmon total: 18 stale deals; total stale amount = 240,000 + 99,000 + 70,000 + 45,000 + 37,440 + 36,000 + 31,500 + 25,200 + 23,400 + 21,000 + 18,000 + 12,600 + 11,400 + 10,920 + 6,000 + 5,502 + 1 + 1 = 692,964

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

Dana Mercer total: 16 stale deals; total stale amount = 60,000 + 43,875 + 27,000 + 23,400 + 20,000 + 18,900 + 16,250 + 15,000 + 10,500 + 9,000 + 9,000 + 8,100 + 7,350 + 5,000 + 4,200 + 1,920 = 279,495

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

Alex Franklin total: 19 stale deals; total stale amount = 24,000 + 18,000 + 9,300 + 8,316 + 5,100 + 4,800 + 4,680 + 4,400 + 3,840 + 3,600 + 3,240 + 3,120 + 2,700 + 2,600 + 2,400 + 2,160 + 1,800 + 1,600 + 1,080 = 106,736

Cole Ingram
Deal alias | Owner name | Stage | Amount | Days since last contact
Deal-D04904 | Cole Ingram | DS2 | 58,529.25 | 11 = 2026-09-05 - 2026-08-25
Deal-B25F40 | Cole Ingram | DS3 | 40,000 | 8 = 2026-09-05 - 2026-08-28
Deal-813836 | Cole Ingram | DS2 | 32,175 | 11 = 2026-09-05 - 2026-08-25
Deal-1BA595 | Cole Ingram | DS2 | 31,750 | 11 = 2026-09-05 - 2026-08-25
Deal-CFE1E8 | Cole Ingram | DS3 | 18,000 | 11 = 2026-09-05 - 2026-08-25
Deal-CD47A6 | Cole Ingram | DS2 | 12,168 | 11 = 2026-09-05 - 2026-08-25
Deal-627646 | Cole Ingram | DS3 | 11,193 | 11 = 2026-09-05 - 2026-08-25
Deal-FF809F | Cole Ingram | DS2 | 7,781.2 | 11 = 2026-09-05 - 2026-08-25
Deal-AF932D | Cole Ingram | DS2 | 7,225.4 | 11 = 2026-09-05 - 2026-08-25
Deal-A71728 | Cole Ingram | DS2 | 6,947.5 | 11 = 2026-09-05 - 2026-08-25
Deal-8BC9F5 | Cole Ingram | DS2 | 5,616 | 10 = 2026-09-05 - 2026-08-26
Deal-175395 | Cole Ingram | DS3 | 4,779.88 | 11 = 2026-09-05 - 2026-08-25
Deal-481E24 | Cole Ingram | DS3 | 4,140 | 10 = 2026-09-05 - 2026-08-26
Deal-C7F9BF | Cole Ingram | DS2 | 3,360 | 11 = 2026-09-05 - 2026-08-25
Deal-2F3A66 | Cole Ingram | DS3 | 3,334.8 | 11 = 2026-09-05 - 2026-08-25
Deal-342E96 | Cole Ingram | DS2 | 2,700 | 24 = 2026-09-05 - 2026-08-12
Deal-E568D5 | Cole Ingram | DS3 | 1,875 | 11 = 2026-09-05 - 2026-08-25
Deal-FD9F4E | Cole Ingram | DS5 | 1,330 | 10 = 2026-09-05 - 2026-08-26

Cole Ingram total: 18 stale deals; total stale amount = 58,529.25 + 40,000 + 32,175 + 31,750 + 18,000 + 12,168 + 11,193 + 7,781.2 + 7,225.4 + 6,947.5 + 5,616 + 4,779.88 + 4,140 + 3,360 + 3,334.8 + 2,700 + 1,875 + 1,330 = 252,905.03

Farid Osman
Deal alias | Owner name | Stage | Amount | Days since last contact
Deal-8BA24E | Farid Osman | DS1 | 2,880 | 8 = 2026-09-05 - 2026-08-28
Deal-8FDCD2 | Farid Osman | DS1 | 1 | 15 = 2026-09-05 - 2026-08-21

Farid Osman total: 2 stale deals; total stale amount = 2,880 + 1 = 2,881
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 $5.5483 · 417s · in 66,761 / out 19,697 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 for DS2 entries: 2026-08-06 through 2026-09-05 inclusive.

Efficiency ranking, lowest total activities per DS2 entry = most efficient:

1. Alex Franklin
   Arithmetic: 307 emails + 36 calls + 41 meetings = 384 total activities
   Activity mix: 307/384 = 79.9% emails; 36/384 = 9.4% calls; 41/384 = 10.7% meetings
   DS2 entries: 18
   DS2 aliases: 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
   Efficiency: 384 / 18 = 21.33 activities per DS2 entry

2. Bryce Harmon
   Arithmetic: 162 emails + 0 calls + 43 meetings = 205 total activities
   Activity mix: 162/205 = 79.0% emails; 0/205 = 0.0% calls; 43/205 = 21.0% meetings
   DS2 entries: 4
   DS2 aliases: Deal-25F752, Deal-D73B89, Deal-CA7DC0, Deal-1CCE5C
   Efficiency: 205 / 4 = 51.25 activities per DS2 entry

3. Cole Ingram
   Arithmetic: 96 emails + 14 calls + 1 meeting = 111 total activities
   Activity mix: 96/111 = 86.5% emails; 14/111 = 12.6% calls; 1/111 = 0.9% meetings
   DS2 entries: 2
   DS2 aliases: Deal-42326B, Deal-1BA595
   Efficiency: 111 / 2 = 55.50 activities per DS2 entry

4. Farid Osman
   Arithmetic: 38 emails + 0 calls + 34 meetings = 72 total activities
   Activity mix: 38/72 = 52.8% emails; 0/72 = 0.0% calls; 34/72 = 47.2% meetings
   DS2 entries: 1
   DS2 aliases: Deal-499BF6
   Efficiency: 72 / 1 = 72.00 activities per DS2 entry

5. Dana Mercer
   Arithmetic: 84 emails + 18 calls + 11 meetings = 113 total activities
   Activity mix: 84/113 = 74.3% emails; 18/113 = 15.9% calls; 11/113 = 9.7% meetings
   DS2 entries: 1
   DS2 aliases: Deal-57887A
   Efficiency: 113 / 1 = 113.00 activities per DS2 entry

Missing/unranked:
- Elena Sinclair: Deal-57FF13 appears in deals_open.csv, but there is no matching engagement row in engagements_by_deal_90d.csv. Its t_ds2 is blank, so DS2 entries = 0; activity mix and activities per DS2 entry are not computable from the provided data.

Most efficient rep: Alex Franklin, 21.33 activities per DS2 entry.
Highest-volume rep: Alex Franklin, 384 total activities.
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 $5.0072 · 303s · in 57,652 / out 18,209 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

Bookings vs quota
- QTD bookings: $150,000
- Arithmetic: 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 = $150,000
- Quota: $200,000
- Attainment: $150,000 / $200,000 = 75.0%
- Gap to quota: $200,000 - $150,000 = $50,000
- Excluded pre-quarter closed-won: Deal-B3E6F1 $24,000, closed 2026-06-20

New vs expansion split
- New: $113,500 across 5 wins
  - Deal-A1C3E5 $40,000 + Deal-B7D2F4 $35,000 + Deal-C9E1A6 $21,000 + Deal-D4B8C2 $11,000 + Deal-E6F3A9 $6,500 = $113,500
  - $113,500 / $150,000 = 75.7% of bookings
- Expansion: $36,500 across 3 wins
  - Deal-F2C7D8 $20,000 + Deal-A8B4D6 $12,000 + Deal-C5D9E2 $4,500 = $36,500
  - $36,500 / $150,000 = 24.3% of bookings

Active pipeline by stage, status = open
- 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: 125 deals, $1,260,390

Rolling 90-day DS2-to-won rate
- Window: 2026-06-07 through 2026-09-05
- Deals with entered_ds2 in window: 111
- Won from that DS2 cohort by 2026-09-05: 8
- DS2-to-won rate: 8 / 111 = 7.2%

Win/loss counts and top loss reason
- Wins: 8
- Losses: 27
- Win/loss count arithmetic: 8 wins + 27 losses = 35 closed QTD outcomes
- Top loss reason: Lost- Timing (1 year or more)
  - Count: 13 of 27 losses
  - Share: 13 / 27 = 48.1%
  - Amount: $184,681
  - Arithmetic: Deal-55867E $7,200 + Deal-D1A623 $25,200 + Deal-69CF3D $11,520 + Deal-ECBF89 $7,200 + Deal-15DA99 $19,600 + Deal-79B7A1 $25,000 + Deal-F4AF5D $5,760 + Deal-B038F0 $2,340 + Deal-E6E80A $24,000 + Deal-B3ABED $40,001 + Deal-39E25C $3,360 + Deal-29326C $6,300 + Deal-831B7B $7,200 = $184,681

Activity volume, last 30 days
- Emails: 807
- Calls: 112
- Meetings: 128
- Notes: 50
- Total logged activity: 807 + 112 + 128 + 50 = 1,097

Three coaching observations
1. Alex is at 75.0% attainment with a $50,000 gap; active DS4 + DS5 pipeline is $23,574 + $45,730 = $69,304, so late-stage execution is the clearest near-term lever.
2. Loss volume is high relative to wins: 27 losses vs 8 wins, and Lost- Timing (1 year or more) is 13 / 27 losses = 48.1%, representing $184,681 in lost amount.
3. Activity is heavily email-weighted: 807 / 1,097 = 73.6% of logged activity, while calls are 112 / 1,097 = 10.2% and meetings are 128 / 1,097 = 11.7%.
multithreading-gap0.75

? 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 $3.0398 · 253s · in 35,574 / out 10,959 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
Missing data: amount, stage, and open/closed status are not provided. As-of date is not provided; using 2026-09-06, 60-day cutoff arithmetic is 2026-09-06 - 60 days = 2026-07-08. Stage-based “most valuable persona to add” cannot be determined for any deal because stage is missing.

Flagged candidate deals: 11

1. Deal-EC3025 / C-FDD0C7
- Amount: not provided
- Stage: not provided
- Active count: 1 = CT-047C54; CT-F2C1AE excluded because is_former=true
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-6827DB, Chief People Officer, economic buyer

2. Deal-92D97D / C-E23238
- Amount: not provided
- Stage: not provided
- Active count: 1 = CT-01F5B4; CT-A902AE excluded because 2026-06-01 < 2026-07-08
- Personas present: HR admin
- Personas missing: economic buyer, champion, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: none on file

3. Deal-50D386 / C-EB10E4
- Amount: not provided
- Stage: not provided
- Active count: 2 = CT-AA41B2 + CT-B9C35B
- Personas present: champion, HR admin
- Personas missing: economic buyer, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-A1C4B3, Chief People Officer, economic buyer

4. Deal-D0D6B5 / C-32918E
- Amount: not provided
- Stage: not provided
- Active count: 3 = CT-87CED4 + CT-DE6D7C + CT-FD70B2; all active contacts are champion
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-1FA4DB, Chief People Officer, economic buyer

5. Deal-5BFE3B / C-535D36
- Amount: not provided
- Stage: not provided
- Active count: 2 = CT-57123B + CT-5CE757; all active contacts are champion
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: none on file

6. Deal-36C33F / C-077A0E
- Amount: not provided
- Stage: not provided
- Active count: 1 = CT-4FE556; CT-405B45 and CT-86B22F excluded because is_former=true
- Personas present: IT security
- Personas missing: economic buyer, champion, HR admin, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-1DB73E, Chief People Officer, economic buyer

7. Deal-885F45 / C-5E8EFB
- Amount: not provided
- Stage: not provided
- Active count: 2 = CT-51C81E + CT-D9A0E8
- Personas present: economic buyer, champion
- Personas missing: HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-B3F25D, IT Security Lead, IT security

8. Deal-FCBE5B / C-737030
- Amount: not provided
- Stage: not provided
- Active count: 1 = CT-4A5317
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: none on file

9. Deal-5408B0 / C-2AE3AA
- Amount: not provided
- Stage: not provided
- Active count: 2 = CT-D33AE4 + CT-8742FD
- Personas present: champion, HR admin
- Personas missing: economic buyer, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-07FA76, Chief People Officer, economic buyer

10. Deal-C6D97A / C-5A8FC2
- Amount: not provided
- Stage: not provided
- Active count: 3 = CT-223DDC + CT-B03555 + CT-4E8A2B; all active contacts are champion
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: none on file

11. Deal-F9A08A / C-0D15DF
- Amount: not provided
- Stage: not provided
- Active count: 1 = CT-931B10; CT-913581 excluded because 2026-06-20 < 2026-07-08
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add given stage: cannot determine; stage not provided
- On-file unengaged contact who fits: CT-697541, Chief People Officer, economic buyer
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 $2.5644 · 237s · in 39,237 / out 7,707 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
First-five-minute lead:
- Main pattern: 8/10 calls = 80% led with the same retailer proof point on turnover reduction. Deals: Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-EDC141, Deal-D9A12F, Deal-84DBA6.
  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: 2/10 calls = 20%. Deal-403845 led with agenda/security/pricing; Deal-1E2498 led with straight pricing. Arithmetic: 8 + 2 = 10 calls.

Three most common objections and handling:
1. Budget locked until next fiscal year: 4/10 calls = 40%. Deals: Deal-D348E1, Deal-547B2B, Deal-60C2C2, Deal-84DBA6.
   Handling: reframes budget around turnover savings and 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 / open enrollment bandwidth: 3/10 calls = 30%. Deals: Deal-5408B0, Deal-C61CF7, Deal-D9A12F.
   Handling: proposes a smaller 90-day pilot with one department 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 cards: 3/10 calls = 30%. Deals: Deal-403845, Deal-EDC141, Deal-1E2498.
   Handling: contrasts manual recognition with automation and 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 agreement rate:
- 7 agreed next steps / 10 total calls = 70%.
- Arithmetic: 7 ÷ 10 × 100 = 70%.
- Agreed: Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-D9A12F, Deal-1E2498.
- Not agreed: Deal-403845, Deal-EDC141, Deal-84DBA6.
  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.”
- Arithmetic: 2 prospect-raised competitors across 2/10 calls. Workhuman was mentioned by Alex Franklin, not raised by a prospect, so it is not counted.

Coaching notes:
1. Tighten stalled closes: the 3 no-next-step calls ended after committee/no-urgency resistance in Deal-403845, Deal-EDC141, and Deal-84DBA6; ask for a smaller concrete step instead of ending with acknowledgment.
2. Keep the proof-point opener, but tailor it when the call context calls for pricing or security: the standard turnover story appeared in 8/10 calls, while the two exceptions were Deal-403845 and Deal-1E2498.
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 $2.9208 · 155s · in 39,011 / out 9,725 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 forecast

Quarter: 2026-07-01 to 2026-09-30. Amount currency/unit was not provided.

Category counts inside quarter:
| forecast_category | deal count |
|---|---:|
| COMMIT | 7 |
| BEST_CASE | 24 |
| PIPELINE | 23 |

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: 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: 115,976.75

Arithmetic:
(100% × 44,729) + (35% × 203,565) + (0% × PIPELINE) = 44,729 + 71,247.75 + 0 = 115,976.75

## Top 5 BEST_CASE deals inside Q3

| rank | deal_alias | amount | close_date |
|---:|---|---:|---|
| 1 | Deal-2D7423 | 38,935 | 2026-09-30 |
| 2 | Deal-25F752 | 24,000 | 2026-09-25 |
| 3 | Deal-E53952 | 19,656 | 2026-09-30 |
| 4 | Deal-5EED42 | 16,250 | 2026-09-30 |
| 5 | Deal-FA32A0 | 11,116 | 2026-09-25 |

## Deals excluded for being outside Q3

Count: 32  
Total amount: 227,575

| deal_alias | forecast_category | amount | close_date |
|---|---|---:|---|
| Deal-E51FB7 | PIPELINE | 43,875 | 2026-10-01 |
| Deal-B936FE | PIPELINE | 18,000 | 2026-10-09 |
| Deal-D9A12F | PIPELINE | 17,000 | 2026-10-15 |
| Deal-D348E1 | COMMIT | 13,770 | 2026-10-15 |
| Deal-4062CF | PIPELINE | 10,800 | 2026-10-15 |
| Deal-293AF3 | PIPELINE | 9,000 | 2026-10-09 |
| Deal-034D49 | PIPELINE | 9,000 | 2026-10-15 |
| Deal-E0ADD8 | PIPELINE | 7,920 | 2026-10-15 |
| Deal-9F2E43 | PIPELINE | 7,690 | 2026-10-08 |
| Deal-FCBE5B | PIPELINE | 7,500 | 2026-10-07 |
| Deal-712010 | PIPELINE | 7,200 | 2026-10-15 |
| Deal-6691E0 | PIPELINE | 5,700 | 2026-10-15 |
| Deal-C61CF7 | BEST_CASE | 5,400 | 2026-10-09 |
| Deal-600CD9 | PIPELINE | 5,400 | 2026-10-02 |
| Deal-A92065 | PIPELINE | 5,400 | 2026-10-15 |
| Deal-1D532E | PIPELINE | 5,400 | 2026-10-15 |
| Deal-48B656 | BEST_CASE | 5,160 | 2026-10-15 |
| Deal-E531A6 | PIPELINE | 4,800 | 2026-10-15 |
| Deal-D1E6C2 | PIPELINE | 4,400 | 2026-10-09 |
| Deal-D9E112 | PIPELINE | 4,300 | 2026-10-09 |
| Deal-5AD94B | PIPELINE | 4,000 | 2026-10-15 |
| Deal-901332 | BEST_CASE | 3,600 | 2026-10-15 |
| Deal-47AE31 | BEST_CASE | 3,600 | 2026-10-09 |
| Deal-15D24F | BEST_CASE | 3,600 | 2026-10-09 |
| Deal-766C74 | PIPELINE | 3,300 | 2026-10-14 |
| Deal-ED725A | BEST_CASE | 2,400 | 2026-10-08 |
| Deal-8AD4A5 | BEST_CASE | 1,800 | 2026-10-07 |
| Deal-D7E999 | PIPELINE | 1,800 | 2026-10-15 |
| Deal-ED13B0 | PIPELINE | 1,680 | 2026-10-09 |
| Deal-5FDCE4 | BEST_CASE | 1,600 | 2026-10-01 |
| Deal-7FA0C3 | PIPELINE | 1,400 | 2026-10-01 |
| Deal-F5A622 | BEST_CASE | 1,080 | 2026-10-08 |

Arithmetic:
43,875 + 18,000 + 17,000 + 13,770 + 10,800 + 9,000 + 9,000 + 7,920 + 7,690 + 7,500 + 7,200 + 5,700 + 5,400 + 5,400 + 5,400 + 5,400 + 5,160 + 4,800 + 4,400 + 4,300 + 4,000 + 3,600 + 3,600 + 3,600 + 3,300 + 2,400 + 1,800 + 1,800 + 1,680 + 1,600 + 1,400 + 1,080 = 227,575

## Data quality

Owner is missing on 85 of 86 rows; only Deal-C9C286 has owner Bryce Harmon. why_buys_chars is 0 on 71 of 86 rows and 49 of 54 inside-quarter rows. Forecast category and stage are inconsistent in the extract: Deal-A5E80A is DS1 COMMIT, Deal-499BF6 is DS2 COMMIT, and Deal-C61CF7 is DS5 BEST_CASE. The extract includes 32 deals dated after 2026-09-30, and the amount currency/unit is not specified.
aha-moment-2x2PASS 1.00

? 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 $4.0784 · 213s · in 59,489 / out 12,743 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
Full 2x2:

| Cohort | Definition | Cohort size | Retained at 24 months | Retention rate |
|---|---:|---:|---:|---:|
| 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% |

Excluded from denominator: 0 companies. All 220 companies had the fields needed for this test. current_status = active was counted as retained; all other statuses were counted as not retained.

Activation hypothesis result: supported directionally in this extract. Both-signals retention is higher than every comparison cohort:
65.96% vs 46.94% givers-only = +19.02 pp
65.96% vs 31.03% redemption-only = +34.93 pp
65.96% vs 40.00% neither = +25.96 pp

Single signal with largest retention lift:
Using neither as baseline:
Givers-only lift = 46.94% - 40.00% = +6.94 pp
Redemption-only lift = 31.03% - 40.00% = -8.97 pp
Largest lift: 5+ unique givers, m1_users >= 5.

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

What this does not prove: it does not prove causality, does not prove that adding givers or redemptions causes retention, and does not control for tier, ARR, industry, country, integrations, or any missing confounders.
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 $2.3801 · 186s · in 35,104 / out 7,372 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
Basis: billing total uses subscriptions with status = active. Cancelled subscriptions count as $0 current billing ARR.

CRM ARR total = sum(hubspot_arr) = $603,581.76
Billing ARR total = sum(active MRR) x 12 = $50,394.94 x 12 = $604,739.28

Variance = CRM ARR - Billing ARR
Variance = $603,581.76 - $604,739.28 = -$1,157.52
Billing is higher by $1,157.52.

Decomposition of variance:

Status mismatch = $4,905.24 + $8,253.24 = $13,158.48
Rounding = $16.00 + $20.00 = $36.00
Missing records = $16,497.24 - $28,449.24 = -$11,952.00
Other = -$2,400.00

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

Mismatched accounts:

company_alias | CRM ARR | Billing ARR | Variance | Bucket | Suggested owner
C-0C8323BF | $4,905.24 | $0.00 | $4,905.24 - $0.00 = $4,905.24 | status mismatch; SUB-000E is cancelled | RevOps/CRM owner
C-0DC4FB8C | $8,253.24 | $0.00 | $8,253.24 - $0.00 = $8,253.24 | status mismatch; SUB-000F is cancelled | RevOps/CRM owner
C-0D5BBE3A | $16,497.24 | $0.00 | $16,497.24 - $0.00 = $16,497.24 | missing records; no subscription record provided | Billing Ops/Finance
C-21629AA4 | $0.00 | $28,449.24 | $0.00 - $28,449.24 = -$28,449.24 | missing records; no CRM company record provided | RevOps/CRM owner
C-0D66DF9E | $23,200.00 | $23,184.00 | $23,200.00 - $23,184.00 = $16.00 | rounding | RevOps/CRM owner
C-14D70CE0 | $18,200.00 | $18,180.00 | $18,200.00 - $18,180.00 = $20.00 | rounding | RevOps/CRM owner
C-0F7269D7 | $24,396.00 | $26,796.00 | $24,396.00 - $26,796.00 = -$2,400.00 | other | Finance Ops/Billing owner

Named account-owner data was not provided, so suggested owners are functional owners only.

Agreement end date rule violations:

subscription_id | company_alias | term_months | cf_agreement_end_date
SUB-0002 | C-1794A52C | 24 | missing
SUB-0019 | C-22170CA1 | 36 | 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 $1.9950 · 106s · in 37,694 / out 4,801 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
No weights/users were provided, so values are simple averages across 30 company rows/month.

| KVM | 2026-08 value | 2026-07 prior | Absolute change | Relative change | Direction |
|---|---:|---:|---:|---:|---|
| Giving rate | 18.0814/30 = 0.6027 | 18.0689/30 = 0.6023 | 0.602713 - 0.602297 = +0.0004 | +0.000417/0.602297 = +0.07% | Up |
| Redemptions per user | 51.9049/30 = 1.7302 | 51.8995/30 = 1.7300 | 1.730163 - 1.729983 = +0.0002 | +0.000180/1.729983 = +0.01% | Up |
| 1:1 meetings engagement | 13.4153/30 = 0.4472 | 13.4066/30 = 0.4469 | 0.447177 - 0.446887 = +0.0003 | +0.000290/0.446887 = +0.06% | Up |
| Pulse check engagement | 15.2583/30 = 0.5086 | 18.0176/30 = 0.6006 | 0.508610 - 0.600587 = -0.0920 | -0.091977/0.600587 = -15.31% | Down |

Largest relative move: pulse check engagement, down 15.31%. Driver supported by size_band: enterprise pulse fell 0.5500→0.2743, Δ -0.2757 (-50.13%), contributing -0.0919 of total -0.0920. plan_tier does not identify a driver: 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 $5.5276 · 279s · in 76,469 / out 17,964 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
Redemptions through last completed month: 2026-08

- Redemption count: 378
- Spend: $27,846.00
  - $10,873.00 custom + $8,505.00 Tremendous + $5,238.00 Snappy + $3,230.00 TangoCard = $27,846.00
- Unique redeemers: 235
- Redemptions per redeemer: 378 ÷ 235 = 1.61

Provider mix, percent of spend:
- custom: $10,873.00 ÷ $27,846.00 = 39.1%
- Tremendous: $8,505.00 ÷ $27,846.00 = 30.5%
- Snappy: $5,238.00 ÷ $27,846.00 = 18.8%
- TangoCard: $3,230.00 ÷ $27,846.00 = 11.6%
- Total: 39.1% + 30.5% + 18.8% + 11.6% = 100.0%

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 $2.2403 · 139s · in 33,360 / out 6,886 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 arithmetic: snapshot 2026-09-05 + 120 days = 2027-01-03. Qualifies only if health_score < 60, churn_save_eligible_amount > 0, and renewal_date is on/before 2027-01-03.

Documented play-assignment rules were not provided, so play fit below uses only the cited account signals.

Qualifying at-risk accounts:

| account_alias | eligibility arithmetic | amount at stake | play | signal justifying play |
|---|---:|---:|---|---|
| C-0F6C0F34 | 51 < 60; $49,707.00 > $0; renewal in 28 days | $49,707.00 | executive touch | champion_active=false |
| C-0B827671 | 56 < 60; $25,365.00 > $0; renewal in 70 days | $25,365.00 | usage revival | usage_trend_3m=declining |
| C-0B360C78 | 57 < 60; $35,748.00 > $0; renewal in 53 days | $35,748.00 | commercial concession | churn_save_eligible_amount=$35,748.00 with renewal in 53 days; usage_trend_3m=growing and champion_active=true |
| C-0B0F1BAB | 38 < 60; $5,494.00 > $0; renewal in 18 days | $5,494.00 | executive touch | champion_active=false |
| C-0CA21961 | 58 < 60; $16,829.00 > $0; renewal in 114 days | $16,829.00 | usage revival | seats_used/seats = 84/325 = 25.8%; usage_trend_3m=flat |
| C-0E9C27D1 | 39 < 60; $41,235.00 > $0; renewal in 19 days | $41,235.00 | commercial concession | churn_save_eligible_amount=$41,235.00 with renewal in 19 days; champion_active=true and seats_used/seats = 134/157 = 85.4% |
| C-0CEF69FD | 53 < 60; $32,621.00 > $0; renewal in 77 days | $32,621.00 | executive touch | champion_active=false |
| C-0D3278C7 | 54 < 60; $17,602.00 > $0; renewal in 68 days | $17,602.00 | usage revival | usage_trend_3m=declining; seats_used/seats = 126/380 = 33.2% |

Total amount at stake:
$49,707.00 + $25,365.00 + $35,748.00 + $5,494.00 + $16,829.00 + $41,235.00 + $32,621.00 + $17,602.00 = $224,601.00

At-risk but not qualifying:

| account_alias | why it looks at risk | why it does not qualify |
|---|---|---|
| C-0BC71BDD | health_score 55 < 60 | churn_save_eligible_amount is $0.00, not > $0 |
| C-0BA71F12 | health_score 52 < 60 | renewal is in 218 days, not within 120 days |
| C-0F6694C3 | health_score 43 < 60 | churn_save_eligible_amount is $0.00, not > $0; renewal is in 197 days, not within 120 days |
| C-0BE96399 | health_score 54 < 60 | churn_save_eligible_amount is $0.00, not > $0 |
| C-0F876796 | health_score 47 < 60 | renewal is in 154 days, not within 120 days |
| C-0FCCD2DF | health_score 43 < 60 | churn_save_eligible_amount is $0.00, not > $0; renewal is in 230 days, not within 120 days |
| C-10A56B0F | health_score 54 < 60 | churn_save_eligible_amount is $0.00, not > $0 |
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 $1.0273 · 90s · in 29,707 / out 756 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 for C-0DDFC9A7

Seat coverage:
150 licensed seats / 400 headcount = 37.5% licensed over headcount.

Usage health:
Monthly active users rose from 88 in 2026-03 to 126 in 2026-08.
126 - 88 = +38 users, or 38 / 88 = 43.2% growth.

August usage was 126 active users against 150 licensed seats.
126 / 150 = 84.0% seat utilization, leaving 150 - 126 = 24 licensed seats unused.

Headroom:
Current per-seat rate = $9,000.00 ARR / 150 licensed seats = $60.00 per seat.

Seat headroom to full headcount = 400 headcount - 150 licensed seats = 250 seats.
ARR headroom at current per-seat rate = 250 * $60.00 = $15,000.00.

Who replied / can they buy:
Maria S., People Operations Coordinator, replied.
She explicitly said she is not the right person for purchasing decisions.

Right buyer from contacts:
Dana R., VP People.
Maria S. said budget and seat expansion sit with Dana R.

Reply email:
Subject: Re: Growing your team's recognition program

Hi Maria,

Thanks — really glad to hear the team is loving Bonusly.

The usage trend backs that up: monthly active users grew from 88 in March to 126 in August, so it makes sense Dana has been asking about the numbers.

Since budget and seat expansion sit with Dana, an introduction would be very helpful. I’m happy to keep it lightweight and simply share the usage snapshot so she can decide whether it’s worth discussing coverage for the broader team.

Thanks again,
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 $1.5551 · 111s · in 30,388 / out 3,575 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 — 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.
  Data shows 2 admins added; no admin-add date provided.
- 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.
- Full integrations connected: not complete because HRIS is blank, even though Slack is connected.

Early engagement signals:
- Active givers increased from 3 on 2026-08-11 to 15 on 2026-09-04.
  Arithmetic: 15 - 3 = 12 more active givers; 12 / 3 = 400% increase; 15 / 3 = 5.0x.
- First 7 days average active givers:
  3 + 3 + 4 + 4 + 5 + 4 + 7 = 30; 30 / 7 = 4.29.
- Last 7 days average active givers:
  11 + 13 + 11 + 13 + 13 + 15 + 15 = 91; 91 / 7 = 13.00.
- 7-day average change:
  13.00 - 4.29 = 8.71 more average active givers; 8.71 / 4.29 = 203.3% increase.
- Highest active_givers in provided data: 15 on 2026-09-03 and 2026-09-04.
- No target active-giver benchmark, employee count, or adoption goal was provided, so performance versus goal cannot be assessed.

Three things to cover on the call:
1. HRIS integration gap: integration_hris is blank; confirm blocker, owner, and next step.
2. First redemption gap: first_redemption_at is blank; confirm why no redemption has happened and what setup or enablement is needed.
3. Sustain early engagement: first recognition is complete and active_givers reached 15; agree next actions to maintain or expand giving momentum.
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 $3.8075 · 228s · in 46,335 / out 13,430 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
Missing data: actual company names and an explicit 90-day as-of date are not provided; using account_alias as the company identifier and all listed renewals.

Date rule used: trust Chargebee for multi-year contracts because multi-year contracts are known to be wrong in ChurnZero; trust both systems where dates agree on annual contracts.

Risk rule used: High = seat utilization <50% or 3-month usage down >=10%; Medium = seat utilization <65% or any 3-month usage decline; Low = utilization >=65% and usage flat/up. ARR at risk = High + Medium.

Date disagreements flagged:
- C-0B7D2C30: ChurnZero 2026-09-10 vs Chargebee 2026-09-15; used Chargebee because multi-year.
- C-0BCDB8C2: ChurnZero 2027-09-18 vs Chargebee 2026-09-18; used Chargebee because multi-year.
- C-0D2AB865: ChurnZero 2026-09-10 vs Chargebee 2026-09-22; used Chargebee because multi-year.
- C-0BBE3E60: ChurnZero 2027-09-26 vs Chargebee 2026-09-26; used Chargebee because multi-year.
- C-0F5D2323: ChurnZero 2026-09-10 vs Chargebee 2026-09-29; used Chargebee because multi-year.

| Company | CSM | ARR | Date used | Seat utilization | 3-month usage trend | Risk |
|---|---|---:|---|---:|---|---|
| C-0B7D2C30 | Dana Mercer | $65,901.00 | 2026-09-15; Chargebee trusted, multi-year, disagreement flagged | 274/476 = 57.6% | 97 → 94 → 84; -13/97 = -13.4% | High — Usage fell -13.4% over 3 months, creating renewal risk despite 57.6% seat utilization. |
| C-0BCDB8C2 | Cole Ingram | $54,427.00 | 2026-09-18; Chargebee trusted, multi-year, disagreement flagged | 232/424 = 54.7% | 127 → 118 → 110; -17/127 = -13.4% | High — Usage fell -13.4% over 3 months and utilization is only 54.7%. |
| C-0D2AB865 | Elena Sinclair | $38,022.00 | 2026-09-22; Chargebee trusted, multi-year, disagreement flagged | 250/407 = 61.4% | 125 → 117 → 109; -16/125 = -12.8% | High — Usage fell -12.8% over 3 months even though utilization is 61.4%. |
| C-0BBE3E60 | Dana Mercer | $30,993.00 | 2026-09-26; Chargebee trusted, multi-year, disagreement flagged | 74/114 = 64.9% | 39 → 35 → 33; -6/39 = -15.4% | High — Usage fell -15.4% over 3 months. |
| C-0F5D2323 | Cole Ingram | $90,647.00 | 2026-09-29; Chargebee trusted, multi-year, disagreement flagged | 111/390 = 28.5% | 20 → 21 → 18; -2/20 = -10.0% | High — Seat utilization is very low at 28.5% and usage fell -10.0%. |
| C-0EC6999D | Elena Sinclair | $79,419.00 | 2026-10-03; systems agree, annual term | 31/112 = 27.7% | 17 → 16 → 15; -2/17 = -11.8% | High — Seat utilization is 27.7% and usage fell -11.8%. |
| C-0B20DB64 | Dana Mercer | $21,770.00 | 2026-10-07; systems agree, annual term | 214/378 = 56.6% | 294 → 298 → 294; 0/294 = 0.0% | Medium — Usage is flat, but seat utilization is only 56.6%. |
| C-0BBC4E7A | Cole Ingram | $56,374.00 | 2026-10-10; systems agree, annual term | 228/337 = 67.7% | 142 → 141 → 139; -3/142 = -2.1% | Medium — Utilization is 67.7%, but usage slipped -2.1%. |
| C-0FD551AB | Elena Sinclair | $48,815.00 | 2026-10-14; systems agree, annual term | 210/376 = 55.9% | 123 → 122 → 126; 3/123 = 2.4% | Medium — Usage increased 2.4%, but seat utilization is only 55.9%. |
| C-0F9F8F13 | Dana Mercer | $46,230.00 | 2026-10-18; systems agree, annual term | 199/352 = 56.5% | 185 → 185 → 182; -3/185 = -1.6% | Medium — Seat utilization is 56.5% and usage declined -1.6%. |
| C-0BC34584 | Cole Ingram | $16,740.00 | 2026-10-22; systems agree, annual term | 327/494 = 66.2% | 104 → 104 → 106; 2/104 = 1.9% | Low — Utilization is 66.2% and usage increased 1.9%. |
| C-0B7A7546 | Elena Sinclair | $35,062.00 | 2026-10-25; systems agree, annual term | 182/205 = 88.8% | 64 → 65 → 63; -1/64 = -1.6% | Medium — Utilization is strong at 88.8%, but usage declined slightly by -1.6%. |
| C-0B369871 | Dana Mercer | $85,128.00 | 2026-10-29; systems agree, annual term | 317/422 = 75.1% | 326 → 330 → 333; 7/326 = 2.1% | Low — Utilization is 75.1% and usage increased 2.1%. |
| C-0B144C78 | Cole Ingram | $30,899.00 | 2026-11-02; systems agree, annual term | 169/224 = 75.4% | 101 → 101 → 106; 5/101 = 5.0% | Low — Utilization is 75.4% and usage increased 5.0%. |
| C-0FC4DBB8 | Elena Sinclair | $94,732.00 | 2026-11-05; systems agree, annual term | 356/464 = 76.7% | 189 → 191 → 193; 4/189 = 2.1% | Low — Utilization is 76.7% and usage increased 2.1%. |
| C-0D5BBE3A | Dana Mercer | $39,740.00 | 2026-11-09; systems agree, annual term | 85/102 = 83.3% | 88 → 90 → 91; 3/88 = 3.4% | Low — Utilization is 83.3% and usage increased 3.4%. |
| C-0FB9D5AF | Cole Ingram | $63,158.00 | 2026-11-13; systems agree, annual term | 144/199 = 72.4% | 173 → 173 → 176; 3/173 = 1.7% | Low — Utilization is 72.4% and usage increased 1.7%. |
| C-0B344485 | Elena Sinclair | $64,384.00 | 2026-11-16; systems agree, annual term | 224/287 = 78.0% | 238 → 240 → 244; 6/238 = 2.5% | Low — Utilization is 78.0% and usage increased 2.5%. |
| C-0CB2C1B4 | Dana Mercer | $40,628.00 | 2026-11-20; systems agree, annual term | 386/473 = 81.6% | 47 → 48 → 49; 2/47 = 4.3% | Low — Utilization is 81.6% and usage increased 4.3%. |
| C-22170CA1 | Cole Ingram | $45,646.00 | 2026-11-24; systems agree, annual term | 251/294 = 85.4% | 143 → 148 → 146; 3/143 = 2.1% | Low — Utilization is 85.4% and usage increased 2.1%. |

Total ARR renewing arithmetic:
$65,901.00 + $54,427.00 + $38,022.00 + $30,993.00 + $90,647.00 + $79,419.00 + $21,770.00 + $56,374.00 + $48,815.00 + $46,230.00 + $16,740.00 + $35,062.00 + $85,128.00 + $30,899.00 + $94,732.00 + $39,740.00 + $63,158.00 + $64,384.00 + $40,628.00 + $45,646.00 = $1,048,715.00

ARR at risk arithmetic:
High ARR = $65,901.00 + $54,427.00 + $38,022.00 + $30,993.00 + $90,647.00 + $79,419.00 = $359,409.00
Medium ARR = $21,770.00 + $56,374.00 + $48,815.00 + $46,230.00 + $35,062.00 = $208,251.00
ARR at risk = High + Medium = $359,409.00 + $208,251.00 = $567,660.00

Total ARR renewing: $1,048,715.00
ARR at risk: $567,660.00
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 $2.6952 · 160s · in 41,833 / out 8,001 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. Share = theme count / 80.

Broad patterns, ranked by ARR exposure:

| ARR rank | Theme | Count / share | Distinct accounts | ARR affected arithmetic | Two ticket ids | Recommendation |
|---:|---|---:|---|---:|---|---|
| 1 | HRIS provisioning/sync failures | 12; 12/80 = 15.0% | 3: C-0B2213A9, C-0F6C0F34, C-0DDFC9A7 | 36,000 + 30,000 + 48,000 = 114,000 | IC-460059, IC-460062 | Prioritize HRIS sync/provisioning reliability and backfill missed new-hire accounts. |
| 2 | Gift card redemption/checkout failures | 18; 18/80 = 22.5% | 7: C-0CEF69FD, C-0B827671, C-0FCCD2DF, C-0F876796, C-14264ABD, C-0D9CA315, C-0B0F1BAB | 8,900 + 10,700 + 9,600 + 8,700 + 11,000 + 9,600 + 10,300 = 68,800 | IC-460025, IC-460024 | Stabilize checkout/redemption flow and reconcile cases where points were deducted without gift card delivery. |
| 4 | Recognition points posting/balance failures | 20; 20/80 = 25.0% | 9: C-0D3278C7, C-0BF20542, C-0D0B047C, C-0BE96399, C-0D284E42, C-0D6CC8E3, C-21FEBCBB, C-0DD0626C, C-0B2895EF | 3,500 + 4,500 + 4,500 + 2,700 + 3,400 + 4,200 + 2,900 + 2,500 + 2,900 = 31,100 | IC-460004, IC-460016 | Audit recognition-to-points posting and add balance reconciliation for delayed/missing points. |
| 5 | Slack recognition integration failures | 14; 14/80 = 17.5% | 4: C-0B843542, C-10A56B0F, C-0BA71F12, C-8C2E8F00 | 4,400 + 5,400 + 3,900 + 5,200 = 18,900 | IC-460041, IC-460047 | Fix Slack sync/auth persistence and slash-command failures before expanding integration usage. |

Single-account noise, separated from broad patterns but still ARR-ranked:

| ARR rank | Theme | Count / share | Distinct accounts | ARR affected arithmetic | Two ticket ids | Recommendation |
|---:|---|---:|---|---:|---|---|
| 3 | Invoice/seat-count/tier-price billing errors | 16; 16/80 = 20.0% | 1: C-0E9C27D1 | 52,000 = 52,000 | IC-460071, IC-460078 | Treat as a high-ARR account escalation for C-0E9C27D1, but do not generalize it as a broad pattern from this data alone. |
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 $1.2562 · 51s · in 31,330 / out 1,757 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
Scoring: 1 point per exact match across industry, size_band, use_case, region. Only customers with has_case_study=true considered.

1. C-11C31562 — 3/4 match
   Arithmetic: industry 0 + size_band 1 + use_case 1 + region 1 = 3
   Match fields: size_band=Mid-Market, use_case=employee_recognition, region=NA-West
   Non-match: industry=Manufacturing vs prospect industry=Technology

2. C-64171065 — 3/4 match
   Arithmetic: industry 1 + size_band 1 + use_case 1 + region 0 = 3
   Match fields: industry=Technology, size_band=Mid-Market, use_case=employee_recognition
   Non-match: region=NA-East vs prospect region=NA-West

3. C-A13C193D — 3/4 match
   Arithmetic: industry 1 + size_band 1 + use_case 0 + region 1 = 3
   Match fields: industry=Technology, size_band=Mid-Market, region=NA-West
   Non-match: use_case=retention vs prospect use_case=employee_recognition

These three are tied on similarity score at 3/4.
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 $2.8475 · 287s · in 39,165 / out 9,292 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: 2026-03 through 2026-08. Calculations include all provided rows; SQO-before-SQM rows are flagged below.

Paid channel performance

| channel | spend | SQMs | SQOs | cost per SQM | cost per SQO | SQM-to-SQO rate | pipeline amount | pipeline per dollar |
|---|---:|---:|---:|---:|---:|---:|---:|---:|
| paid_search | 6 × $6,000 = $36,000 | 40 | 18 | $36,000 / 40 = $900 | $36,000 / 18 = $2,000 | 18 / 40 = 45.0% | 18 × $40,000 = $720,000 | $720,000 / $36,000 = 20.00 |
| linkedin_ads | 6 × $4,000 = $24,000 | 25 | 8 | $24,000 / 25 = $960 | $24,000 / 8 = $3,000 | 8 / 25 = 32.0% | 8 × $12,000 = $96,000 | $96,000 / $24,000 = 4.00 |
| paid_social | 6 × $3,000 = $18,000 | 0 | 0 | undefined ($18,000 / 0) | undefined ($18,000 / 0) | undefined (0 / 0) | $0 | $0 / $18,000 = 0.00 |
| webinars | 6 × $1,500 = $9,000 | 12 | 5 | $9,000 / 12 = $750 | $9,000 / 5 = $1,800 | 5 / 12 = 41.7% | 5 × $12,000 = $60,000 | $60,000 / $9,000 = 6.67 |

Organic / no-spend channel performance

No spend rows were provided for organic_search or referral.

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

Rows where SQO date precedes SQM date

| contact_key | channel | sqm_date | sqo_date | pipeline_amount |
|---|---|---|---|---:|
| CT-000044 | linkedin_ads | 2026-07-23 | 2026-07-18 | $12,000 |
| CT-000041 | linkedin_ads | 2026-06-14 | 2026-06-09 | $12,000 |

Reallocation recommendation: reallocate paid_social’s $18,000 trailing-six-month spend to paid_search first, because paid_social produced 0 SQMs while paid_search produced the highest pipeline per dollar: $720,000 / $36,000 = 20.00. If reallocating further, prioritize webinars over linkedin_ads on cost per SQO ($1,800 vs. $3,000), but paid_search is still strongest on pipeline per dollar.

Confidence: moderate. paid_search has the largest paid sample size at 40 SQMs / 18 SQOs. linkedin_ads has 25 SQMs / 8 SQOs and two date-order flags, reducing confidence. webinars has only 12 SQMs / 5 SQOs, so its efficiency is promising but less stable. paid_social has 0 SQMs, so confidence is high that it should not keep the same allocation without fixing the underlying issue.
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 $2.7071 · 215s · in 32,138 / out 9,683 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

## One-line positioning
Rivally is a points-based recognition platform with an engaging recognition feed (S02, S16), quick Slack-enabled setup evidence from a mid-market review (S04), and an expanding EU/Pulse story via EU data residency and Rivally Pulse engagement surveys (S06, S15, S23).

## Pricing with source and date
- Current public list: Recognition Starter is $7/user/month, annual billing required, per 2026-08-12 pricing_page (S17).
- Newer deal note: a 2026-08-14 call note says a prospect reported $7/user/mo list with a 15% discount for a 3-year term (S18).
  - Arithmetic: $7 × (1 - 0.15) = $7 × 0.85 = $5.95/user/mo for that reported 3-year quote (S18).
- Conflict: older pricing_page sources listed $5/user/month on 2026-01-20 and 2026-04-01 (S03, S08), and a 2026-06-02 deal note listed $6.50/user/mo for a 500-seat annual term (S13).
- Newer source wins: use $7/user/month annual as current public list because the 2026-08-12 pricing_page supersedes the older $5 pricing_page entries (S17 vs. S03, S08), with deal-specific discount evidence from 2026-08-14 (S18).
- Rivally Pulse is priced as an add-on, not bundled; no add-on price amount is provided (S23).

## Where they win
- Recognition engagement: reviewers praise the points-based recognition feed and say the recognition feed is 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 enterprise story: Rivally hired an ex-Workday VP EMEA to lead European expansion (S11), opened a Dublin office and made EU data residency generally available (S15), and an EU enterprise reviewer praised multi-language support for distributed EU teams (S12).
- Support: a G2 review praised support response time as under 4 hours (S22).

## Where we win
- Analytics depth: an 800-seat prospect picked Bonusly over Rivally citing analytics depth (S25).
- Analytics wedge: reviewers cite limited analytics, basic reporting dashboards, and CSV-only analytics exports during migration (S02, S07, S20).
- Enterprise admin wedge: Rivally lacks SCIM provisioning, manual user management is painful, admin tooling lags peers, and bulk recognition editing is still missing (S10, S16, S24).
- EMEA rewards wedge: a TrustRadius review says Rivally’s EMEA rewards catalog is thinner than its US catalog (S14).
- Missing data: beyond the Bonusly win cited in S25, the provided data does not include our product capabilities, so do not claim superiority outside the sourced wedges above.

## Objections and responses
- “Rivally has the better recognition experience.”
  - Response: acknowledge reviewers praise the points-based/engaging feed (S02, S16), then pivot to analytics and admin gaps: limited analytics, basic dashboards, CSV-only analytics exports, lack of SCIM, admin tooling lag, and no bulk recognition editing (S02, S07, S20, S10, S16, S24).

- “Rivally is easier to deploy and has Slack.”
  - Response: do not repeat the old Slack-gap claim; a reviewer says Slack worked out of the box and setup took under a week (S04). Reframe around enterprise scale: lack of SCIM and painful manual user management are cited by an enterprise reviewer (S10).

- “Rivally is stronger for EU teams.”
  - Response: acknowledge EU data residency GA, Dublin office, EMEA leadership hire, and multi-language praise (S15, S11, S12). Counter with the EMEA rewards catalog weakness (S14).

- “Rivally is cheaper.”
  - Response: old $5 pricing is outdated by the newer $7 pricing_page entry (S03, S08, S17). A later deal note reports $7 list with a 15% discount for a 3-year term, which calculates to $5.95/user/mo for that reported quote only (S18).

- “Rivally has Teams and Pulse.”
  - Response: Teams app v2 was in public preview as of 2026-08-20 (S19). Rivally Pulse exited beta on 2026-09-01 and is priced as an add-on, not bundled (S23).

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

## Old-card cleanup
- Old claim “Rivally lacks a Slack integration” should be removed because a reviewer says Slack integration worked out of the box (S04).
- Old claim “Rivally was acquired by WorkHuman in 2025” is UNVERIFIED: no provided snippet re-sources it.
- Old $5 pricing is re-sourced but outdated by newer $7 pricing_page data (S03, S08, S17).
- Old EU enterprise/multi-language claim is re-sourced by an EU enterprise reviewer praising multi-language support (S12).
- Not used as competitor facts: Bryce Harmon’s “UI is clunky” note is AE opinion and not verified against the product (S09); Elena Sinclair’s “discounting aggressively” note is rep opinion and not confirmed (S21).

## Our 12-month win/loss record against Rivally
- Period in provided deal data: 2025-09 through 2026-08.
- Wins: 13 deals — Deal-A9FD43, Deal-7AA785, Deal-44C524, Deal-0D0CD6, Deal-D5B790, Deal-5C636E, Deal-67BE14, Deal-1B6969, Deal-F03E7B, Deal-072E31, Deal-F65C8F, Deal-E46EAB, Deal-1D2392.
- Losses: 7 deals — Deal-7767F5, Deal-5645A5, Deal-C6FFAA, Deal-D263E0, Deal-935746, Deal-9066A6, Deal-72A02F.
- Arithmetic:
  - Total deals = 13 wins + 7 losses = 20.
  - Win rate = 13 / 20 = 65.0%.
  - Loss rate = 7 / 20 = 35.0%.
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 $2.8768 · 215s · in 52,650 / out 7,207 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
Per sequence (rates = total ÷ total sent; weakest step by reply rate):
- 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 3: 18/428=4.2%.
- Expansion Nurture: sent 300+300+275=875; reported open 565/875=64.6% but invalid; reply 59/875=6.7%; meeting 12/875=1.4%; weakest step 3: 12/275=4.4%.
- 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 3: 1/590=0.2%.
- 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 3: 6/377=1.6%.

Tracking error:
- Expansion Nurture step 2: opened 340 > sent 300.

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: opens exist, but replies do not convert: 8 replies from 545 opens; 0 meetings.
- Cold Outbound - People Ops step 3: late-step decay; 6/377=1.6%.

Changes:
- Cold Outbound - HR Leaders: rewrite step 1 CTA/value prop before more sends.
- Cold Outbound - People Ops: replace or pause step 3.

Fix first: Cold Outbound - HR Leaders; lowest reply rate and zero 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 $1.1935 · 102s · in 29,926 / out 1,643 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
Weekly marketing goals update for Q3-2026, QTD through 66 of 92 days elapsed, 66 / 92 = 71.7% of quarter elapsed.

SQMs: QTD actual 230; target 300; delta 230 - 300 = -70; pace target to date 300 × 66 / 92 = 215.2, so 230 - 215.2 = +14.8: ahead.

SQOs: QTD actual 84; target 120; delta 84 - 120 = -36; pace target to date 120 × 66 / 92 = 86.1, so 84 - 86.1 = -2.1: behind.

DS2s: QTD actual 40; target 75; delta 40 - 75 = -35; pace target to date 75 × 66 / 92 = 53.8, so 40 - 53.8 = -13.8: behind.

Closed-lost MIA rate: QTD actual 5 / 25 = 20.0%; target 10.0%; delta 20.0% - 10.0% = +10.0 pts; lower is better, so behind.

Same-quarter close count: QTD actual 10; target 20; delta 10 - 20 = -10; pace target to date 20 × 66 / 92 = 14.3, so 10 - 14.3 = -4.3: behind.

Active pipeline coverage against target: QTD actual $3,000,000; target $4,000,000; delta $3,000,000 - $4,000,000 = -$1,000,000; coverage $3,000,000 / $4,000,000 = 75.0%; pace target to date $4,000,000 × 66 / 92 = $2,869,565.2, so $3,000,000 - $2,869,565.2 = +$130,434.8: ahead.

What moved this week: no prior-week data was provided, so week-over-week movement cannot be calculated. Current QTD position shows SQMs and active pipeline ahead of elapsed-quarter pace, while SQOs, DS2s, closed-lost MIA rate, and same-quarter closes are behind pace.
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 $0.5683 · 20s · in 14,814 / out 688 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
Call Q3 at 115,976.75 weighted, not a rep-level quota forecast: 44,729 COMMIT + 0.35 × 203,565 BEST_CASE = 115,976.75, PIPELINE = 0. Only 54/86 deals are in-quarter; 32 are excluded after 2026-09-30, totaling 227,575, including Deal-D348E1 COMMIT 13,770 dated 2026-10-15 and 9 BEST_CASE totaling 28,240. Caveat: owner is blank on 85/86 and why-buys empty on 71/86, including all 7 in-quarter COMMIT deals.
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 $0.5516 · 28s · in 14,636 / out 625 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
Hi,

Following up on my Aug. 5 recap of the July 28 demo with pricing for 150 seats. The People team had a strong reaction to automated milestone awards and the points catalog, and asked for pricing.

Could you reply with whether the 150-seat pricing is still under consideration, or if we should close this out for now?

Thanks,
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 $0.5968 · 19s · in 14,500 / out 899 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: Marketing delivered 46 SQMs vs. a 52 SQM target, a gap of 6 SQMs (52 - 46 = 6). Webinar contributed 18 SQMs, or 39.1% of total SQMs (18 / 46 = 39.1%). Paid search cost per SQM held at $150; paid-search SQM volume was not provided, so total paid-search spend cannot be calculated.

Sales: Sales converted 14 SQOs, set 9 DS2 meetings, created $310,000 in new pipeline, and closed 3 same-quarter deals. DS2 meetings equaled 64.3% of SQOs (9 / 14 = 64.3%). New pipeline averaged $22,142.86 per SQO ($310,000 / 14 = $22,142.86). Weekly targets were not provided, so variance cannot be calculated.

CS: CS saved 2 renewals, Team NPS moved to 61, and 3 open red-flag accounts are heading into next week. Saved renewals minus red-flag accounts equals -1 net account-risk movement (2 - 3 = -1). Prior NPS was not provided, so the NPS change cannot be calculated.

PLG: PLG added 412 new signups, with activation at 31%, and 38 companies reached the aha moment of 10 recognition gives. Activation math is 412 × 31% = 127.72, but the exact activated-signup count was not provided. Aha-moment companies as a share of new signups is 9.2% (38 / 412 = 9.2%), noting signups and companies may not be the same unit.
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 $1.0892 · 43s · in 29,954 / out 1,059 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 for 2026-08-24 to 2026-09-04

Partner-sourced pipeline total: 5 deals, $550,000
Arithmetic: $180,000 + $95,000 + $140,000 + $60,000 + $75,000 = $550,000

Apex Rewards Co: Active. 2 partner-sourced DS1 opps: Deal-DDAAF2 ($180,000) and Deal-2CF33E ($95,000). Pipeline arithmetic: $180,000 + $95,000 = $275,000. Co-webinar locked for 09-15.

HRCloud Partners: Active. 1 partner-sourced opp: Deal-F1CDA5 ($140,000). Pipeline arithmetic: $140,000. Integration referral closed security review and moved to DS2.

CultureBridge: Active. 2 partner-sourced early-stage opps: Deal-096E1D ($60,000) and Deal-067213 ($75,000). Pipeline arithmetic: $60,000 + $75,000 = $135,000. Lunch-and-learn produced both opps.

WorkWell Group: Active. 0 partner-sourced deals, $0 pipeline. Joint playbook restart planned for Q4; planning call booked for 09-09.

Recogniq: Quiet. 0 partner-sourced deals, $0 pipeline; no period activity provided.

KudosWave: Quiet. 0 partner-sourced deals, $0 pipeline; no period activity provided.

PeopleFirst Advisors: Quiet. 0 partner-sourced deals, $0 pipeline; no period activity provided.

TotalPerk: Quiet. 0 partner-sourced deals, $0 pipeline; no period activity provided.
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 $1.2445 · 41s · in 32,614 / out 1,478 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 | Answer |
|---|---|
| Q1 | Yes. Customer data is encrypted at rest using AES-256. Citation: [P1] |
| Q2 | Yes. Data in transit is encrypted with TLS 1.2 or higher. Citation: [P1] |
| Q3 | Yes. Bonusly maintains a SOC 2 Type II report, renewed annually. The report is available to prospects under NDA. Citation: [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 point. Citation: [P3] |
| Q5 | The current subprocessor list is maintained at trust.bonusly.com. Customers receive 30 days notice before a new subprocessor is added. Arithmetic: notice period = 30 days before addition. Citation: [P4] |
| Q6 | Yes. SAML 2.0 single sign-on is available on the Enterprise plan. Citation: [P5] |
| Q7 | Production databases are backed up daily. Backups are encrypted and retained for 35 days. Arithmetic: backup frequency = every 1 day; backup retention = 35 days. Citation: [P6] |
| Q8 | Unanswerable from the provided excerpts. No excerpt states whether Bonusly holds ISO 27001 certification. The answering document would be an ISO 27001 certificate or compliance certifications statement. Citation: none in [P1]-[P8] |
| Q9 | Unanswerable from the provided excerpts. No excerpt states a contractual uptime SLA percentage. The answering document would be the SLA, MSA, or service-level terms. Citation: none in [P1]-[P8] |
| Q10 | Unanswerable from the provided excerpts. No excerpt states whether Bonusly will sign a HIPAA Business Associate Agreement. The answering document would be a HIPAA/BAA addendum or legal/compliance terms covering HIPAA. Citation: none in [P1]-[P8] |
ops-maintenance
skill-file-reconciliation0.86

? 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 $9.2137 · 455s · in 159,380 / out 24,624 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
Findings based only on the provided manifest and SKILL.md bodies.

1. CRITICAL | MERGE
Finding: ALWAYS-trigger duplicate between `comms-drafter` and `email-drafter`.
Evidence: both trigger for `"write me an email"`, `"draft a follow-up"`, `"help me reply"`, `"what should I say"`, `"bump email"`, `"contract nudge"`, and email review/rewrite requests.
Version/survivor: `comms-drafter` should survive as the broader external-communications owner; preserve `email-drafter`’s unique Gmail-signature and no-markdown email rules.
Proposal: merge `email-drafter` into `comms-drafter`.

2. WARNING | TRIM_DESC
Finding: ALWAYS-trigger overlap between `pipeline-intelligence-report` and `weekly-pipeline-report`.
Evidence: `pipeline-intelligence-report` triggers on `"run the pipeline report"`, `"pipeline review"`, `"pipeline update"`, `"what's the pipeline look like"`; `weekly-pipeline-report` triggers on `"run the pipeline update"`, `"generate the pipeline report"`, `"pipeline summary"`, `"update the pipeline"`, `"what does pipeline look like"`.
Proposal: trim generic pipeline-report wording from one description so `pipeline-intelligence-report` owns scored/tiered active-deal reporting and `weekly-pipeline-report` owns weekly SQM/SQO/DS2/bookings performance.

3. WARNING | TRIM_DESC
Finding: ALWAYS-trigger overlap between `pipeline-intelligence-report` and `sales-forecast`.
Evidence: `pipeline-intelligence-report` triggers when “any VP asks for pipeline health or forecast context”; `sales-forecast` triggers on `"pipeline forecast"`, `"forecast update"`, `"what do we think we're going to close"`, deal-level confidence, COMMIT vs BEST CASE, and quarter-close risk.
Proposal: trim descriptions so `sales-forecast` owns current-quarter revenue outlook and `pipeline-intelligence-report` owns full active-pipeline scoring.

4. WARNING | TRIM_DESC
Finding: ALWAYS-trigger overlap between `next-to-close` and `sales-forecast`.
Evidence: `next-to-close` triggers on `"what's about to close"`, `"which deals are most likely to close"`, `"closest to signature"`; `sales-forecast` triggers on `"what do we think we're going to close"` and deal-level confidence.
Proposal: trim descriptions so `next-to-close` owns shortlists of specific imminent closes and `sales-forecast` owns quarter-level forecast reporting.

5. INFO | REVIEW
Finding: Intentional trigger overlap among `analysis-validator`, `signalforge-claim-compressor`, and `signalforge-feedback`.
Evidence: all trigger around SignalForge reports, analyses, pipeline/forecast briefs, or intelligence outputs, but their bodies define a sequence: validator → compressor → feedback.
Proposal: keep overlap only if orchestration enforces that sequence.

6. CRITICAL | UPDATE_BODY
Finding: Circular delegation chain: `deal-strategy-coach` → `email-drafter` → `deal-strategy-coach`.
Evidence: `deal-strategy-coach` says manager-to-prospect emails should use `email-drafter`; `email-drafter` says deal strategy, diagnosis, or coaching should use `deal-strategy-coach`.
Proposal: make `deal-strategy-coach` the strategy owner and `email-drafter` a terminal drafting pass, not a router back to strategy.

7. CRITICAL | UPDATE_BODY
Finding: Dangling delegation target `bonusly-brand`.
Evidence: referenced by `comms-drafter`, `email-drafter`, and `sales-forecast`; no manifest row or provided file exists for `bonusly-brand`.
Proposal: add `bonusly-brand` to the manifest/file set or remove the hard dependency.

8. CRITICAL | UPDATE_BODY
Finding: Dangling delegation target `prospect-research-multithreading`.
Evidence: referenced by `comms-drafter`, `email-drafter`, and `deal-strategy-coach`; no manifest row or provided file exists for `prospect-research-multithreading`.
Proposal: add `prospect-research-multithreading` to the manifest/file set or replace it with an existing skill target.

9. WARNING | UPDATE_BODY
Finding: Dangling specialist validation targets in `analysis-validator`.
Evidence: Section 12.4 names missing targets: `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`.
Proposal: add these specialist skills to the manifest/file set or mark them as external dependencies.

10. WARNING | REVIEW
Finding: Dangling reference target `signalforge-reports`.
Evidence: `pipeline-intelligence-report` and `weekly-pipeline-report` require `/mnt/skills/organization/signalforge-reports/SKILL.md`, `DESIGN-SYSTEM.md`, and `signalforge.css`; no manifest row or provided file exists for `signalforge-reports`.
Proposal: add `signalforge-reports` as a manifest dependency or remove the mandatory reference.

11. INFO | REVIEW
Finding: Dangling reference target `caveman`.
Evidence: `signalforge-claim-compressor` says it can be used together with Caveman, but no manifest row or provided file exists for `caveman`.
Proposal: either add `caveman` or mark the comparison as informational only.

12. WARNING | UPDATE_BODY
Finding: Version conflict inside `analysis-validator`.
Evidence: body says `Version: 3.6`, `Last Updated: May 9, 2026`, and footer `analysis-validator v3.6`, but the validation trail template says `Validator: analysis-validator v3.2`; the Gate 2 decision tree says G2-A through G2-E even though v3.6 adds G2-F.
Survivor: `analysis-validator v3.6`.
Proposal: update internal version references to one surviving version.

13. WARNING | UPDATE_BODY
Finding: Version conflict inside `sales-forecast`.
Evidence: description and changelog say quarter-agnostic/current-quarter behavior, but body still contains `Open Q2 Deals`, `Q2 total`, and Q2-specific examples.
Survivor: `sales-forecast` v1.1 quarter-agnostic behavior.
Proposal: update Q2-specific body text to match the surviving quarter-agnostic version.

14. INFO | REVIEW
Finding: Manifest descriptions over 1,024 characters.
Arithmetic: 14 manifest rows inspected. Count where `description_chars > 1024` = 0. Maximum `description_chars` value = 1006. 1024 - 1006 = 18 characters below the cap.
Proposal: no TRIM_DESC action required for length.

15. WARNING | REVIEW
Finding: Hardcoded page/folder IDs in skill bodies.
Evidence:
- `deal-strategy-coach`: page `2257879045`
- `partner-digest`: folder `2286616609`; pages `2286321666`, `2265382925`, `2236940297`, `2237825028`, `2239365136`, `2238283777`
- `sales-forecast`: parent page `2232582148`; space ID `2232811524`
- `signalforge-feedback`: page `2295136266`; parent `2234417154`; Build Log page `2247295002`; space ID `2232811524`
Proposal: review which IDs are intentional constants and move volatile IDs into config/manifest metadata.

16. WARNING | REVIEW
Finding: Hardcoded dates in skill bodies.
Evidence includes:
- `analysis-validator`: `April 26, 2026`, `May 9, 2026`, `May 4, 2026`, `May 2026`
- `closed-lost-analysis`: `May 2026`, `May 4–12`, `4/13`
- `deal-strategy-coach`: `April 2026`, `2026`
- `model-selection`: `2026-05-19`, `April 14, 2026`, `Feb 2025`, `Aug 2025`, `Jan 2026`
- `partner-digest`: `May 19, 2026`, `June 2, 2026`, `May 16, 2026`, `2026-05-17`
- `pipeline-intelligence-report`: `v6 · May 2026`, `March 2023`
- `sales-forecast`: `Q2`, `Q1 2026`, `April 27, 2026`
- `signalforge-claim-compressor`: `2026-05-09`
- `stale-pipeline-report`: `5/15`, `5/19`, `5/7`, `2026-06-10`
- `weekly-pipeline-report`: `Q2 (April 1 – June 30, 2026)`, `Q1 2026`
Proposal: review dates and keep only changelog/example dates that are intentionally static.

17. WARNING | REVIEW
Finding: Hardcoded person names in skill bodies.
Evidence includes:
- `analysis-validator`: `Manish`, `Amani`, `Alaina Loori`, `Bryce Harmon`, `Hugo Lindqvist`, `Dana Mercer`, `Alex Franklin`, `Cole Ingram`, `Gavin Porter`, `Shealagh Coughlin`, `Colleen Perry`, `Ellie Barton`, `Ashley Reyer`, `Ashley Le`, `Megan Franz`, `Elena Sinclair`, `Tracy`, `Youssef Elkhateeb`, `Amanda Czenkus`, `Ben Castelli`, `Amani Phipps`, `John Thomas`, `Yasmin Wahid`
- `deal-strategy-coach`: `Farid`
- `partner-digest`: `Amani Phipps`, `Kelli`, `Jen Lee`, `Hani`, `Bryce`, `Sara`
- `pipeline-intelligence-report`: `Bryce Harmon`, `Dana Mercer`, `Cole Ingram`, `Alex Franklin`, `Gavin Porter`
- `sales-forecast`: `Alaina`, `Elena`
- `stale-pipeline-report`: `Alaina`
- `weekly-pipeline-report`: `Ben Lavin`, `Ben`
Proposal: review whether these should be live lookups, config values, or example-only text.

18. INFO | REVIEW
Finding: Manifest drift, files with no manifest row.
Arithmetic: provided skill files = 14; manifest rows = 14; matching file names = 14. Files with no manifest row = 14 - 14 = 0.
Proposal: no action required.

19. INFO | REVIEW
Finding: Manifest drift, manifest rows with no file.
Arithmetic: manifest rows = 14; provided skill files = 14; matching file names = 14. Manifest rows with no file = 14 - 14 = 0.
Proposal: no action required.
runbook-from-slack-thread0.75

? 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 $2.2724 · 186s · in 30,064 / out 7,614 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
Runbook — #incident-2026-08-29-reward-queue

1. Acknowledge alert and assign incident commander
   Source: [M01]
   Who ran it: Bryce Harmon
   Exact action taken: “PagerDuty alert fired for reward-worker queue depth > 10k. Acknowledging, taking IC.”
   Success verified: Not stated; needs confirmation if formal PagerDuty acknowledgment verification is required.
   Rollback: N/A — no system state change stated.

2. Check reward queue depth
   Source: [M02]
   Who ran it: Farid Osman
   Exact command: `bundle exec rake sidekiq:queue_depth`
   Success verified: Command showed reward queue at 48,213 pending jobs; normal is under 500.
   Rollback: N/A — read-only check.

3. Check Sidekiq dead set
   Source: [M03]
   Who ran it: Farid Osman
   Exact command/action: Command not stated; needs confirmation.
   Success verified: Dead set had 112 jobs, all Redis::TimeoutError from around 13:58.
   Rollback: N/A — read-only check as stated.

4. Pause enqueue to stop new reward jobs
   Source: [M04]
   Who ran it: Farid Osman
   Exact command: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`
   Success verified: Not independently verified in [M04]; later queue depth was down to 9,400 and falling ~1,200/min [M07], then 0 with Datadog error rate back to baseline [M08].
   Rollback: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` [M04]

5. Clear the dead set
   Source: [M05]
   Who ran it: Elena Sinclair
   Exact command/action: “While I was in the console I cleared out the dead set.” Exact console command not stated; needs confirmation.
   Success verified: Not stated; needs confirmation.
   Rollback: Not stated; needs confirmation.

6. Scale reward workers up
   Source: [M06]
   Who ran it: Bryce Harmon
   Exact command: `kubectl scale deployment/reward-worker --replicas=6`
   Success verified: Queue depth down to 9,400 and falling ~1,200/min [M07]; later `bundle exec rake sidekiq:queue_depth` returned 0 and Datadog error rate was back to baseline [M08].
   Rollback: `kubectl scale deployment/reward-worker --replicas=3` [M06]

7. Confirm queue is draining
   Source: [M07]
   Who ran it: Farid Osman
   Exact command/action: Command not stated; needs confirmation.
   Success verified: Queue depth was down to 9,400 and falling ~1,200/min.
   Rollback: N/A — verification step only.

8. Verify queue cleared and errors recovered
   Source: [M08]
   Who ran it: Cole Ingram
   Exact command/action: `bundle exec rake sidekiq:queue_depth`; checked Datadog error rate.
   Success verified: Queue depth returned 0; error rate in Datadog was back to baseline.
   Rollback: N/A — verification step only.

9. Re-enable enqueue
   Source: [M09]
   Who ran it: Bryce Harmon
   Exact command: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`
   Success verified: 40 new jobs processed cleanly in the next 3 minutes.
   Rollback: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'` — exact command appears in [M04], but [M09] does not explicitly label it as rollback; needs confirmation if formal rollback is required.

10. Scale reward workers back down
   Source: [M10]
   Who ran it: Bryce Harmon
   Exact command: `kubectl scale deployment/reward-worker --replicas=3`
   Success verified: Queue stable at 0; incident resolved.
   Rollback: `kubectl scale deployment/reward-worker --replicas=6` — exact command appears in [M06], but [M10] does not explicitly label it as rollback; needs confirmation if formal rollback is required.

Arithmetic shown from provided data:
- Initial drain to progress checkpoint: 48,213 pending jobs - 9,400 pending jobs = 38,813 fewer pending jobs [M02], [M07].
- Initial drain to cleared queue: 48,213 pending jobs - 0 pending jobs = 48,213 fewer pending jobs [M02], [M08].
- Worker scale-up: 6 replicas - 3 replicas = 3 additional replicas; 6 / 3 = 2x original worker count [M06].
- Worker scale-down: 6 replicas - 3 replicas = 3 fewer replicas, returning to the original 3 replicas [M06], [M10].
- Exact excess over “normal” cannot be calculated because normal is only stated as “under 500,” not as a specific number [M02].
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 $3.3057 · 189s · in 59,339 / out 8,475 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
Failure sequence

First error:
- 2026-09-03T14:01:12Z
- service: reward-service
- message: Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s

Service and job involved:
- First failing service shown: reward-service
- Worker service involved next: sidekiq
- Primary job shown in Datadog cascade: RewardGiveJob
- sidekiq_jobs.csv also shows RecognitionDigestJob failures later.
- Failed job arithmetic: 12 RewardGiveJob rows + 4 RecognitionDigestJob rows = 16 total Redis::TimeoutError job-failure rows.

Cascade in order, using 2026-09-03T14:01:12Z as t0:

1. 2026-09-03T14:01:12Z, t0 + 0s
   - reward-service ERROR
   - Redis connection timeout to redis-primary:6379.

2. 2026-09-03T14:01:20Z, t0 + 8s
   - Arithmetic: 14:01:20 - 14:01:12 = 8 seconds
   - reward-service ERROR
   - Redis::TimeoutError: retry exhausted for RewardGiveJob.

3. 2026-09-03T14:01:30Z and 2026-09-03T14:01:40Z, t0 + 18s and t0 + 28s
   - Arithmetic: 30 - 12 = 18 seconds; 40 - 12 = 28 seconds
   - reward-service ERROR
   - More retry exhaustion for RewardGiveJob.

4. 2026-09-03T14:01:40Z, t0 + 28s
   - sidekiq ERROR
   - RewardGiveJob failed: Redis::TimeoutError; retrying in 60s.

5. 2026-09-03T14:01:46Z, t0 + 34s
   - Arithmetic: 46 - 12 = 34 seconds
   - sidekiq_jobs.csv earliest failed job row:
   - J-00005, RewardGiveJob, Redis::TimeoutError.
   - RewardGiveJob failures continue through 2026-09-03T14:02:58Z.

6. 2026-09-03T14:02:30Z, t0 + 78s
   - Arithmetic: 1 minute 18 seconds = 78 seconds
   - sidekiq WARN
   - Queue reward depth above 10,000.

7. 2026-09-03T14:02:36Z, t0 + 84s
   - Arithmetic: 1 minute 24 seconds = 84 seconds
   - sidekiq_jobs.csv first RecognitionDigestJob failure:
   - J-00013, RecognitionDigestJob, Redis::TimeoutError.

8. 2026-09-03T14:03:05Z, t0 + 113s
   - Arithmetic: 1 minute 53 seconds = 113 seconds
   - api-gateway ERROR
   - 502 upstream timeout calling reward-service /gives.

9. 2026-09-03T14:03:30Z, t0 + 138s
   - Arithmetic: 2 minutes 18 seconds = 138 seconds
   - web-app ERROR
   - Give form submission failed: upstream 502 from api-gateway.

10. 2026-09-03T14:03:31Z through 2026-09-03T14:06:52Z
   - Continued sidekiq RewardGiveJob Redis::TimeoutError retries.
   - Continued api-gateway 502 upstream timeouts calling reward-service.
   - Continued web-app Give form submission failures.

Recovery shown:
- 2026-09-03T14:22:10Z, t0 + 20m58s
  - reward-service INFO
  - Redis connection restored; resuming job processing.
- 2026-09-03T14:24:45Z, t0 + 23m33s
  - sidekiq INFO
  - Queue reward depth below 500.

Datadog query to confirm the first error:
- Time window: 2026-09-03T14:01:00Z to 2026-09-03T14:01:15Z
- Query:
  service:reward-service @level:ERROR "Redis::TimeoutError" "redis-primary:6379"

What the logs do not show:
- They do not show why Redis timed out.
- They do not show Redis server logs or Redis metrics.
- They do not show whether the Redis issue was caused by network, load, failover, configuration, or infrastructure.
- They do not show request IDs, user IDs, tenant IDs, deal/company aliases, or job payloads.
- They do not show the total number of impacted users or submissions.
- They do not show Postgres errors; only postgres INFO checkpoint complete entries are present.
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 $1.2994 · 69s · in 30,097 / out 2,203 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
Listed export contains 9 flags, totaling 456 company-target entries:
42 + 220 + 87 + 12 + 65 + 9 + 14 + 7 + 0 = 456

On flags total 421 company-target entries:
42 + 220 + 87 + 65 + 7 = 421

Off flags total 35 company-target entries:
12 + 9 + 14 + 0 = 35

1. recognition_streaks_v2
- State: on
- Code control: records recognition streaks via `StreakTracker.record(give)` in `app/models/recognition.rb`
- Targeting rule: `segment:beta_companies`
- Company count: 42

2. points_budget_guardrails
- State: on
- Code control: enforces budget guardrails via `BudgetService.new(company).enforce!(giver, points)` in `app/services/budget_service.rb`
- Targeting rule: `all_companies`
- Company count: 220

3. slack_dm_nudges
- State: on
- Code control: sends Slack DM nudges via `SlackDm.send_nudge(user)` in `app/jobs/nudge_job.rb`
- Targeting rule: `segment:region_na`
- Company count: 87

4. redeem_flow_redesign
- State: off
- Code control: switches redemption UI between `RedeemV2Component` when enabled and `RedeemV1Component` otherwise in `app/controllers/redeem_controller.rb`
- Targeting rule: `targeted_list`
- Company count: 12

5. analytics_dashboard_v3
- State: on
- Code control: uses `AnalyticsV3.new(company)` in `app/controllers/analytics_controller.rb`
- Targeting rule: `segment:tier_three`
- Company count: 65

6. ms_teams_app_v2
- State: off
- Code control: installs Teams app v2 via `TeamsAppV2.install(company)` in `app/services/teams_installer.rb`
- Targeting rule: `targeted_list`
- Company count: 9

7. legacy_give_modal
- State: off
- Code control: no code reference in the provided excerpt
- Targeting rule: `segment:legacy_plan`
- Company count: 14

8. survey_boosters_q3
- State: on
- Code control: no code reference in the provided excerpt
- Targeting rule: `segment:legacy_plan`
- Company count: 7

9. paused_offboard_cleanup
- State: off
- Code control: no code reference in the provided excerpt
- Targeting rule: missing / blank
- Company count: 0

Flags with no code reference in the provided excerpt:
- legacy_give_modal: 14 companies
- survey_boosters_q3: 7 companies
- paused_offboard_cleanup: 0 companies

Flags with no targets:
- paused_offboard_cleanup: blank targeting rule, 0 companies
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 $0.6519 · 19s · in 14,763 / out 1,161 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: Driven by standard clauses: “Mutual confidentiality,” “Carve-outs: information that (a) is or becomes publicly available…” and “Governing law: the laws of the State of Delaware, USA”; arithmetic: 2-year term + 3-year survival = up to 5 years of confidentiality obligations, with no non-solicit, non-compete, exclusivity, or missing carve-outs.

NDA-2 — [PARTY B] and Bonusly — YELLOW: Counsel review due to embedded non-solicit: “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…”; arithmetic: 3-year term + 18 months thereafter = up to 4 years 6 months of hiring restriction, despite standard carve-outs and Delaware law.

NDA-3 — [PARTY C] and Bonusly — RED: Full legal review due to non-compete, missing carve-outs, one-way structure, unusual term, and unusual governing law: “Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser’s business,” “No confidentiality carve-outs are stated,” “One-way confidentiality in favor of [PARTY C]. Term: five (5) years,” and “laws of the Republic of Ireland… exclusive jurisdiction of its courts”; arithmetic: 3-year non-compete + 5-year one-way confidentiality term.