home · ← back to all models
nvidia

nvidia/nemotron-3-nano-30b-a3b

Mean 0.728 · 15/40 perfect tests · $0.73 total · each card: the question → the correct answer (gold) → this model's actual answer

data-crm
stage-hygiene-audit0.67

? 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 $0.0049 · 29s · in 76,079 / out 5,496 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+: any pipeline stage DS2, DS3, DS4, DS5.
why_buys: must be substantive (≥15 chars, not placeholder; LONG(n) counts).

Results:
{
  "overall_percent_non_compliant": 81.45,
  "non_compliant_by_owner": {
    "Bryce Harmon": 83.33,
    "Alex Franklin": 78.69,
    "Dana Mercer": 81.82,
    "Cole Ingram": 86.36,
    "Farid Osman": 100.0
  },
  "deals_no_ds1_timestamp": 0,
  "deals_regressed": 0,
  "process_fixes": [
    "Enforce mandatory why-buys field entry at DS2+ stage with length >=15 chars",
    "Automate timestamp validation to flag out-of-order stage entry dates",
    "Integrate why-buys validation into pipeline entry workflow to block placeholders"
  ]
}
owner-resolution0.50

? 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 $0.0809 · 360s · in 1,331,568 / out 71,741 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: 142  

Deals with owner ID not found in owners table: (none)  

Owner IDs that map to archived owners (and their names): (none)  

Total pipeline amount per resolved owner:  
- 119337721: 1054144  
- 716654662: 1249  
- 83155923: 341195  
- 83155924: 148302.5  
- 84342457: 624310
gong-hubspot-join-integrityFAIL 0.00

? The Question

Check the integrity of the call-to-deal mapping below. The gong table lists calls in the last 90 days keyed to HubSpot deal ids; deals_open lists the current open default-pipeline deals. Report: (a) count of gong rows whose deal id has NO match in deals_open (orphans; list a few sample aliases), (b) duplicate conversation keys (rows where calls_90d exceeds distinct_conversation_keys), (c) among the open deals that ARE at stage DS3 or later, the share that have at least one logged call. Give sample aliases for the orphan finding, all taken from the data. Note: gong_owner_id is a Gong user id, not a HubSpot owner id.
cost $0.0226 · 480s · in 42,276 / out 102,679 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
Orphan rows: 52 (sample aliases – Deal‑C6FE92, Deal‑F9A3C1, Deal‑03BA69).  
Duplicate conversation‑key rows: 14 (sample aliases – Deal‑03BA69, Deal‑8FDCD2, Deal‑117863).  
Among open deals at stage DS3 or later, 14 of 51 have at least one logged call ≈ 27.5 %.
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 $0.0019 · 27s · in 18,522 / out 4,836 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
-- Aggregated month‑1 company metrics from PLG.COMPANY_COHORT_SUMMARY
SELECT
    company_id,
    M1_GIVES AS unique_givers,
    M1_RECOGNITIONS AS recognition_count,
    M1_REDEMPTIONS AS successful_redemption_count
FROM PRODUCTION.PLG.COMPANY_COHORT_SUMMARY;
```
crm-completeness-enrichmentPASS 1.00

? The Question

Audit the CRM extract for completeness and propose fixes. Deals need owner, stage, amount, close date, why-buys; companies need industry, employee count, HQ country; contacts need email, title, persona. Report completeness percent per field. Identify duplicate company clusters (name variants, shared domain) with a survivor per cluster. List invalid emails and domain mismatches. Fill missing company fields only where the enrichment export has a matching row; where CRM and enrichment disagree list both and recommend a source. Never invent a value. End with the 10 fixes with the most pipeline amount at stake.
cost $0.0042 · 79s · in 20,606 / out 16,031 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
Industry completeness: 30 / 30 = 100 %
Employee‑count completeness: 22 / 30 = 0.733 → 73 %
HQ‑country completeness: 23 / 30 = 0.767 → 77 %

Duplicate company clusters (shared domain) – survivor selected:

- acme‑corp.com: aliases C‑0A092931 and C‑0A092932. Survivor = C‑0A092932 (higher employee count 510, matches enrichment industry “Technology”).
- globex.io: aliases C‑0A092933 and C‑0A092934. Survivor = C‑0A092934 (enrichment lists industry “Technology”, matching this alias).

Invalid e‑mail addresses (missing domain or empty):

- CT‑0010 : user0@  
- CT‑0022 :  (empty)  
- CT‑0080 : user0@  
- CT‑0081 : user1@  
- CT‑0192 : user2@  

Domain mismatches (e‑mail domain ≠ company domain):

- CT‑0011 : user1@other‑domain.com does not match company domain 66d1fc.com  

Missing company fields filled from enrichment (where a matching row exists):

- C‑950043 : hq_country = “United States” (enrichment)  
- C‑EC3025 : employee_count = 400 (enrichment); industry disagrees (CRM “Technology” vs Enrichment “Computer Software”) – recommend enrichment source  
- C‑96039F : employee_count = 400 (enrichment)  
- C‑44EA29 : employee_count = 400 (enrichment); industry disagrees (CRM “tech” vs Enrichment “Computer Software”) – recommend enrichment source  
- C‑B23205 : employee_count = 400 (enrichment); hq_country = “United States” (enrichment) – both fields filled from enrichment  
- C‑E51FB7 : hq_country = “United States” (enrichment) – CRM had “USA”  
- C‑D0662E : hq_country = “United States” (enrichment) – CRM had “US”  
- C‑60C75F : employee_count = 400 (enrichment); industry disagrees (CRM “tech” vs Enrichment “Computer Software”) – recommend enrichment source  
- C‑7BBDFA : employee_count = 400 (enrichment); industry matches enrichment “health care”  
- C‑50D386 : employee_count = 400 (enrichment); industry matches enrichment “health care”  

Disagreements where CRM and enrichment values differ (both shown, recommended source in brackets):

- C‑66D1FC industry: CRM “tech” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑EC3025 industry: CRM “Technology” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑44EA29 industry: CRM “tech” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑92D97D industry: CRM “Technology” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑D04904 industry: CRM “Technology” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑77A95A industry: CRM “Technology” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑AA8DDA industry: CRM “Technology” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑B25F40 industry: CRM “Technology” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑60C75F industry: CRM “tech” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑425E2A industry: CRM “Tech ” vs Enrichment “Computer Software” – **[Enrichment]**  
- C‑BA969B industry: CRM “Tech ” vs Enrichment “Computer Software” – **[Enrichment]**  

**Ten fixes addressing the largest gaps (pipeline impact cannot be ranked due to missing deal‑amount data):**

1. Set hq_country = “United States” for C‑950043 (filled from enrichment).  
2. Set employee_count = 400 for C‑EC3025 (filled from enrichment).  
3. Set employee_count = 400 for C‑96039F (filled from enrichment).  
4. Set employee_count = 400 for C‑44EA29 (filled from enrichment).  
5. Set employee_count = 400 and hq_country = “United States” for C‑B23205 (both filled from enrichment).  
6. Set hq_country = “United States” for C‑E51FB7 (filled from enrichment).  
7. Set hq_country = “United States” for C‑D0662E (filled from enrichment).  
8. Set employee_count = 400 for C‑60C75F (filled from enrichment).  
9. Set employee_count = 400 for C‑7BBDFA (filled from enrichment).  
10. Set employee_count = 400 for C‑50D386 (filled from enrichment).  

These actions complete missing fields, resolve domain mismatches, and align company records with the enrichment source where discrepancies existed.
deal-intelligence
closed-lost-classification0.60

? 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 $0.0117 · 254s · in 24,000 / out 52,542 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
Category counts:  
pricing – 1  
competitor – 22  
no decision – 7  
timing – 19  
product gap – 1  
champion left – 15  
other – 1  
(Total deals = 66)

Side split:  
buyer – 64  
Bonusly – 1  
unknown – 1  

Disagreement deals (structured tag vs. free‑text): 1 (Deal‑5DB9B0 tag “Lost‑ Does not fit ICP (write in notes)” with reason “Spam.”)

Two patterns most worth acting on:  
- competitor (22 deals) – e.g., Deal‑F7F635  
- timing (19 deals) – e.g., Deal‑DB0AAC
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 $0.0091 · 94s · in 140,227 / out 10,508 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": {
    "BUILD": 9,
    "RISKY": 33,
    "ACTION": 4,
    "LOCK": 5,
    "WATCH": 37,
    "REVIVE": 68
  },
  "tier_examples": {
    "LOCK": [
      "Deal-944310",
      "Deal-1FC049",
      "Deal-C6FE92"
    ],
    "ACTION": [
      "Deal-D348E1",
      "Deal-C26D20",
      "Deal-403845"
    ],
    "BUILD": [
      "Deal-25F752",
      "Deal-3974EB",
      "Deal-62D607"
    ],
    "REVIVE": [
      "Deal-2D1F1B",
      "Deal-66D1FC",
      "Deal-950043"
    ],
    "WATCH": [
      "Deal-6787C2",
      "Deal-40522D",
      "Deal-F0EBBB"
    ],
    "RISKY": [
      "Deal-E53952",
      "Deal-5408B0",
      "Deal-9AAE5F",
      "Deal-547B2B",
      "Deal-B7EBD1",
      "Deal-A2B47C",
      "Deal-2465CE",
      "Deal-C61CF7",
      "Deal-584EE5",
      "Deal-C6D97A",
      "Deal-F9A08A",
      "Deal-0660B4",
      "Deal-FD9F4E",
      "Deal-BA571A",
      "Deal-FC22A3",
      "Deal-7BBDFA",
      "Deal-60C2C2",
      "Deal-4A13AD",
      "Deal-8AD4A5",
      "Deal-15D24F",
      "Deal-9D0060",
      "Deal-690476",
      "Deal-635B8E",
      "Deal-ED725A",
      "Deal-55164C",
      "Deal-3BA5EA",
      "Deal-5FDCE4",
      "Deal-F336B6",
      "Deal-5EED42",
      "Deal-BA3DDC",
      "Deal-F9A3C1",
      "Deal-FA32A0"
    ]
  },
  "risky_deals": [
    "Deal-E53952",
    "Deal-5408B0",
    "Deal-9AAE5F",
    "Deal-547B2B",
    "Deal-B7EBD1",
    "Deal-A2B47C",
    "Deal-2465CE",
    "Deal-C61CF7",
    "Deal-584EE5",
    "Deal-C6D97A",
    "Deal-F9A08A",
    "Deal-0660B4",
    "Deal-FD9F4E",
    "Deal-BA571A",
    "Deal-FC22A3",
    "Deal-7BBDFA",
    "Deal-60C2C2",
    "Deal-4A13AD",
    "Deal-8AD4A5",
    "Deal-15D24F",
    "Deal-9D0060",
    "Deal-690476",
    "Deal-635B8E",
    "Deal-ED725A",
    "Deal-55164C",
    "Deal-3BA5EA",
    "Deal-5FDCE4",
    "Deal-F336B6",
    "Deal-5EED42",
    "Deal-BA3DDC",
    "Deal-F9A3C1",
    "Deal-FA32A0"
  ],
  "lock_violations": 0,
  "pipeline_shape": "The open pipeline is dominated by early‑stage PIPELINE deals (DS1‑DS2) that are classified as REVIVE or WATCH, with a smaller but steady share of LOCK and ACTION deals reflecting higher‑confidence BEST_CASE and COMMIT opportunities, while a few RISKY deals indicate mismatches between forecast category and engagement evidence."
}
call-transcript-extractionPASS 1.00

? The Question

For each transcript, extract CRM write-back fields as JSON: why-buys (prospect statements only), pain points, stakeholders from the speaker list, budget signal (prospect-stated or null), timeline signal, competitor mentioned (only if the prospect raised it), next step (only if explicitly agreed), objections, confidence. Never fill a field from what the rep said or hoped.
cost $0.0050 · 99s · in 19,541 / out 20,179 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
{
  "TX-001": {
    "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.",
      "\"Right now we track everything in a spreadsheet, and people slip through the cracks.\""
    ],
    "pain points": [
      "\"Right now we track everything in a spreadsheet, and people slip through the cracks.\""
    ],
    "stakeholders": [
      "VP People",
      "HR Admin"
    ],
    "budget signal": "$40k",
    "timeline signal": "Ideally we would have this live before open enrollment in November.",
    "competitor mentioned": "Achievers",
    "next step": "set up a security review on September 12",
    "objections": [
      "need SSO and audit logs for IT to sign off"
    ],
    "confidence": "high"
  },
  "TX-002": {
    "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": [
      "Head of Total Rewards",
      "CFO"
    ],
    "budget signal": "$25k",
    "timeline signal": "We want a decision by end of September.",
    "competitor mentioned": null,
    "next step": "send the pilot agreement and we'll route it to legal this week.",
    "objections": [],
    "confidence": "high"
  },
  "TX-003": {
    "why-buys": [
      "We need to make recognition visible across our 12 retail locations.",
      "Store managers have zero budget autonomy for on-the-spot recognition today."
    ],
    "pain points": [
      "Store managers have zero budget autonomy for on-the-spot recognition today."
    ],
    "stakeholders": [
      "People Ops Manager"
    ],
    "budget signal": null,
    "timeline signal": "no rush until Q1",
    "competitor mentioned": "Bucketlist",
    "next step": "schedule a call with our CEO",
    "objections": [
      "CEO has to be sold first — she decides anything people-related."
    ],
    "confidence": "high"
  },
  "TX-004": {
    "why-buys": [
      "We want to consolidate three separate recognition tools into one.",
      "We're paying for three tools and none of them talk to our HRIS."
    ],
    "pain points": [
      "We're paying for three tools and none of them talk to our HRIS.",
      "The security review took three months for our last vendor — that's my hesitation."
    ],
    "stakeholders": [
      "VP People",
      "IT Security Lead"
    ],
    "budget signal": "$15k annually",
    "timeline signal": null,
    "competitor mentioned": null,
    "next step": null,
    "objections": [
      "Our procurement cycle runs six to eight weeks minimum",
      "The security review took three months for our last vendor — that's my hesitation."
    ],
    "confidence": "high"
  },
  "TX-005": {
    "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": [
      "HR Director",
      "People Ops Coordinator"
    ],
    "budget signal": "$12k",
    "timeline signal": "We need this running before our January all-hands.",
    "competitor mentioned": "Nectar",
    "next step": "present to our exec team on October 2",
    "objections": [
      "Our exec team is skeptical after a failed rollout two years ago."
    ],
    "confidence": "high"
  },
  "TX-006": {
    "why-buys": [
      "I'd love to cut the admin time on service awards.",
      "I personally spend five hours a month ordering and shipping plaques."
    ],
    "pain points": [
      "I personally spend five hours a month ordering and shipping plaques."
    ],
    "stakeholders": [
      "HR Manager"
    ],
    "budget signal": null,
    "timeline signal": "Q1 start",
    "competitor mentioned": null,
    "next step": "send the one-page overview and I'll forward it to our COO this week.",
    "objections": [
      "Fair warning, our COO usually prefers building things in-house."
    ],
    "confidence": "high"
  }
}
next-to-close0.25

? The Question

Which 3 deals are closest to signature right now? Use the CRM data and the Slack thread; Slack often has the real status before the CRM does. For each: deal, amount, why it is close, what is left. Under 250 words.
cost $0.0013 · 11s · in 18,933 / out 1,913 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
Deal‑547B2B – $11,200 – Why close: Slack (Alex Franklin 2026‑09‑04 09:12) says redlines are clean, the signing page is out and the VP People confirmed they will sign tomorrow; stage DS5 COMMIT, close 2026‑09‑11. What’s left: final signature and contract execution.  

Deal‑403845 – $9,000 – Why close: Slack (Dana Mercer 2026‑09‑04 10:02) notes the order form is with the buyer’s finance team; stage DS5 COMMIT, close 2026‑09‑11. What’s left: finance approval and signing.  

Deal‑B7EBD1 – $9,000 – Why close: CRM shows DS5 COMMIT with the earliest upcoming close date (2026‑09‑10) among open COMMIT deals; no block reported. What’s left: standard legal review and signature.
product-gap-detection0.25

? 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 $0.0012 · 11s · in 18,164 / out 1,649 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
Deal‑EC3025 – real gap  
Quote: “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.”  
Deal amount: not provided  

Deal‑D0D6B5 – real gap  
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.”  
Deal amount: not provided
rep-performance
stale-pipeline-by-rep0.33

? The Question

The snapshot date is 2026-09-05. Using the open deals and the engagements-by-deal table, list every open deal with no logged email, call, or meeting in the last 7 days. Compute recency from the engagements table's last_email/last_call/last_meeting fields, NOT from any date field on the deal (the deal's last_contacted_field is unreliable). For each stale deal give: deal alias, owner name, stage, amount, days since last contact. Group by owner, order by amount descending within each owner. Then state, per owner, how many stale deals they carry and the total stale amount. (Do not write outreach text.)
cost $0.0170 · 274s · in 112,040 / out 57,155 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
Owner: Bryce Harmon
- Deal-2D1F1B | DS1 | $240,000.00 | 81
- Deal-66D1FC | DS1 | $99,000.00 | N/A
- Deal-950043 | DS1 | $70,000.00 | 19
- Deal-D73B89 | DS2 | $63,600.00 | N/A
- Deal-B23205 | DS1 | $45,000.00 | 16
- Deal-7BBDFA | DS3 | $37,440.00 | 12
- Deal-7BBDFA | DS3 | $37,440.00 | 46
- Deal-C1FA6D | DS1 | $18,000.00 | N/A
- Deal-BB8880 | DS1 | $17,400.00 | N/A
- Deal-01E193 | DS1 | $12,600.00 | N/A
- Deal-F0EBBB | DS3 | $11,400.00 | 24
- Deal-40522D | DS3 | $7,200.00 | 19
- Deal-E25A09 | DS1 | $6,000.00 | 9
- Deal-A5E80A | DS1 | $2,520.00 | N/A
- Deal-012CB1 | DS1 | $1.00 | N/A
  -> carries 15 stale deals, total stale amount $667,601.00

Owner: Alex Franklin
- Deal-1BEEBF | DS3 | $31,500.00 | 19
- Deal-1E2498 | DS3 | $16,700.00 | N/A
- Deal-36C33F | DS2 | $15,000.00 | N/A
- Deal-5296C9 | DS3 | $10,000.00 | N/A
- Deal-885F45 | DS2 | $9,300.00 | 12
- Deal-403845 | DS5 | $9,000.00 | N/A
- Deal-317E6F | DS3 | $5,400.00 | N/A
- Deal-0D2F7A | DS3 | $5,100.00 | N/A
- Deal-C6D97A | DS4 | $4,800.00 | 8
- Deal-E531A6 | DS3 | $4,800.00 | N/A
- Deal-6C60D4 | DS3 | $4,800.00 | 12
- Deal-D1E6C2 | DS2 | $4,400.00 | N/A
- Deal-5AD94B | DS2 | $4,000.00 | N/A
- Deal-9D0060 | DS3 | $3,840.00 | 12
- Deal-690476 | DS2 | $3,600.00 | 18
- Deal-EE195F | DS3 | $3,120.00 | N/A
- Deal-278DEC | DS3 | $2,700.00 | 8
- Deal-F436DA | DS2 | $2,520.00 | N/A
- Deal-6883F3 | DS1 | $2,400.00 | N/A
- Deal-1FC049 | DS4 | $1,920.00 | N/A
- Deal-7FA0C3 | DS2 | $1,400.00 | N/A
- Deal-BA571A | DS4 | $1,080.00 | 18
  -> carries 22 stale deals, total stale amount $147,380.00

Owner: Dana Mercer
- Deal-B7EBD1 | DS5 | $9,000.00 | 16
- Deal-3974EB | DS4 | $9,000.00 | 8
- Deal-0660B4 | DS4 | $1,920.00 | 16
  -> carries 3 stale deals, total stale amount $19,920.00

Owner: Cole Ingram
- Deal-FD9F4E | DS5 | $1,330.00 | N/A
  -> carries 1 stale deals, total stale amount $1,330.00

Owner: Farid Osman
- Deal-499BF6 | DS2 | $1,249.00 | N/A
  -> carries 1 stale deals, total stale amount $1,249.00
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 $0.0792 · 504s · in 1,242,427 / out 85,335 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
Rank | Owner ID | Owner Name | Total Activities | DS2 Entries | Ratio (activities per DS2 entry) | Email % | Call % | Meeting %
1 | 84342457 | Alex Franklin | 384 | 18 | 21.33 | 79.9% | 9.4% | 10.7%
2 | 119337721 | Bryce Harmon | 205 | 4 | 51.25 | 79.0% | 0.0% | 21.0%
3 | 83155924 | Cole Ingram | 111 | 2 | 55.50 | 86.5% | 12.6% | 0.9%
4 | 716654662 | Farid Osman | 72 | 1 | 72.00 | 52.8% | 0.0% | 47.2%

Most efficient rep: Alex Franklin
Highest-volume rep: Alex Franklin

Note: The most efficient and highest-volume rep are the same person.
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 $0.0505 · 379s · in 695,883 / out 78,461 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 ===
Bookings (as of 2026-09-05): $150,000
Quota (2026-Q3): $200,000
Attainment: 75.0%

New vs Expansion Split:
  New: $113,500 (75.7% of bookings)
  Expansion: $36,500 (24.3% of bookings)

Active Pipeline by Stage:
  DS1: $284,621
  DS2: $353,760
  DS3: $552,705
  DS4: $23,574
  DS5: $45,730

Rolling 90‑day DS2‑to‑won Rate: 7.2%

Win / Loss Summary:
  Wins: 8
  Losses: 27
  Top loss reason: "Lost- Timing (1 year or more)" (13 occurrences) – e.g., Deal-55624236610, Deal-62121718303

Activity Volume (last 30 days):
  Emails: 807
  Calls: 112
  Meetings: 128
  Notes: 50

=== COACHING OBSERVATIONS ===
1. Attainment is below quota – prioritize accelerating new deal closures to lift the %.
2. Expansion dominates new bookings – focus on upsell/cross‑sell with existing champions.
3. DS2‑to‑won rate is low (7.2%) – intervene early in qualification/scoping to improve conversion.
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 $0.0040 · 80s · in 19,783 / out 15,057 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
Deal-EC3025
  amount: not provided
  stage: not provided
  active contact count: 1 (CT-047C54 engaged 2026-09-02, not former)
  personas present: champion
  personas missing: economic buyer, HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-6827DB (Chief People Officer, economic buyer)

Deal-92D97D
  amount: not provided
  stage: not provided
  active contact count: 1 (CT-01F5B4 engaged 2026-08-28, not former)
  personas present: HR admin
  personas missing: economic buyer, champion, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: none on file

Deal-50D386
  amount: not provided
  stage: not provided
  active contact count: 2 (CT-AA41B2 engaged 2026-09-01, not former; CT-B9C35B engaged 2026-08-25, not former)
  personas present: champion, HR admin
  personas missing: economic buyer, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-A1C4B3 (Chief People Officer, economic buyer)

Deal-D0D6B5
  amount: not provided
  stage: not provided
  active contact count: 2 (CT-87CED4 engaged 2026-09-02, not former; CT-DE6D7C engaged 2026-08-19, not former)
  personas present: champion
  personas missing: economic buyer, HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-1FA4DB (Chief People Officer, economic buyer)

Deal-5BFE3B
  amount: not provided
  stage: not provided
  active contact count: 2 (CT-57123B engaged 2026-08-31, not former; CT-5CE757 engaged 2026-08-12, not former)
  personas present: champion
  personas missing: economic buyer, HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: none on file

Deal-36C33F
  amount: not provided
  stage: not provided
  active contact count: 1 (CT-4FE556 engaged 2026-08-15, not former)
  personas present: IT security
  personas missing: economic buyer, champion, HR admin, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-1DB73E (Chief People Officer, economic buyer)

Deal-885F45
  amount: not provided
  stage: not provided
  active contact count: 2 (CT-51C81E engaged 2026-08-26, not former; CT-D9A0E8 engaged 2026-08-11, not former)
  personas present: economic buyer, champion
  personas missing: HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-B3F25D (IT Security Lead, IT security)

Deal-C6D97A
  amount: not provided
  stage: not provided
  active contact count: 2 (CT-223DDC engaged 2026-08-31, not former; CT-B03555 engaged 2026-08-20, not former)
  personas present: champion
  personas missing: economic buyer, HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: none on file

Deal-5408B0
  amount: not provided
  stage: not provided
  active contact count: 2 (CT-D33AE4 engaged 2026-09-01, not former; CT-8742FD engaged 2026-08-18, not former)
  personas present: champion, HR admin
  personas missing: economic buyer, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-07FA76 (Chief People Officer, economic buyer)

Deal-FCBE5B
  amount: not provided
  stage: not provided
  active contact count: 1 (CT-4A5317 engaged 2026-08-29, not former)
  personas present: champion
  personas missing: economic buyer, HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: none on file

Deal-F9A08A
  amount: not provided
  stage: not provided
  active contact count: 1 (CT-931B10 engaged 2026-09-03, not former)
  personas present: champion
  personas missing: economic buyer, HR admin, IT security, finance
  most valuable persona to add given the stage: not provided
  unengaged contact: CT-697541 (Chief People Officer, economic buyer)
talk-track-from-transcripts0.80

? The Question

From this rep's last 10 calls: what they lead with in the first five minutes, how they handle the three most common objections, how often a concrete next step is agreed (rate), and every competitor a prospect raised. Quote at most one line per finding and only lines that appear in the transcripts. End with two coaching notes.
cost $0.0022 · 30s · in 20,623 / out 5,787 tok
✗ objection_count✓ next_step_rate✓ competitors✓ coaching✓ quote_used

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
Lead with (first 5 minutes): "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."

Budget objection handling: "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."

Spreadsheet objection handling: "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."

Competitor objection handling: "Kudos is solid on social recognition; our difference is automated milestones plus analytics tied to retention."

Competitor – Awardco: "We're also in late talks with Awardco — their rewards catalog looks bigger than yours."

Competitor – Kudos: "How are you different from Kudos? Our CEO used them at her last company."

Competitor – Workhuman: "And unlike Workhuman, our pricing includes the full rewards catalog with no extra margin."

Next‑step agreement rate: 7 agreed next steps out of 10 calls = 70%.

Coaching note 1: Emphasize financing savings early to pre‑empt budget lock‑outs.  
Coaching note 2: Highlight concrete differentiation against named competitors when prospects compare.
reporting-analytics
q3-weighted-forecastFAIL 0.00

? The Question

Below are the open deals in the default sales pipeline with a close date between 2026-07-01 and 2026-10-15, pulled from the CRM warehouse on 2026-09-05. Stages: DS1 (discovery) through DS5 (contract). Build the Q3 2026 forecast (quarter = 2026-07-01 to 2026-09-30). Weighting rule: 100 percent of COMMIT plus 35 percent of BEST_CASE. PIPELINE deals count zero. Only deals with a close date inside the quarter count. Report: COMMIT total, BEST_CASE total, weighted forecast, count of deals in each category inside the quarter, the deals you excluded for being outside the quarter (count and total amount), and the top 5 BEST_CASE deals by amount inside the quarter. Show arithmetic. Then, in a final '## Data quality' section of no more than four sentences, name the data quality problems in this extract that would make the forecast unreliable if it were run unattended.
cost $0.0180 · 396s · in 21,643 / out 84,478 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
COMMIT total: 35729  
BEST_CASE total: 145585  
Weighted forecast: 35729 + (0.35 × 145585) = 35729 + 50954.75 = 86683.75  

Deals inside Q3 (2026-07-01 to 2026-09-30):  
- COMMIT deals count: 6, total amount: 35729  
- BEST_CASE deals count: 14, total amount: 145585  

Excluded deals (close_date outside quarter):  
- Count: 45 deals, total amount: 56379  

Top 5 BEST_CASE deals by amount inside quarter:  
1. Deal-2D7423 – 38935  
2. Deal-25F752 – 24000  
3. Deal-E53952 – 19656  
4. Deal-5EED42 – 16250  
5. Deal-FC22A3 – 10800  

## Data quality  
The extract lacks consistent stage labeling; some deals use DS5 while others jump directly to contract, making stage‑based weighting ambiguous. Several rows omit the “why_buys_chars” field, reducing context for deal‑winning rationale. Amount precision varies (e.g., 2916.4 vs integers), which could affect weighted calculations. Finally, the CSV includes a mix of PIPELINE deals with non‑zero amounts, but the rule states PIPELINE deals count zero, indicating potential data entry errors.
aha-moment-2x20.83

? The Question

Test the activation hypothesis on the company cohort below: companies with 5+ unique givers (m1_users >= 5) AND 1+ successful redemption (m1_redemptions >= 1) in their first calendar month retain better at 24 months than those with one signal or neither. Every company in this extract is already 25+ months old, so current_status = 'active' means retained at 24 months. Report the full 2x2 (cohort size and 24-month retention rate for: both signals, givers-only, redemption-only, neither), state how many companies were excluded from the denominator and why (if none, say so), name the single signal with the largest retention lift, and state what this does and does not prove.
cost $0.1405 · 647s · in 2,274,970 / out 133,916 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
Both‑signals cohort ( m1_users ≥ 5 & m1_redemptions ≥ 1 )  
- Size: **48** companies  
- 24‑month active (retained) count: **31**  
- **Retention rate:** 31 ÷ 48 ≈ **64.6 %**

Givers‑only cohort ( m1_users ≥ 5 & m1_redemptions = 0 )  
- Size: **50** companies  
- 24‑month active count: **23**  
- **Retention rate:** 23 ÷ 50 = **46.0 %**

Redemption‑only cohort ( m1_users < 5 & m1_redemptions ≥ 1 )  
- Size: **28** companies  
- 24‑month active count: **9**  
- **Retention rate:** 9 ÷ 28 ≈ **32.1 %**

Neither‑signal cohort ( m1_users < 5 & m1_redemptions = 0 )  
- Size: **94** companies  
- 24‑month active count: **38**  
- **Retention rate:** 38 ÷ 94 ≈ **40.4 %**

**Exclusions:** 0 companies were excluded; every record had a valid m1_users and m1_redemptions value.

**Signal with the largest retention lift:**  
- The **“5+ unique givers”** signal (i.e., m1_users ≥ 5) yields a higher retention (55.1 % when considered alone) than the redemption‑only signal (≈52.6 %). Among the single‑signal groups, the givers‑only cohort’s 46 % retention is the higher of the two.

**What this does and does not prove**  
- *What it does:* Shows a clear association – companies that exhibit both activation signals (many givers + early redemption) retain at a substantially higher rate (≈65 %) than those showing only one signal or none. It also indicates that the “givers‑only” group retains better than the “redemption‑only” group.  
- *What it does not prove:* This analysis is observational; it does **not** establish causality. Retention could be driven by unobserved factors (e.g., product maturity, market segment, sales effort) that correlate with both giver activity and redemption. The groups differ in size and composition, and selection bias (e.g., only companies still alive at 25 months are considered) limits generalizability. Further causal testing (e.g., random assignment, instrumental variables) would be required to confirm the activation hypothesis.
arr-rollforward-reconciliationFAIL 0.00

? The Question

Reconcile ARR between CRM company records and billing subscriptions as of 2026-09-05. Billing ARR is MRR x 12. Report both totals, the variance, and a decomposition into buckets (status mismatch, rounding, missing records, other) that sums exactly to the variance. List each mismatched account with a suggested owner. Business rule: any subscription with a term other than 12 months must have cf_agreement_end_date populated; list violations.
cost $0.0093 · 193s · in 19,434 / out 41,561 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
Billing ARR total: 617897.76
HubSpot ARR total: 587084.52
Variance (billing – hubspot): 30813.24

Arithmetic:
- Total billing ARR = sum of MRR × 12 = 617,897.76
- Total hubspot ARR = 587,084.52
- Variance = 617,897.76 − 587,084.52 = 30,813.24

Decomposition (components sum to variance):
- Missing records: 28,449.24  (C-21629AA4 absent in hubspot)
- Status mismatch: 2,400.00  (C-0F7269D7 billing exceeds hubspot by 2,400.00)
- Rounding: -36.00  (differences: C-0D66DF9E − 16.00, C-14D70CE0 − 20.00)
- Other: 0.00

Sum check: 28,449.24 + 2,400.00 − 36.00 + 0.00 = 30,813.24

Mismatched accounts and suggested owner:
- C-0D66DF9E – owner: TBD
- C-14D70CE0 – owner: TBD
- C-0F7269D7 – owner: TBD
- C-21629AA4 – owner: missing (no hubspot record)
kvm-month-over-month0.60

? The Question

Report the four core KVMs for 2026-08 against 2026-07: giving rate, redemptions per user, 1:1 meetings engagement, pulse check engagement. For each: value, prior value, absolute and relative change, direction. Name the KVM with the largest relative move and the segment (plan_tier or size_band) driving it if the data supports that; otherwise say the data does not. Under 200 words plus one table.
cost $0.0062 · 118s · in 20,683 / out 25,600 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
Four core KVMs (2026‑08 vs 2026‑07):

KVM                     | Aug Value | Jul Value | Δ (abs) | %Δ (rel) | Direction
------------------------|-----------|-----------|---------|----------|---------
giving_rate             | 0.6027    | 0.6025    | +0.0002 | +0.03 %  | ↑
redemptions_per_user    | 1.7302    | 1.7304    | -0.0002 | -0.01 %  | ↓
one_to_one_engagement   | 0.4473    | 0.4475    | -0.0002 | -0.05 %  | ↓
pulse_engagement        | 0.5086    | 0.6005    | -0.0919 | -15.3 %  | ↓

The KVM with the largest relative move is **pulse_engagement**, and the shift is driven by the **enterprise** size_band, whose pulse engagement fell sharply in August.
rewards-ytd-section0.50

? 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 $0.0337 · 80s · in 613,822 / out 15,172 tok
✗ count✗ spend✗ unique_redeemers✓ month_named✓ provider_mix✓ top_country

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
Last completed month: 2026-08  
Redemption count: 48  
Spend: $3,536.00  
Unique redeemers: 46  
Redemptions per redeemer: 1.04  

Provider mix as percent of spend:  
- Tremendous: 32.4%  
- custom: 29.9%  
- Snappy: 23.6%  
- TangoCard: 14.1%  

Top 5 countries by redemptions:  
- US: 31  
- CA: 7  
- GB: 2  
- SG: 2  
- AU: 2
customer-success
churn-save-eligibility0.80

? The Question

Which at-risk accounts qualify for a churn-save offer under the documented eligibility rules, what amount is at stake per account and in total, and which play fits each (usage revival, executive touch, commercial concession)? Cite the signal that justifies each play. List accounts that look at risk but do not qualify and why.
cost $0.0025 · 39s · in 19,099 / out 7,898 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
Qualifying at‑risk accounts (health_score < 60, churn_save_eligible_amount > 0, renewal_date ≤ 2026‑12‑04)

- C-0F6C0F34: $49,707 – Play: usage revival (signal: usage_trend_3m = growing)  
- C-0B827671: $25,365 – Play: executive touch (signal: champion_active = true and usage_trend_3m = declining)  
- C-0B360C78: $35,748 – Play: usage revival (signal: usage_trend_3m = growing)  
- C-0B0F1BAB: $5,494 – Play: commercial concession (signal: usage_trend_3m = flat)  
- C-0E9C27D1: $41,235 – Play: commercial concession (signal: usage_trend_3m = flat)  
- C-0CEF69FD: $32,621 – Play: usage revival (signal: usage_trend_3m = growing)  
- C-0D3278C7: $17,602 – Play: executive touch (signal: usage_trend_3m = declining and champion_active = true)  
- C-0BA71F12: $6,824 – Play: executive touch (signal: usage_trend_3m = declining and champion_active = true)  

Total amount at stake: **$214,596.00**

Accounts that are at‑risk but do NOT qualify

- C-0CA21961: health_score = 58 (at‑risk) but renewal_date = 2026‑12‑28 exceeds the 120‑day window from the snapshot (2026‑09‑05), so it fails rule R3.  
- C-0BC71BDD: health_score = 55 (at‑risk) but churn_save_eligible_amount = 0, failing rule R2.  
- C-0F6694C3: health_score = 43 (at‑risk) but churn_save_eligible_amount = 0, failing rule R2.  
- C-0BE96399: health_score = 54 (at‑risk) but churn_save_eligible_amount = 0, failing rule R2.  
- C-0F876796: health_score = 47 (at‑risk) but renewal_date = 2027‑02‑06 exceeds the 120‑day window, failing rule R3.  
- C-0FCCD2DF: health_score = 43 (at‑risk) but churn_save_eligible_amount = 0, failing rule R2.  
- C-10A56B0F: health_score = 54 (at‑risk) but churn_save_eligible_amount = 0, failing rule R2.
expansion-kit0.50

? The Question

A customer replied to outreach (reply included). Build the expansion kit: seat coverage (licensed over headcount), two lines on usage health, headroom in seats and ARR at the current per-seat rate, who replied and whether they can buy, the right buyer from our contacts, and a reply email under 150 words that moves toward the right person without being pushy and cites one real usage fact.
cost $0.0024 · 43s · in 17,823 / out 7,569 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
Hi Maria,

Thanks for the update! I'm glad to hear the team is enjoying Bonusly and that usage is growing — our records show MAU increased from 88 in March 2026 to 126 in August 2026.

Dana R. (VP People) has been asking about usage numbers, and I'd love to connect with her to explore how we might expand our partnership. If you're open to it, could you introduce us when you have a moment?

No pressure at all — just wanted to say thanks for the great work.

Best,
Cole
onboarding-statusPASS 1.00

? The Question

Prep the CSM for the mid-onboarding call: what is complete (integrations connected, allowance set, admins added, first recognition given, first redemption), what is not, early engagement signals, and the three things to cover on the call. Mark nothing complete without a data field that shows it.
cost $0.0012 · 11s · in 17,899 / out 1,398 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
**Complete items (with data field)**  
- Slack integration connected: 2026‑08‑12 (recorded in onboarding_account.csv)  
- Allowance set: 2026‑08‑13 (recorded in onboarding_account.csv)  
- Admins added: 2 admins (recorded in onboarding_account.csv)  

**Items not yet complete (no data field)**  
- HRIS integration: not connected (field blank in onboarding_account.csv)  
- First recognition given: no timestamp recorded (first_recognition_at empty)  
- First redemption: no timestamp recorded (first_redemption_at empty)  

**Early engagement signals (from onboarding_usage.csv)**  
- Active givers grew from **3** on 2026‑08‑11 to **15** on 2026‑09‑04 → 5× increase.  
- Average daily active givers over the period: **≈ 8.7** (sum = 201; 201 ÷ 23 ≈ 8.7).  
- Usage shows a consistent upward trend after the first week, indicating rising adoption.  

**Three key topics for the mid‑onboarding call**  
1. **HRIS integration status** – confirm timeline for connection and any blockers.  
2. **Recognition & redemption flow** – update on when the first recognition will be issued and how redemptions will be tracked.  
3. **Usage trends & next steps** – discuss the rising active‑giver count, share the average ≈ 8.7 daily users, and outline upcoming milestones (e.g., target ≥ 15 active givers, full integration rollout).
renewal-risk-conflicting-dates0.75

? 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 $0.0081 · 105s · in 75,123 / out 21,628 tok
✓ total_renewing✓ arr_at_risk✗ disagreements_flagged✓ trust_rule

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
90‑Day Renewal Risk Brief  

---  

**C‑0B7D2C30**  
CSM: Dana Mercer  
ARR: 65901  
Renewal date used: 2026‑09‑15  
Seat utilization: 274 ÷ 476 = 57.6% (calculated)  
3‑month usage trend: Declining (usage fell from 155 → 84)  
Risk rating: Medium  
Evidence: Seat utilization 57.6% with usage declining 46% over the last year, indicating weakening engagement.  
Disagreement: ChurnZero shows 2026‑09‑10, Chargebee shows 2026‑09‑15 → using Chargebee (multi‑year contracts are known to be wrong in ChurnZero).  

**C‑0BCDB8C2**  
CSM: Cole Ingram  
ARR: 54427  
Renewal date used: 2026‑09‑18  
Seat utilization: 232 ÷ 424 = 54.7%  
3‑month usage trend: Declining (127 → 110)  
Risk rating: Medium  
Evidence: Seat utilization 54.7% and usage down 44% YoY, signaling potential churn risk.  
Disagreement: No discrepancy (dates match).  

**C‑0D2AB865**  
CSM: Elena Sinclair  
ARR: 38022  
Renewal date used: 2026‑09‑22  
Seat utilization: 250 ÷ 407 = 61.4%  
3‑month usage trend: Declining (125 → 109)  
Risk rating: Medium  
Evidence: Seat utilization 61.4% but usage trending down 42% over the past year, raising concern.  
Disagreement: ChurnZero shows 2026‑09‑10, Chargebee shows 2026‑09‑22 → using Chargebee.  

**C‑0BBE3E60**  
CSM: Dana Mercer  
ARR: 30993  
Renewal date used: 2026‑09‑26  
Seat utilization: 74 ÷ 114 = 64.9%  
3‑month usage trend: Declining (39 → 33)  
Risk rating: Medium  
Evidence: Seat utilization 64.9% yet usage fell 48% from peak, suggesting declining adoption.  
Disagreement: ChurnZero shows 2027‑09‑26, Chargebee shows 2026‑09‑26 → using Chargebee.  

**C‑0F5D2323**  
CSM: Cole Ingram  
ARR: 90647  
Renewal date used: 2026‑09‑29  
Seat utilization: 111 ÷ 390 = 28.5%  
3‑month usage trend: Stable after early dip (20 → 21 → 18)  
Risk rating: High  
Evidence: Seat utilization only 28.5% with usage stagnant at low levels, indicating high churn likelihood.  
Disagreement: ChurnZero shows 2026‑09‑10, Chargebee shows 2026‑09‑29 → using Chargebee.  

**C‑0EC6999D**  
CSM: Elena Sinclair  
ARR: 79419  
Renewal date used: 2026‑10‑03  
Seat utilization: 31 ÷ 112 = 27.7%  
3‑month usage trend: Declining (17 → 15)  
Risk rating: High  
Evidence: Seat utilization 27.7% with usage hovering low, pointing to high risk of cancellation.  
Disagreement: No discrepancy.  

**C‑0B20DB64**  
CSM: Dana Mercer  
ARR: 21770  
Renewal date used: 2026‑10‑07  
Seat utilization: 214 ÷ 378 = 56.6%  
3‑month usage trend: Stable (294 → 298 → 294)  
Risk rating: Low  
Evidence: Seat utilization 56.6% and usage stable around 300, showing healthy engagement.  

**C‑0BBC4E7A**  
CSM: Cole Ingram  
ARR: 56374  
Renewal date used: 2026‑10‑10  
Seat utilization: 228 ÷ 337 = 67.7%  
3‑month usage trend: Stable (142 → 139)  
Risk rating: Low  
Evidence: Seat utilization 67.7% with usage flat, reflecting solid adoption.  

**C‑0FD551AB**  
CSM: Elena Sinclair  
ARR: 48815  
Renewal date used: 2026‑10‑14  
Seat utilization: 210 ÷ 376 = 55.9%  
3‑month usage trend: Stable (123 → 122 → 126)  
Risk rating: Low  
Evidence: Seat utilization 55.9% and usage stable, indicating consistent usage.  

**C‑0F9F8F13**  
CSM: Dana Mercer  
ARR: 46230  
Renewal date used: 2026‑10‑18  
Seat utilization: 199 ÷ 352 = 56.5%  
3‑month usage trend: Stable (185 → 185 → 182)  
Risk rating: Low  
Evidence: Seat utilization 56.5% and usage steady, suggesting stable demand.  

**C‑0BC34584**  
CSM: Cole Ingram  
ARR: 16740  
Renewal date used: 2026‑10‑22  
Seat utilization: 327 ÷ 494 = 66.2%  
3‑month usage trend: Stable (104 → 104 → 106)  
Risk rating: Low  
Evidence: Seat utilization 66.2% and usage stable, showing reliable engagement.  

**C‑0B7A7546**  
CSM: Elena Sinclair  
ARR: 35062  
Renewal date used: 2026‑10‑25  
Seat utilization: 182 ÷ 205 = 88.8%  
3‑month usage trend: Stable (64 → 65 → 63)  
Risk rating: Low  
Evidence: Seat utilization 88.8% and usage slightly rising, indicating strong usage.  

**C‑0B369871**  
CSM: Dana Mercer  
ARR: 85128  
Renewal date used: 2026‑10‑29  
Seat utilization: 317 ÷ 422 = 75.1%  
3‑month usage trend: Rising (326 → 330 → 333)  
Risk rating: Low  
Evidence: Seat utilization 75.1% and usage growing, reflecting expanding adoption.  

**C‑0B144C78**  
CSM: Cole Ingram  
ARR: 30899  
Renewal date used: 2026‑11‑02  
Seat utilization: 169 ÷ 224 = 75.4%  
3‑month usage trend: Rising (101 → 101 → 106)  
Risk rating: Low  
Evidence: Seat utilization 75.4% and usage increasing, showing positive traction.  

**C‑0FC4DBB8**  
CSM: Elena Sinclair  
ARR: 94732  
Renewal date used: 2026‑11‑05  
Seat utilization: 356 ÷ 464 = 76.7%  
3‑month usage trend: Rising (189 → 191 → 193)  
Risk rating: Low  
Evidence: Seat utilization 76.7% and usage rising, indicating growth.  

**C‑0D5BBE3A**  
CSM: Dana Mercer  
ARR: 39740  
Renewal date used: 2026‑11‑09  
Seat utilization: 85 ÷ 102 = 83.3%  
3‑month usage trend: Rising (88 → 90 → 91)  
Risk rating: Low  
Evidence: Seat utilization 83.3% and usage increasing, reflecting strong performance.  

**C‑0FB9D5AF**  
CSM: Cole Ingram  
ARR: 63158  
Renewal date used: 2026‑11‑13  
Seat utilization: 144 ÷ 199 = 72.4%  
3‑month usage trend: Rising (173 → 173 → 176)  
Risk rating: Low  
Evidence: Seat utilization 72.4% and usage rising, indicating growth.  

**C‑0B344485**  
CSM: Elena Sinclair  
ARR: 64384  
Renewal date used: 2026‑11‑16  
Seat utilization: 224 ÷ 287 = 78.0%  
3‑month usage trend: Rising (238 → 240 → 244)  
Risk rating: Low  
Evidence: Seat utilization 78.0% and usage increasing, showing expansion.  

**C‑0CB2C1B4**  
CSM: Dana Mercer  
ARR: 40628  
Renewal date used: 2026‑11‑20  
Seat utilization: 386 ÷ 473 = 81.6%  
3‑month usage trend: Rising (47 → 48 → 49)  
Risk rating: Low  
Evidence: Seat utilization 81.6% and usage steady, reflecting stable usage.  

**C‑22170CA1**  
CSM: Cole Ingram  
ARR: 45646  
Renewal date used: 2026‑11‑24  
Seat utilization: 251 ÷ 294 = 85.3%  
3‑month usage trend: Stable (148 → 148 → 146)  
Risk rating: Low  
Evidence: Seat utilization 85.3% and usage stable, indicating robust engagement.  

---  

**Summary**  
Total ARR renewing: 65901 + 54427 + 38022 + 30993 + 90647 + 79419 + 21770 + 56374 + 48815 + 46230 + 16740 + 35062 + 85128 + 30899 + 94732 + 39740 + 63158 + 64384 + 40628 + 45646 = **1,048,715**  
ARR at risk (high‑risk accounts): 90,647 + 79,419 = **170,066**  

All disagreements flagged above were resolved by trusting the Chargebee renewal date, per the rule that multi‑year contracts are known to be incorrect in ChurnZero.
ticket-theme-synthesis0.60

? The Question

Synthesize the quarter's support tickets into 4 to 7 themes. Do not trust existing tags; read the text. Per theme: name, count, share, distinct accounts, ARR affected, two ticket ids, one-line recommendation. Separate broad patterns from single-account noise and rank by ARR exposure, not volume.
cost $0.1791 · 567s · in 2,935,306 / out 161,728 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
Theme: HRISProvisioning  
Count: 7  
Share: 0.0886  
DistinctAccounts: 3  
ARRAffected: 276000.00  
TicketIds: IC-460059, IC-460055  
Recommendation: Investigate integration issue  

Theme: CheckoutRedemption  
Count: 18  
Share: 0.2278  
DistinctAccounts: 7  
ARRAffected: 177300.00  
TicketIds: IC-460025, IC-460030  
Recommendation: Investigate integration issue  

Theme: PointsNotPosted  
Count: 20  
Share: 0.2532  
DistinctAccounts: 9  
ARRAffected: 70200.00  
TicketIds: IC-460004, IC-460016  
Recommendation: Investigate integration issue  

Theme: SlackIntegration  
Count: 12  
Share: 0.1519  
DistinctAccounts: 4  
ARRAffected: 54100.00  
TicketIds: IC-460041, IC-460047  
Recommendation: Investigate integration issue
marketing
case-study-match0.75

? The Question

Given the prospect, rank the three most similar existing customers with public case studies for use as social proof. Similarity on industry, size band, use case, region. Cite the fields that drove each match. Do not name any customer without a case study and never include billing data or contact names.
cost $0.0013 · 14s · in 18,116 / out 2,051 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
C-11C31562 – matched size_band (Mid-Market), use_case (employee_recognition), region (NA-West)  
C-64171065 – matched industry (Technology), size_band (Mid-Market), use_case (employee_recognition)  
C-CD4829A7 – matched industry (Technology), size_band (Mid-Market)
channel-attribution-math0.80

? The Question

Compute channel performance for the trailing 6 months. Paid: spend, SQMs, SQOs, cost per SQM, cost per SQO, SQM-to-SQO rate, pipeline amount, pipeline per dollar. Organic: volume, SQO rate, pipeline. Report a channel with spend and zero SQMs as undefined, not zero. Flag rows where SQO date precedes SQM date. Finish with a reallocation recommendation and your confidence given sample sizes.
cost $0.0073 · 149s · in 21,728 / out 31,090 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
Channel performance (trailing 6 months)

---  
**paid_search**  
- spend: $36,000  (6 × $6,000)  
- SQMs: 28 (all rows have a non‑empty sqm_date)  
- SQOs: 12 (non‑empty sqo_date)  
- cost per SQM: 36,000 ÷ 28 = $1,285.71  
- cost per SQO: 36,000 ÷ 12 = $3,000.00  
- SQM‑to‑SQO rate: 12 ÷ 28 = 0.43  (43 %)  
- pipeline amount: $480,000  (12 × $40,000)  
- pipeline per dollar: 480,000 ÷ 36,000 = 13.33  

**linkedin_ads**  
- spend: $24,000  (6 × $4,000)  
- SQMs: 11 (all rows have a non‑empty sqm_date)  
- SQOs: 5 (non‑empty sqo_date)  
- cost per SQM: 24,000 ÷ 11 = $2,181.82  
- cost per SQO: 24,000 ÷ 5 = $4,800.00  
- SQM‑to‑SQO rate: 5 ÷ 11 = 0.45  (45 %)  
- pipeline amount: $60,000  (5 × $12,000)  
- pipeline per dollar: 60,000 ÷ 24,000 = 2.5  
- flagged row: **CT‑000041** – sqo_date = 2026‑06‑09 precedes sqm_date = 2026‑06‑14 (order anomaly)  

**paid_social**  
- spend: $18,000  
- SQMs: 0 → cost per SQM **undefined** (no SQM data)  
- SQOs: 0 → cost per SQO **undefined**  
- SQM‑to‑SQO rate: undefined  
- pipeline amount: $0 (no contacts)  
- pipeline per dollar: undefined  

**webinars**  
- spend: $9,000  (6 × $1,500)  
- SQMs: 8 (all rows have a non‑empty sqm_date)  
- SQOs: 2 (non‑empty sqo_date)  
- cost per SQM: 9,000 ÷ 8 = $1,125.00  
- cost per SQO: 9,000 ÷ 2 = $4,500.00  
- SQM‑to‑SQO rate: 2 ÷ 8 = 0.25  (25 %)  
- pipeline amount: $24,000  (2 × $12,000)  
- pipeline per dollar: 24,000 ÷ 9,000 ≈ 2.67  

**organic_search**  
- volume (contacts): 19  
- SQO rate: 9 ÷ 19 = 0.47  (47 %)  
- pipeline amount: $81,000  (9 × $9,000)  

---  

**Reallocation recommendation**  
- Reduce or pause **paid_social** spend ($18 k) because it yields no measurable SQM/SQO activity and therefore no pipeline; re‑allocate those funds to **paid_search** (pipeline per dollar = 13.33) or **webinars** (pipeline per dollar ≈ 2.67).  
- Consider modest increase for **linkedin_ads** (pipeline per dollar = 2.5) only if the flagged order issue is resolved, as its conversion rate (45 %) is comparable to paid_search but with a lower pipeline efficiency.  

**Confidence** (based on sample size)  
- **paid_search**: high confidence – 28 SQMs and 12 SQOs provide a solid basis.  
- **linkedin_ads**: medium confidence – 11 SQMs and 5 SQOs, but the order anomaly flags data quality concerns.  
- **webinars**: low‑medium confidence – only 8 SQMs and 2 SQOs; results are more volatile.  
- **paid_social**: none – no measurable activity, so confidence in any performance claim is nil.  

Overall, shifting budget from paid_social toward paid_search is the most data‑driven adjustment given the current sample sizes.
competitor-battlecard-update0.80

? The Question

Update the battlecard for the competitor. Sections: one-line positioning, pricing with source and date (newer source wins, note the conflict), where they win, where we win, objections and responses, recent changes, our 12-month win/loss record against them. Cite a snippet id for every factual claim. Rep opinion on a call is not a fact about the competitor. Anything from the old card you cannot re-source gets marked unverified.
cost $0.0042 · 78s · in 18,970 / out 16,440 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
One-line positioning: Points‑based recognition platform for mid‑market customers. (snippet_id=S02)  
Pricing: $7 per user/month (annual) as of 2026‑08‑12 (newer source); previously listed at $5 per user/month (annual) as of 2026‑03‑05 (older source). (snippet_id=S17, snippet_id=S03)  
Where they win: EU data residency and multi‑language support; fast Slack integration out of the box. (snippet_id=S12, snippet_id=S04)  
Where we win: Advanced analytics and bulk‑editing capabilities; richer reporting versus their basic dashboards. (snippet_id=S24, snippet_id=S07)  
Objections and responses: Prospects cite limited analytics, basic reporting dashboards, lack of SCIM provisioning, no bulk editing, CSV‑only exports; we respond with deep analytics, customizable dashboards, SCIM provisioning, bulk editing, and flexible export options. (snippet_id=S02, snippet_id=S07, snippet_id=S10, snippet_id=S24, snippet_id=S20)  
Recent changes: Launch of Rivally Pulse add‑on (2026‑06‑02); pricing updated to $7 per user/month (2026‑08‑12); Dublin office opened (2026‑05‑11). (snippet_id=S23, snippet_id=S17, snippet_id=S15)  
12‑month win/loss record: 13 wins, 6 losses (19 deals) in the period from 2025‑09 to 2026‑08. (snippet_id=S01)
nurture-sequence-diagnosis0.75

? The Question

Review the sequences. Per sequence: sent, open rate, reply rate, meeting rate, weakest step. Identify tracking errors (opened above sent), audience overlap between sequences, and the failure mode for anything under 2 percent reply. One change per weak sequence and which to fix first. Under 350 words.
cost $0.0023 · 18s · in 33,867 / out 3,149 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
**Sequences – key metrics**  
| Sequence | Step | Sent | Open % | Reply % | Meetings % | Weakest step |
|----------|------|------|-------|--------|-----------|--------------|
| New Logo Nurture | 1 | 500 | 42 % | 8.4 % | 2.4 % | – |
|  | 2 | 458 | 28 % | 6.6 % | 2.0 % | – |
|  | 3 | 428 | 28 % | 4.2 % | 1.4 % | – |
| Expansion Nurture | 1 | 300 | 43 % | 7.3 % | 1.7 % | – |
|  | 2 | 300 | **113 %** (error) | 8.3 % | 1.3 % | – |
|  | 3 | 275 | 35 % | 4.4 % | 2.2 % | – |
| Cold Outbound ‑ HR Leaders | 1 | 600 | 40 % | **0.83 %** | 0.83 % | Step 1 |
|  | 2 | 595 | 30 % | **0.34 %** | 0.34 % | Step 2 |
|  | 3 | 590 | 22 % | **0.17 %** | 0.17 % | Step 3 |
| Cold Outbound ‑ People Ops | 1 | 400 | 38 % | 3.5 % | 3.5 % | – |
|  | 2 | 386 | 28 % | 2.3 % | 2.3 % | – |
|  | 3 | 377 | 21 % | **1.6 %** | 1.6 % | Step 3 |

**Tracking error** – Expansion Nurture Step 2 shows *opened (340) > sent (300)*, indicating a measurement fault.

**Audience overlap** – No contact_key appears in more than one sequence; all mappings are unique.

**Failure mode (< 2 % reply)** –  
- Cold Outbound ‑ HR Leaders: all three steps fall below 2 % reply (0.83 %, 0.34 %, 0.17 %).  
- Cold Outbound ‑ People Ops Step 3: 1.6 % reply.

**Recommended single change per weak sequence**  
1. **Cold Outbound ‑ HR Leaders – Step 3** – Add a hyper‑personalized value hook (e.g., reference a recent company Initiative) and a clear, low‑friction CTA. This addresses the poorest reply rate (0.17 %) and should be the first fix.  

2. **Cold Outbound ‑ People Ops – Step 3** – Introduce a brief, relevant case‑study snippet that aligns with the prospect’s role, increasing relevance and reply likelihood.

**Prioritization** – Fix Cold Outbound ‑ HR Leaders Step 3 first, as it records the lowest reply rate (0.17 %) and represents the biggest drop‑off in the outreach funnel.
weekly-marketing-goals-rollup0.80

? The Question

Produce the weekly marketing goals update for the active quarter: SQMs, SQOs, DS2s, closed-lost MIA rate, same-quarter close count, active pipeline coverage against target. For each: QTD actual, target, delta, pace (on/behind/ahead given days elapsed). One paragraph on what moved this week.
cost $0.0017 · 22s · in 17,679 / out 3,941 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
SQMs: QTD actual 230, target 300, delta ‑70, pace ahead (expected at this point ≈ 300 × 66/92 ≈ 215.2; actual 230 > 215.2)  
SQOs: QTD actual 84, target 120, delta ‑36, pace behind (expected ≈ 120 × 66/92 ≈ 86.1; actual 84 < 86.1)  
DS2s: QTD actual 40, target 75, delta ‑35, pace behind (expected ≈ 75 × 66/92 ≈ 53.8; actual 40 < 53.8)  
closed_lost_mia_rate: QTD actual 5 (count only), target 0.1 (rate); rate cannot be derived from the count, so delta and pace are not applicable  
same_quarter_closes: QTD actual 10, target 20, delta ‑10, pace behind (expected ≈ 20 × 66/92 ≈ 14.3; actual 10 < 14.3)  
active_pipeline: QTD actual 3000000, target 4000000, delta ‑1000000, pace ahead (expected ≈ 4000000 × 66/92 ≈ 2869560; actual 3000000 > 2869560)  

This week SQMs and active‑pipeline coverage continued to move ahead of schedule, while SQOs, DS2s, and same‑quarter closes remain behind pace. The closed‑lost MIA rate cannot be evaluated with the data provided. Overall, a few metrics are on track, but accelerating the mid‑funnel metrics is needed to meet the quarterly targets.
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 $0.0015 · 18s · in 18,044 / out 3,118 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
Q3 forecast stands at $115,977, driven by $44,729 in committed deals, $203,565 of best-case pipeline, with top deal $38,935, but $227,575 of later-quarter deals are excluded. However data quality issues, owners blank on 85 of 86 deals and missing why-buys, prevent reliable roll-up, and 32 deals close in October, including a $13,770 committed and $28,240 best-case. Proceed with caution and prioritize qualifying these pipeline deals before quarter close.
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 $0.0011 · 8s · in 17,824 / out 888 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
Subject: Quick follow‑up on our July 28 demo  

Hi Alex,

I hope you’re well. Following our July 28 demo with the People team, where the automated milestone awards and points catalog sparked interest, could we set up a short call next week to discuss pricing for 150 seats? I’m happy to share a revised proposal at your convenience.

Looking forward to your thoughts.

Best,  
[Your Name]
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 $0.0012 · 10s · in 17,633 / out 1,823 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 logged 46 SQMs this week, hitting roughly 88 % of the 52‑SQM target (46 ÷ 52 ≈ 0.88). The webinar channel alone drove 18 of those SQMs, and paid‑search cost per SQM stayed steady at **$150**.  

Sales converted **14 SQOs** and set **9 DS2 meetings**. New pipeline generated reached **$310,000**, which works out to about **$103k of pipeline per same‑quarter close** (310,000 ÷ 3 ≈ 103,333). The team closed **3** deals, reinforcing forward momentum.  

Customer Success saved **2 renewals** and lifted the team NPS to **61**. Looking ahead, there are **3 open red‑flag accounts** that will need attention next week, but the NPS trajectory remains positive.  

PLG added **412 new signups**, with activation at **31 %**. Notably, **38 companies** reached the “aha” moment of 10 recognition gives, underscoring strong early‑product engagement and product‑market fit.
partner-digest-section0.67

? The Question

Write the partner digest for the period. Every partner in the roster appears once: active plays get status with numbers, quiet partners get one line. Partner-sourced pipeline count and amount must match the deal data. Nothing omitted, nothing added.
cost $0.0013 · 12s · in 17,863 / out 2,158 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
Apex Rewards Co (active): 2 sourced opps, $275,000
HRCloud Partners (active): 1 sourced opp, $140,000
CultureBridge (active): 2 sourced opps, $135,000
WorkWell Group (active): 0 sourced opps, $0
Recogniq (quiet): 0, $0
KudosWave (quiet): 0, $0
PeopleFirst Advisors (quiet): 0, $0
TotalPerk (quiet): 0, $0
rfp-answer-from-policyPASS 1.00

? The Question

Answer the 10 questionnaire items from the policy excerpts only. Cite the excerpt id for every answer. Where the excerpts do not answer the question, mark it unanswerable and say what document would; do not guess. Tone: vendor response, direct.
cost $0.0011 · 9s · in 17,821 / out 1,163 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
**Q1:** Yes. Customer data is encrypted at rest using AES‑256. 【P1】

**Q2:** Yes. Data in transit is encrypted with TLS 1.2 or higher. 【P1】

**Q3:** Yes. Bonusly maintains a SOC 2 Type II report (renewed annually) and can provide a copy to prospects under NDA. 【P2】

**Q4:** Customer data is retained for the term of the contract plus **90 days** after which it is deleted from production systems. 【P3】

**Q5:** The subprocessor list is published at **trust.bonusly.com**, and customers receive **30‑day notice** before any new subprocessor is added. 【P4】

**Q6:** Yes. SAML 2.0 single sign‑on is available (on the Enterprise plan). 【P5】

**Q7:** Production databases are backed up **daily**, and backups are retained for **35 days**. 【P6】

**Q8:** Unanswerable. The provided excerpts do not mention ISO 27001 certification. This information would be found in a certification document or policy excerpt that states ISO 27001 compliance.

**Q9:** Unanswerable. The provided excerpts do not include any uptime SLA percentage. This would be detailed in an SLA agreement or service-level policy document.

**Q10:** Unanswerable. The provided excerpts do not address HIPAA Business Associate Agreement execution. This would be covered in a legal agreement or compliance policy document.
ops-maintenance
skill-file-reconciliationPASS 1.00

? The Question

Reconcile the skill set below against its manifest. Find and report (with severity CRITICAL/WARNING/INFO and an action type TRIM_DESC, UPDATE_BODY, DELETE_SKILL, MERGE, or REVIEW): (1) any two skills whose ALWAYS-trigger phrases overlap/duplicate, (2) any circular delegation chain between skills (name it), (3) any delegation target that does not exist (dangling, name it), (4) any version conflict and which skill should survive, (5) how many manifest descriptions exceed 1,024 characters, (6) any hardcoded page ids, dates, or person names in skill bodies, (7) manifest drift in BOTH directions (files with no manifest row, and manifest rows with no file). Make one proposal per finding; rewrite nothing.
cost $0.0058 · 37s · in 86,508 / out 7,445 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
analysis-validator & closed-lost-analysis – Overlap in ALWAYS‑trigger phrases (loss analysis, why did we lose, loss reasons, loss breakdown). SEVERITY: WARNING – ACTION: REVIEW – Proposal: Align trigger definitions to consolidate duplicate loss‑analysis triggers.

pipeline-intelligence-report & sales-forecast – Overlap in ALWAYS‑trigger phrases (pipeline report, pipeline update, “what’s the pipeline look like”). SEVERITY: WARNING – ACTION: REVIEW – Proposal: Refine trigger lists to ensure each skill’s scope is distinct.

pipeline-intelligence-report & stale-pipeline-report – Overlap in ALWAYS‑trigger phrases (pipeline report, pipeline update). SEVERITY: INFO – ACTION: REVIEW – Proposal: Differentiate trigger wording to avoid redundancy.

pipeline-intelligence-report & weekly-pipeline-report – Overlap in ALWAYS‑trigger phrases (pipeline report, pipeline summary, pipeline update). SEVERITY: INFO – ACTION: REVIEW – Proposal: Adjust triggers so each skill’s activation criteria are mutually exclusive.

Circular delegation chain – None detected. SEVERITY: INFO – ACTION: NONE – Proposal: No action required.

Dangling delegation target – analysis-validator references specialist skills bonusly-data-questions, bonusly-product-questions, bonusly-business-reporting-questions, bonusly-rewards-questions, bonusly-ppp-questions, bonusly-feature-flag-questions, bonusly-datadog-questions, none of which appear in the skill_manifest.csv. SEVERITY: CRITICAL – ACTION: DELETE_SKILL – Proposal: Remove the dangling references from analysis-validator or add the missing specialist skills to the manifest.

Version conflict – None detected. SEVERITY: INFO – ACTION: NONE – Proposal: No action required.

Manifest descriptions exceeding 1,024 characters – 0. SEVERITY: INFO – ACTION: NONE – Proposal: No action required.

Hardcoded page ids, dates, or person names in skill bodies – model-selection contains hardcoded date “2026‑05‑19”; pipeline-intelligence-report contains hardcoded date “May 2026”. SEVERITY: INFO – ACTION: REVIEW – Proposal: Replace hardcoded dates with dynamic references or external constants.

Manifest drift in BOTH directions – specialist skills referenced by analysis-validator have no manifest rows; no manifest rows are missing a corresponding skill file. SEVERITY: WARNING – ACTION: REVIEW – Proposal: Update the manifest to include the missing specialist skill definitions or remove the references from analysis-validator.
runbook-from-slack-threadPASS 1.00

? The Question

Turn the resolved incident thread into a runbook: ordered steps with the exact command or action taken, who ran it, how success was verified, and rollback for each step that changed state. Every step must trace to a message in the thread. Add nothing the thread does not contain; where the thread is unclear, mark the step as needing confirmation.
cost $0.0016 · 20s · in 18,090 / out 3,549 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
1. Disable auto_recognition_enqueue feature flag  
   - Command: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`  
   - Ran by: Farid Osman (M04)  
   - Success verified: not explicit in thread – needs confirmation  
   - Rollback command: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` (M04)  

2. Clear dead set manually  
   - Action: cleared out the dead set (manual console clear)  
   - Ran by: Elena Sinclair (M05)  
   - Success verified: not stated – needs confirmation  
   - Rollback: not specified in thread  

3. Scale reward‑worker deployment to 6 replicas  
   - Command: `kubectl scale deployment/reward-worker --replicas=6`  
   - Ran by: Bryce Harmon (M06)  
   - Success verified: queue depth down to 9,400 and falling ~1,200/min (M07)  
   - Rollback command: `kubectl scale deployment/reward-worker --replicas=3` (M06)  

4. Verify queue depth is zero and error rate baseline  
   - Command: `bundle exec rake sidekiq:queue_depth`  
   - Ran by: Cole Ingram (M08)  
   - Success verified: returns 0; error rate back to baseline (M08)  

5. Re‑enable auto_recognition_enqueue feature flag  
   - Command: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`  
   - Ran by: Bryce Harmon (M09)  
   - Success verified: 40 new jobs processed cleanly in the next 3 minutes (M09)  
   - Rollback: not provided in thread  

6. Scale reward‑worker deployment back to 3 replicas  
   - Command: `kubectl scale deployment/reward-worker --replicas=3`  
   - Ran by: Bryce Harmon (M10)  
   - Success verified: queue stable at 0 (M10)  
   - Rollback: not applicable (original replica count was 3)
datadog-incident-timeline0.80

? The Question

From the log slice, sequence the failure: first error with timestamp, the cascade in order, the service and job involved, and the Datadog query that would confirm the first error. State what the logs do not show.
cost $0.0014 · 14s · in 19,486 / out 2,297 tok
✓ first_error_ts✓ service_named✗ cascade_ordered✓ query✓ gaps_stated

✓ Correct Answer (ground truth)

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

Model's actual answer

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

**Cascade in order**  
1. **2026-09-03T14:01:12Z** – Redis timeout in **reward‑service** (triggers failure of the `RewardGiveJob`).  
2. **2026-09-03T14:01:40Z** – **sidekiq** ERROR `RewardGiveJob failed: Redis::TimeoutError; retrying in 60s`.  
3. **2026-09-03T14:02:28Z** – **sidekiq** WARN “Queue reward depth above 10,000”.  
4. **2026-09-03T14:03:05Z** – **api‑gateway** ERROR `502 upstream timeout calling reward-service /gives`.  
5. **2026-09-03T14:03:30Z** – **web‑app** ERROR “Give form submission failed: upstream 502 from api‑gateway”.  
6. Repeated **api‑gateway** 502 timeouts and **sidekiq** retry messages continue until the Redis outage clears.  
7. **2026-09-03T14:22:10Z** – **reward‑service** INFO “Redis connection restored; resuming job processing”.

**Service & job involved in the first error**  
- **Service:** `reward-service`  
- **Job:** `RewardGiveJob` (the job that enqueues reward give operations).

**Datadog query that would confirm the first error**  
A log‑based query such as:  

```
service:reward-service level:ERROR "Redis::TimeoutError"
```

or an equivalent count query to surface the first occurrence of that error string.

**What the logs do not show**  
- The underlying network or infrastructure cause of the Redis timeout (e.g., partition, CPU saturation).  
- Pre‑failure Redis latency or health metrics that could explain why the timeout occurred when it did.  
- The exact duration of the outage before the first error is logged (the logs only record the timeout event, not a prior “connection degraded” signal).  
- Any proactive circuit‑breaker or fallback action taken by the system before the error cascade.  
- Detailed queue depth trends prior to the **14:02:28Z** warning; only the spike is captured, not the build‑up.  
- Granular recovery details beyond the “Redis connection restored” INFO line (e.g., which processes resumed, how many pending jobs were cleared).  

These gaps limit visibility into the root cause and the full impact timeline.
feature-flag-state-summaryPASS 1.00

? The Question

Summarize the state of the listed feature flags: what each controls per the code excerpt, which companies or segments have it on, targeting rules, and any flag with no code reference or no targets. Company counts must match the export. Do not describe a flag that is not in the export.
cost $0.0013 · 12s · in 17,869 / out 2,188 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
recognition_streaks_v2: controls the streak‑tracking feature; enabled for companies in **segment:beta_companies**; targeting rule **segment:beta_companies**; **42** companies have it on (export count).

points_budget_guardrails: controls the points‑budget guardrails feature; enabled for **all_companies**; targeting rule **all_companies**; **220** companies have it on (export count).

slack_dm_nudges: controls Slack DM nudges; enabled for companies in **segment:region_na**; targeting rule **segment:region_na**; **87** companies have it on (export count).

redeem_flow_redesign: controls the redesigned redeem flow; currently **off**; targeting rule **targeted_list**; **12** companies are targeted when turned on (export count).

analytics_dashboard_v3: controls the analytics dashboard v3; enabled for companies in **segment:tier_three**; targeting rule **segment:tier_three**; **65** companies have it on (export count).

ms_teams_app_v2: controls installation of the Teams app v2; currently **off**; targeting rule **targeted_list**; **9** companies are targeted when turned on (export count).

legacy_give_modal: controls the legacy give modal; currently **off**; targeting rule **segment:legacy_plan**; **14** companies are targeted when turned on; **no code reference** in the excerpt.

paused_offboard_cleanup: controls the off‑board cleanup process; currently **off**; targeting rule **none** (empty); **0** companies targeted; **no code reference** in the excerpt.

survey_boosters_q3: controls the Q3 survey boosters; enabled for companies in **segment:legacy_plan**; targeting rule **segment:legacy_plan**; **7** companies have it on; **no code reference** in the excerpt.

**Arithmetic check:** sum of all `company_count` values in the export = 42 + 220 + 87 + 12 + 65 + 9 + 14 + 0 + 7 = **456**, matching the exported total.
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 $0.0011 · 8s · in 17,885 / out 1,142 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 – GREEN – Clause 1: “Mutual confidentiality. Each party may disclose Confidential Information to the other for the purpose of evaluating a business relationship.”  
NDA-2 – YELLOW – Clause 4: “During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement.”  
NDA-3 – RED – Clause 2: “For a period of three (3) years following the Effective Date, Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser's business.”