← back to all models ← RevenueBench home
cohere

cohere/command-a-plus

Mean 0.863 · 24/40 perfect tests · $3.06 total · modalities in: text, image · out: text · each card: the prompt → the correct answer (gold) → this model's actual answer

What do the modalities mean?

Modalities in means what you can send this model: text, images, files, video, or audio. Modalities out means what it can send back. Bench tasks feed text extracts, so modalities do not change the score. They are here so you know what this model can handle in real work.

data-crm 5 tests
stage-hygiene-audit0.83
Plain-English question: How much of the open DS2+ pipeline is missing a substantive why-buys, and is anything missing DS1 timestamps or out of order?
Prompt — what the model saw
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 $0.0977 · 61s · in 274,212 / out 10,319 tok
✓ noncomp_pct✓ no_ds1_0✓ regressed_0✗ per_owner_breakdown✓ definitions_first✓ three_fixes

✓ Correct Answer (ground truth)

Plain-English answer: 81.5% of the 124 DS2+ deals are missing a substantive why-buys — Alex Franklin 48, Cole Ingram 19, Dana Mercer 18, Bryce Harmon 15, Farid Osman 1 — and every deal has a DS1 timestamp with none regressed.
The answer in one line: n_deals = 156; ds2plus = 124; noncomp_pct = 81.5; bryce_noncomp = 15; no_ds1 = 0; regressed = 0 (+1 more below)
n_deals156
bryce_noncomp15
ds2plus124
no_ds10
noncomp_pct81.5
regressed0
per_owner_noncompAlex Franklin=48 of 61 (78.7%); Cole Ingram=19 of 22 (86.4%); Dana Mercer=18 of 22 (81.8%); Bryce Harmon=15 of 18 (83.3%); Farid Osman=1 of 1 (100%)
graded checksnoncomp_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+ deals: deals in stage DS2, DS3, DS4, or DS5
- Why-buys substantive: non-empty, >=15 chars, not placeholder (tbd/n/a/see notes); LONG() counts as present
- DS1 timestamp missing: t_ds1 empty
- Regression: any earlier-stage timestamp later than a later-stage timestamp

Calculations:
Total DS2+ deals: 124
Non-compliant why-buys: 101
Percent non-compliant overall: 81.45%
DS1 timestamp missing count: 0
Regressed deals count: 0

Non-compliant by owner (percent):
  Justin Durfee: 78.69%
  Jenn Tully: 81.82%
  Jake Mason: 83.33%
  Kevin Schermerhorn: 86.36%
  Saif Rahman: 100.00%

Process fixes:
1. Implement mandatory why-buys validation at DS2 entry: require 15+ character substantive text; auto-fill from previous stage if missing.
2. Enforce DS1 timestamp completion before stage advancement; add validation checkpoint in CRM workflow.
3. Add timestamp order validation audit job; flag and notify owners of regression for immediate correction.

JSON output:
{
  "definitions": {
    "DS2_plus_deals": "Deals in stage DS2, DS3, DS4, or DS5",
    "why_buys_substantive": "Non-empty, >=15 chars, not placeholder (tbd/n/a/see notes); LONG() counts as present",
    "ds1_missing": "t_ds1 timestamp empty",
    "regression": "Earlier-stage timestamp later than later-stage timestamp"
  },
  "metrics": {
    "total_ds2_plus": 124,
    "non_compliant_why_buys_overall": 101,
    "percent_non_compliant_overall": 81.45,
    "ds1_timestamp_missing": 0,
    "regressed_deals": 0,
    "non_compliant_by_owner": {
      "Justin Durfee": 78.69,
      "Jenn Tully": 81.82,
      "Jake Mason": 83.33,
      "Kevin Schermerhorn": 86.36,
      "Saif Rahman": 100.0
    }
  }
}
owner-resolution0.67
Plain-English question: Every open deal has a blank owner name — resolve each one to a real person using the owners table.
Prompt — what the model saw
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 $0.0305 · 70s · in 88,282 / out 2,704 tok
✓ resolved_count✓ unmatched_none✗ deactivated_flagged✓ jake_amount✓ justin_amount✗ no_invented

✓ Correct Answer (ground truth)

Plain-English answer: All 156 deals resolve to six named owners; jake_amount maps to Bryce Harmon ($1,054,144) and justin_amount to Alex Franklin ($624,310).
The answer in one line: jake_amount = 1,054,144; justin_amount = 624,310; resolved = 156
jake_amount1,054,144
justin_amount624,310
resolved156
deactivated
per_ownerBryce Harmon=1,054,144; Alex Franklin=624,310; Dana Mercer=341,195; Cole Ingram=288,161.43; Farid Osman=4,134; Elena Sinclair=2,100
graded checksresolved_count · unmatched_none · deactivated_flagged · jake_amount · justin_amount · no_invented

Model's actual answer

show the model's full answer
Based on the data provided:

**Deals resolved:** 156 of 169 total open deals had matching owner_ids in the owners table.

**Deals with unmatched owner IDs:** 0 deals. All owner_ids present in deals exist in owners.csv.

**Archived/deactivated owners with resolved deals:** None. All resolved owners are marked "false" in the archived column.

**Total pipeline amount per resolved owner:**
- Jake Mason: $1,054,144.00 (119337721)
- Justin Durfee: $624,310.00 (84342457)  
- Jenn Tully: $341,195.00 (83155923)
- Kevin Schermerhorn: $288,161.43 (83155924)
- Saif Rahman: $4,134.00 (716654662)
- Tracie Wilson: $2,100.00 (701163055)

**Calculation verification:** Sum of resolved amounts = $2,314,044.43, matching the sum of individual owner totals.
gong-hubspot-join-integrityPASS 1.00
Plain-English question: How many call records point at deal ids that do not exist in the open pipeline?
Prompt — what the model saw
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 $0.0239 · 23s · in 64,923 / out 2,954 tok
✓ orphan_count✓ dup_keys_0✓ ds3_coverage✓ sample_ids_present

✓ Correct Answer (ground truth)

Plain-English answer: 30 Gong call rows are orphans keyed to dead deal ids, none are duplicates, and DS3 call coverage is 29.4%.
The answer in one line: orphans = 30; ds3_cov_pct = 29.4; dup = 0
orphans30
ds3_cov_pct29.4
dup0
orphan_aliasesDeal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42, Deal-36EA09
graded checksorphan_count · dup_keys_0 · ds3_coverage · sample_ids_present

Model's actual answer

show the model's full answer
**Call-to-Deal Mapping Integrity Report**

**(a) Orphan Gong Rows**
- Gong rows: 67
- Unique deal IDs: 67  
- Orphan deal IDs (no match in deals_open): 30
- Arithmetic: 30 ÷ 67 = 44.8% of gong rows are orphans
- Sample orphan aliases (from data):
  - Deal-8FA85D (hs_deal_id: 60251290957)
  - Deal-8FC3F9 (hs_deal_id: 60251649055)  
  - Deal-3B7945 (hs_deal_id: 60251639682)
  - Deal-42B265 (hs_deal_id: 61227242540)
  - Deal-9CCC42 (hs_deal_id: 61430316324)

**(b) Duplicate Conversation Keys**
- Rows where calls_90d > distinct_conversation_keys: 0
- Arithmetic: 0 ÷ 67 = 0.0% have duplicate conversation keys
- No duplicate conversation key issues found

**(c) DS3+ Deal Coverage**
- Open deals at DS3/DS4/DS5: 85
- DS3+ deals with logged calls: 25
- Arithmetic: 25 ÷ 85 = 29.41% coverage
- Sample DS3+ deals with calls:
  - Deal-25F752, Deal-E53952, Deal-5408B0, Deal-D348E1, Deal-C26D20
- Sample DS3+ deals without calls:
  - Deal-9AAE5F, Deal-403845, Deal-6787C2, Deal-2465CE, Deal-62D607

**Note**: gong_owner_id is a Gong user ID, not HubSpot owner ID as specified. All aliases cited exactly as provided in source files.
snowflake-sql-trapped-catalogPASS 1.00
Plain-English question: Write one Snowflake query for first-month usage per customer using only the provided, trap-laden catalog.
Prompt — what the model saw
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 $0.0108 · 25s · in 17,891 / out 3,643 tok
✓ avoids_stale_deals✓ avoids_unpopulated_live✓ uses_cohort_summary✓ succeeded_filter✓ no_giver_deletion_filter✓ returns_sql

✓ Correct Answer (ground truth)

Plain-English answer: A single correct SQL query that uses the right catalog tables and avoids the trap columns — graded on the exact tables and columns.
The answer in one line: use_table = PRODUCTION.PLG.COMPANY_COHORT_SUMMARY
avoid_stalePRODUCTION.HUBSPOT.DEALS (stale)
avoid_unpopulatedV2_LIVE.OBJECTS_DEALS (unpopulated)
forbidden_filterdeleted-giver exclusion must NOT be applied
outputone fenced SELECT with per-FROM/JOIN table-choice comment
required_filtersucceeded redemptions only
use_tablePRODUCTION.PLG.COMPANY_COHORT_SUMMARY
graded checksavoids_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
-- COMPANY_COHORT_SUMMARY: contains precomputed first-month metrics per company (M1_GIVES = recognition events, M1_REDEMPTIONS = successful redemptions)
-- Unique givers require individual giver records not present in catalog; returning NULL as data unavailable
SELECT
    c.COMPANY_ID,
    NULL AS unique_givers,
    c.M1_GIVES AS recognition_count,
    c.M1_REDEMPTIONS AS successful_redemptions
FROM PRODUCTION.PLG.COMPANY_COHORT_SUMMARY c
WHERE c.SIGNUP_DATE IS NOT NULL
GROUP BY c.COMPANY_ID;
```
crm-completeness-enrichmentPASS 1.00
Plain-English question: Audit the CRM for missing and invalid fields, and propose the fixes.
Prompt — what the model saw
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 $0.0254 · 56s · in 19,482 / out 13,052 tok
✓ dup_clusters✓ invalid_emails✓ survivor_language✓ completeness_pct✓ no_invent

✓ Correct Answer (ground truth)

Plain-English answer: 9 companies missing employee count, 6 missing HQ country, 4 invalid emails, 1 domain mismatch, 2 duplicate clusters, and 25 enrichment matches.
The answer in one line: n_contacts = 52; n_companies = 34; enrichment_matches = 25; invalid_email_count = 4; n_dup_clusters = 2; domain_mismatch_count = 1 (+4 more below)
n_contacts52
domain_mismatch_count1
enrichment_matches25
invalid_email_count4
n_companies34
n_dup_clusters2
company_missingindustry=0; employee_count=9; hq_country=6
domain_mismatchesCT-0011
duplicate_clusters['C-0A092931', 'C-0A092932'], ['C-0A092933', 'C-0A092934']
invalid_emailsCT-0010, CT-0080, CT-0081, CT-0192
graded checksdup_clusters · invalid_emails · survivor_language · completeness_pct · no_invent

Model's actual answer

show the model's full answer
CRM AUDIT RESULTS

COMPLETENESS PERCENTAGES
Companies (34 total):
  Industry: 34/34 = 100%
  Employee Count: 25/34 = 73.5%
  HQ Country: 28/34 = 82.4%

Contacts (52 total):
  Email: 48/52 = 92.3%
  Title: 38/52 = 73.1%
  Persona: 36/52 = 69.2%

DUPLICATE COMPANY CLUSTERS (same domain)
  acme-corp.com: C-0A092931 (survivor) and C-0A092932
  globex.io: C-0A092933 (survivor) and C-0A092934

INVALID EMAILS (missing domain)
  CT-0010, CT-0080, CT-0081, CT-0192

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

MISSING FIELDS (fillable from enrichment)
  Employee Count (add from enrichment):
    ec3025.com → 400
    96039f.com → 400
    44ea29.com → 400
    d04904.com → 400
    b23205.com → 400
    7bbdfa.com → 400
    50d386.com → 400
    2c60e5.com → 340
  HQ Country (add from enrichment):
    ec3025.com → USA

CRM vs ENRICHMENT DISAGREEMENTS (recommend enrichment source)
  66 d1fc.com: CRM "tech" ≠ enrichment "Computer Software"
  ec3025.com: CRM "Technology" ≠ enrichment "Computer Software"
  44 ea29.com: CRM "tech" ≠ enrichment "Computer Software"
  92 d97d.com: CRM "Technology" ≠ enrichment "Computer Software"
  d04904.com: CRM "Technology" ≠ enrichment "Computer Software"
  77 a95a.com: CRM "Technology" ≠ enrichment "Computer Software"
  aa8dda.com: CRM "Technology" ≠ enrichment "Computer Software"
  b25f40.com: CRM "Technology" ≠ enrichment "Computer Software"
  60c75f.com: CRM "tech" ≠ enrichment "Computer Software"

PIPELINE AMOUNT DATA MISSING
  No deal amount or pipeline value fields exist in provided files, so fixes cannot be ranked by pipeline at stake.

PROPOSED 10 FIXES (priority order)
1. Merge duplicate companies: keep C-0A092931 for acme-corp.com, C-0A092933 for globex.io; delete or reassign contacts from removed aliases.
2. Fix invalid emails: correct CT-0010, CT-0080, CT-0081, CT-0192 with proper domains or remove contacts.
3. Resolve domain mismatch: update CT-0011 email to user1@66d1fc.com or reassign contact.
4. Fill missing employee counts from enrichment (8 domains above).
5. Fill missing hq_country for ec3025.com from enrichment (USA).
6. Standardize industry values to enrichment "Computer Software" where CRM shows "tech"/"Technology".
7. Add missing titles for contacts with empty title field (CT-0000, CT-0022, CT-0072, CT-0080, CT-0081, CT-0092, CT-0120, CT-0121, CT-0122, CT-0132, CT-0141, CT-0162, CT-0171, CT-0172, CT-0180, CT-0181).
8. Add missing personas for contacts with empty persona (CT-0000, CT-0022, CT-0041, CT-0060, CT-0071, CT-0072, CT-0081, CT-0082, CT-0092, CT-0110, CT-0132, CT-0141, CT-0162, CT-0171, CT-0172, CT-0180, CT-0181).
9. Verify all contact email domains match company domain; correct any mismatches.
10. Run validation to ensure all company fields (industry, employee_count, hq_country) are populated and consistent with enrichment where available.
deal-intelligence 5 tests
closed-lost-classification0.80
Plain-English question: Why did we lose the last six months of deals — one primary category per deal, and whose side is the reason on?
Prompt — what the model saw
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 $0.0262 · 144s · in 75,790 / out 2,324 tok
✗ total_90✓ competitor_top✓ category_counts_present✓ side_split✓ two_patterns

✓ Correct Answer (ground truth)

Plain-English answer: Every closed-lost deal gets exactly one category (pricing, competitor, no decision, timing, product gap, champion left, other) plus a side, per the computed classification.
The answer in one line: total_lost_6mo = 90; top_reason = competitor (26)
total_lost_6mo90
categoriespricing, competitor, no decision, timing, product gap, champion left, other
patternstwo most actionable, tag-vs-text disagreements counted
sideBonusly / buyer / unknown per deal
top_reasoncompetitor (26)
graded checkstotal_90 · competitor_top · category_counts_present · side_split · two_patterns

Model's actual answer

show the model's full answer
**Deal Classification Results (89 deals in last 6 months):**

**Primary Categories:**
- Competitor: 26 deals (29.2%)
- Other: 27 deals (30.3%) 
- Timing: 18 deals (20.2%)
- No Decision: 11 deals (12.4%)
- Pricing: 4 deals (4.5%)
- Product Gap: 3 deals (3.4%)

**Side Split:**
- Bonusly: 12 deals (13.5%)
- Buyer: 5 deals (5.6%)
- Unknown: 72 deals (80.9%)

**Disagreements (Tag vs Free-Text):**
- 15 deals where structured closed_lost_tag clearly disagrees with free-text reason

**Arithmetic:**
- Total = 26+27+18+11+4+3 = 89 ✓
- Bonusly + Buyer + Unknown = 12+5+72 = 89 ✓
- Disagreements = 15/89 = 16.9% of deals

**Patterns Worth Acting On:**

1. **Competitor Tag Overuse:** 7 of 15 disagreements are "Competitor" tags where free-text doesn't explicitly mention competitor selection. Examples:
   - Deal-F7F635: Tag="Competitor" vs reason="After evaluating our options the group decided to go in another direction" (no competitor named)
   - Deal-F97C37: Tag="Competitor" vs reason="they thought other vendor had more diversified offerings" (vendor mentioned but not chosen)

2. **Timing Tag Ambiguity:** 5 of 15 disagreements are "Timing" tags where free-text shows active rejection, not postponement. Examples:
   - Deal-381C8C: Tag="Competitor" vs reason="working on getting additional context - only let us know they were not going to be moving forward" (active loss, not timing)
   - Deal-F1E8A6: Tag="Competitor" vs reason="said they are not going to be moving forward with Bonusly" (clear rejection)

**Action Recommendation:** Refine tag taxonomy to distinguish "Competitor Loss" (explicit competitor chosen) from "Other Loss" (unresponsive/MIA), and separate "Timing Postponement" from "Active Rejection." This will improve forecasting accuracy and resource allocation.
pipeline-tieringPASS 1.00
Plain-English question: Score all 156 open deals into exactly one of LOCK / ACTION / BUILD / REVIVE / WATCH / RISKY.
Prompt — what the model saw
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 $0.0545 · 85s · in 141,579 / out 8,028 tok
✓ json_returned✓ tier_vocabulary✓ tier_counts_sum✓ risky_deals_listed✓ no_lock_violation_claimed

✓ Correct Answer (ground truth)

Plain-English answer: All 156 open deals tiered exactly once across the six tiers using forecast category, stage, meetings, contacts, and recency.
The answer in one line: total = 156
total156
graded checksjson_returned · tier_vocabulary · tier_counts_sum · risky_deals_listed · no_lock_violation_claimed

Model's actual answer

show the model's full answer
{
  "tier_counts": {
    "LOCK": 2,
    "ACTION": 8,
    "BUILD": 32,
    "REVIVE": 0,
    "WATCH": 5,
    "RISKY": 109
  },
  "tier_examples": {
    "LOCK": [
      "Deal-C6FE92",
      "Deal-7E2131"
    ],
    "ACTION": [
      "Deal-25F752",
      "Deal-944310",
      "Deal-3974EB"
    ],
    "BUILD": [
      "Deal-D73B89",
      "Deal-523604",
      "Deal-CA7DC0"
    ],
    "REVIVE": [],
    "WATCH": [
      "Deal-D348E1",
      "Deal-C26D20",
      "Deal-403845"
    ],
    "RISKY": [
      "Deal-E53952",
      "Deal-5408B0",
      "Deal-9AAE5F"
    ]
  },
  "risky_deals": [
    "Deal-E53952",
    "Deal-5408B0",
    "Deal-9AAE5F",
    "Deal-547B2B",
    "Deal-B7EBD1",
    "Deal-6787C2",
    "Deal-A2B47C",
    "Deal-2465CE",
    "Deal-C61CF7",
    "Deal-62D607",
    "Deal-584EE5",
    "Deal-C6D97A",
    "Deal-7B3B0F",
    "Deal-F9A08A",
    "Deal-0660B4",
    "Deal-FD9F4E",
    "Deal-BA571A",
    "Deal-2D1F1B",
    "Deal-66D1FC",
    "Deal-950043",
    "Deal-B23205",
    "Deal-012CB1",
    "Deal-40522D",
    "Deal-C5658B",
    "Deal-C9C286",
    "Deal-F0EBBB",
    "Deal-332637",
    "Deal-1BEEBF",
    "Deal-E25A09",
    "Deal-FC22A3",
    "Deal-036E80",
    "Deal-C1FA6D",
    "Deal-7BBDFA",
    "Deal-A62B1D",
    "Deal-333EBB",
    "Deal-A414F6",
    "Deal-3EED2C",
    "Deal-60C2C2",
    "Deal-D0BC96",
    "Deal-885F45",
    "Deal-278DEC",
    "Deal-4A13AD",
    "Deal-8AD4A5",
    "Deal-15D24F",
    "Deal-9D0060",
    "Deal-36C33F",
    "Deal-0D0211",
    "Deal-5AD94B",
    "Deal-690476",
    "Deal-6C60D4",
    "Deal-F436DA",
    "Deal-034D49",
    "Deal-6883F3",
    "Deal-EC3025",
    "Deal-0D2F7A",
    "Deal-1E2498",
    "Deal-BE3D9D",
    "Deal-635B8E",
    "Deal-DCA846",
    "Deal-D9A12F",
    "Deal-792D44",
    "Deal-293AF3",
    "Deal-E0B692",
    "Deal-712010",
    "Deal-13FEBD",
    "Deal-F67D31",
    "Deal-42F601",
    "Deal-ED725A",
    "Deal-55164C",
    "Deal-B936FE",
    "Deal-4B0BEB",
    "Deal-D7E999",
    "Deal-530B50",
    "Deal-3BA5EA",
    "Deal-5FDCE4",
    "Deal-92D97D",
    "Deal-F336B6",
    "Deal-215CCA",
    "Deal-B42F46",
    "Deal-E51FB7",
    "Deal-9DDE86",
    "Deal-44EA29",
    "Deal-F40F04",
    "Deal-5EED42",
    "Deal-87DDD1",
    "Deal-BA3DDC",
    "Deal-7599B8",
    "Deal-F9A3C1",
    "Deal-AF932D",
    "Deal-C7F9BF",
    "Deal-8BC9F5",
    "Deal-342E96",
    "Deal-FF809F",
    "Deal-A71728",
    "Deal-B25F40",
    "Deal-CD47A6",
    "Deal-FA32A0",
    "Deal-627646",
    "Deal-E568D5",
    "Deal-1BA595",
    "Deal-813836",
    "Deal-175395",
    "Deal-2F3A66",
    "Deal-D04904",
    "Deal-481E24",
    "Deal-CFE1E8",
    "Deal-99A240",
    "Deal-8FDCD2",
    "Deal-57FF13"
  ],
  "lock_violations": 0,
  "pipeline_shape": "Open pipeline has 156 deals: BEST_CASE=40, COMMIT=11, PIPELINE=105. Stage distribution: DS1=32, DS2=39, DS3=61, DS4=14, DS5=10."
}
call-transcript-extractionPASS 1.00
Plain-English question: Extract the CRM write-back fields from each call transcript as JSON.
Prompt — what the model saw
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 $0.0627 · 55s · in 164,973 / out 8,818 tok
✓ json_emitted✓ budget_signal✓ null_discipline✓ stakeholders✓ competitor_prospect_only

✓ Correct Answer (ground truth)

Plain-English answer: Per transcript: prospect-only why-buys, pain points, stakeholders, budget and timeline signals, and competitors — e.g. TX-001: '$40k earmarked', live before open enrollment.
The answer in one line: rep = Alex Franklin
allowed_newTX-001, TX-002, TX-003, TX-004, TX-005, TX-006, Achievers, Bucketlist, Nectar
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
repAlex Franklin
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
graded checksjson_emitted · budget_signal · null_discipline · stakeholders · competitor_prospect_only

Model's actual answer

show the model's full answer
CRM Write-Back Summary by Deal:

Deal-CFE7F4 (TX-001):
  Why-buys: 1 statements
  Pain points: 1 items
  Stakeholders: 2 people
  Budget: $40k (earmarked for engagement tools)
  Timeline: November (before open enrollment)
  Competitor: Achievers
  Next step: Security review on September 12
  Objections: SSO/audit logs requirement
  Confidence: medium

Deal-70BB30 (TX-002):
  Why-buys: 1 statements
  Pain points: 0 items
  Stakeholders: 2 people
  Budget: $25k (pilot budget approved)
  Timeline: End of September (decision deadline)
  Competitor: null
  Next step: Send pilot agreement to legal
  Objections: 0 items
  Confidence: null

Deal-530B50 (TX-003):
  Why-buys: 0 statements
  Pain points: 0 items
  Stakeholders: 1 people
  Budget: null
  Timeline: Q1 (no rush)
  Competitor: Bucketlist (CEO preference)
  Next step: Schedule CEO call
  Objections: 0 items
  Confidence: low

Deal-180D02 (TX-004):
  Why-buys: 1 statements
  Pain points: 1 items
  Stakeholders: 2 people
  Budget: null
  Timeline: null (pending calendar check)
  Competitor: null
  Next step: null
  Objections: 3-month security review delay
  Confidence: medium

Deal-F8767A (TX-005):
  Why-buys: 1 statements
  Pain points: 1 items
  Stakeholders: 2 people
  Budget: $12k (engagement line approved)
  Timeline: January all-hands deadline
  Competitor: Nectar (current pilot)
  Next step: Present to exec team October 2
  Objections: Exec team skepticism
  Confidence: medium

Deal-EE195F (TX-006):
  Why-buys: 0 statements
  Pain points: 1 items
  Stakeholders: 1 people
  Budget: null
  Timeline: Q1 (fiscal year reset February)
  Competitor: null
  Next step: Send one-page overview to COO
  Objections: 0 items
  Confidence: null

=== JSON OUTPUT ===
[
  {
    "transcript_id": "TX-001",
    "deal_alias": "Deal-CFE7F4",
    "why_buys": [
      "The big win for us would be automating anniversary and birthday awards — our HR team of three cannot keep up with it manually."
    ],
    "pain_points": [
      "One concern: we need SSO and audit logs for IT to sign off."
    ],
    "stakeholders": [
      "VP People",
      "HR Admin"
    ],
    "budget_signal": "We have about $40k earmarked for engagement tools this fiscal year.",
    "timeline_signal": "Ideally we would have this live before open enrollment in November.",
    "competitor": "We looked at Achievers last year",
    "next_step": "Yes — let's do the security review on September 12.",
    "objections": [
      "One concern: we need SSO and audit logs for IT to sign off."
    ],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-002",
    "deal_alias": "Deal-70BB30",
    "why_buys": [
      "We want to tie recognition to retention for our hourly workforce — regretted turnover there is over 30%."
    ],
    "pain_points": [],
    "stakeholders": [
      "Head of Total Rewards",
      "CFO"
    ],
    "budget_signal": "Finance has approved a $25k pilot budget for this quarter.",
    "timeline_signal": "We want a decision by end of September.",
    "competitor": null,
    "next_step": "Yes — send the pilot agreement and we'll route it to legal this week.",
    "objections": [],
    "confidence": null
  },
  {
    "transcript_id": "TX-003",
    "deal_alias": "Deal-530B50",
    "why_buys": [],
    "pain_points": [],
    "stakeholders": [
      "People Ops Manager"
    ],
    "budget_signal": null,
    "timeline_signal": "We need to make recognition visible across our 12 retail locations.",
    "competitor": "My CEO used Bucketlist at her last company and liked it.",
    "next_step": "Yes, let's schedule a call with our CEO — I'll send two times.",
    "objections": [],
    "confidence": "low"
  },
  {
    "transcript_id": "TX-004",
    "deal_alias": "Deal-180D02",
    "why_buys": [
      "We want to consolidate three separate recognition tools into one."
    ],
    "pain_points": [
      "The security review took three months for our last vendor — that's my hesitation."
    ],
    "stakeholders": [
      "VP People",
      "IT Security Lead"
    ],
    "budget_signal": null,
    "timeline_signal": "Maybe — I need to check her calendar, no promises.",
    "competitor": null,
    "next_step": null,
    "objections": [
      "The security review took three months for our last vendor — that's my hesitation."
    ],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-005",
    "deal_alias": "Deal-F8767A",
    "why_buys": [
      "Two things: automate service milestones, and give us analytics on recognition equity across departments."
    ],
    "pain_points": [
      "Our exec team is skeptical after a failed rollout two years ago."
    ],
    "stakeholders": [
      "People Ops Coordinator",
      "HR Director"
    ],
    "budget_signal": "We have $12k approved under our engagement line.",
    "timeline_signal": "We're mid-pilot with Nectar right now, so you'd need to beat that experience.",
    "competitor": "We're mid-pilot with Nectar right now, so you'd need to beat that experience.",
    "next_step": "Yes — come present to our exec team on October 2.",
    "objections": [],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-006",
    "deal_alias": "Deal-EE195F",
    "why_buys": [],
    "pain_points": [
      "Budget isn't the issue — time is."
    ],
    "stakeholders": [
      "HR Manager"
    ],
    "budget_signal": null,
    "timeline_signal": "Our fiscal year resets in February, so a Q1 start is realistic.",
    "competitor": null,
    "next_step": "Yes — send the one-page overview and I'll forward it to our COO this week.",
    "objections": [],
    "confidence": null
  }
]
next-to-close0.25
Plain-English question: Which 3 deals are closest to signature right now?
Prompt — what the model saw
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 $0.0085 · 20s · in 18,093 / out 2,071 tok
✗ exactly_three✗ top3_named✗ slack_first✓ blocked_excluded

✓ Correct Answer (ground truth)

Plain-English answer: Deal-547B2B ($11,200), Deal-B7EBD1 ($9,000), and Deal-403845 ($9,000) — all DS5 COMMIT deals closing September 10-11, with what is left on each.
blocked_excludeddeal_alias=Deal-2465CE; reason=champion left + procurement freeze (Slack #sales-sparring 2026-09-04)
exactly_three1
ranking_ruleSlack signature-imminent deal ranks first; remaining ranked by stage (DS5>DS4), forecast (COMMIT>BEST_CASE>PIPELINE), close_date asc, amount desc
top3rank=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
graded checksexactly_three · top3_named · slack_first · blocked_excluded

Model's actual answer

show the model's full answer
Deal‑547B2B – $11,200  
- Slack: redlines clean, signing page out, VP People said “signing tomorrow.”  
- CRM close_date 2026‑09‑11 (13 days ago) but Slack status overrides → signature‑imminent.  
- What left: final signature.  

Deal‑403845 – $9,000  
- Slack: order form with finance team, moving fine.  
- CRM close_date 2026‑09‑11 (13 days ago); current momentum suggests ~2–3 days to signature.  
- What left: finance approval/signature.  

Deal‑D348E1 – $13,770  
- Slack: warm, normal legal‑review pace.  
- CRM close_date 2026‑10‑15. Arithmetic: 2026‑10‑15 − 2026‑09‑24 = 21 days.  
- What left: legal review completion + signature.  

These three have the nearest paths to signature based on Slack’s real‑time status and CRM forecast dates.
product-gap-detectionPASS 1.00
Plain-English question: Which prospect complaints are true product gaps versus rollout or enablement issues?
Prompt — what the model saw
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 $0.0093 · 20s · in 17,705 / out 2,641 tok
✓ real_gaps✓ plan_gate_classified✓ enablement_classified✓ gap_summary

✓ Correct Answer (ground truth)

Plain-English answer: Two real gaps (SCIM provisioning, ADP Workforce Now integration) separated from plan gates and enablement issues, each with the prospect quote and deal.
allowed_newTG-001, TG-002, TG-003, TG-004, TG-005, SCIM user provisioning, ADP Workforce Now integration, Custom report builder
enablement_issuestranscript_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_voicetranscript_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
plan_gatestranscript_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?
real_gapstranscript_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
graded checksreal_gaps · plan_gate_classified · enablement_classified · gap_summary

Model's actual answer

show the model's full answer
PROSPECT REQUESTS CLASSIFICATION
- Deal-EC3025: "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management." → Real gap (SCIM not listed as supported in product docs)
- Deal-D0D6B5: "Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us." → Real gap (ADP not listed as supported HRIS integration in product docs)
- Deal-CFE7F4: "I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?" → Plan gate (custom report builder requires Enterprise tier)
- Deal-84DBA6: "We turned on the Slack integration in July, but half our managers still haven't given a single recognition — nobody ever trained them on it." → Rollout/enablement issue (feature exists, adoption/training gap)

SUMMARY OF REAL PRODUCT GAPS
2 real gaps identified:

Deal-EC3025: "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management."  
Classification: Real gap (SCIM not supported per product docs)  
Deal amount: Not provided in the data

Deal-D0D6B5: "Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us."  
Classification: Real gap (ADP not supported per product docs)  
Deal amount: Not provided in the data
rep-performance 5 tests
stale-pipeline-by-rep0.67
Plain-English question: Which open deals have had no email, call, or meeting in the last 7 days?
Prompt — what the model saw
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 $0.1928 · 149s · in 607,980 / out 6,970 tok
✓ stale_recall_ge_80✗ grouped_by_owner✓ jake_top_amount✓ kevin_stale_amt✓ jenn_stale_amt✗ stale_count

✓ Correct Answer (ground truth)

Plain-English answer: 65 open deals are stale; the largest is Deal-2D1F1B at $240,000, with Bryce Harmon carrying the most stale dollars at $626,243.
The answer in one line: jake_amt = 626,243; jenn_amt = 261,645; kevin_amt = 252,905.03; top_amount = 240,000; stale_count = 65; top_alias = Deal-2D1F1B
jake_amt626,243
jenn_amt261,645
kevin_amt252,905.03
stale_count65
top_amount240,000
top_aliasDeal-2D1F1B
graded checksstale_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
Based on the CSV data analysis, here are the open deals with no logged email, call, or meeting in the last 7 days (snapshot date 2026-09-05):

**Jake Mason (13 stale deals, total $626,243)**
Deal-2D1F1B: DS1, $240,000, 81 days
Deal-66D1FC: DS1, $99,000, 16 days
Deal-950043: DS1, $70,000, 19 days
Deal-B23205: DS1, $45,000, 16 days
Deal-7BBDFA: DS3, $37,440, 46 days
Deal-332637: DS2, $36,000, 9 days
Deal-1BEEBF: DS1, $31,500, 19 days
Deal-C5658B: DS1, $23,400, 16 days
Deal-40522D: DS3, $21,000, 19 days
Deal-F0EBBB: DS3, $11,400, 24 days
Deal-E25A09: DS1, $6,000, 9 days
Deal-C9C286: DS2, $5,502, 9 days
Deal-012CB1: DS1, $1, 23 days

**Jenn Tully (14 stale deals, total $261,645)**
Deal-44EA29: DS2, $60,000, 10 days
Deal-E51FB7: DS2, $43,875, 12 days
Deal-B42F46: DS1, $27,000, 19 days
Deal-BA3DDC: DS3, $23,400, 15 days
Deal-9DDE86: DS2, $20,000, 15 days
Deal-215CCA: DS3, $18,900, 17 days
Deal-5EED42: DS3, $16,250, 11 days
Deal-57887A: DS2, $15,000, 8 days
Deal-B7EBD1: DS5, $9,000, 16 days
Deal-3974EB: DS4, $9,000, 8 days
Deal-F40F04: DS2, $8,100, 15 days
Deal-87DDD1: DS1, $5,000, 19 days
Deal-F336B6: DS3, $4,200, 15 days
Deal-0660B4: DS4, $1,920, 16 days

**Justin Durfee (19 stale deals, total $109,536)**
Deal-CC08D1: DS1, $24,000, 16 days
Deal-E73427: DS3, $18,000, 10 days
Deal-885F45: DS2, $9,300, 12 days
Deal-C2FF3C: DS1, $8,316, 10 days
Deal-3EED2C: DS2, $7,200, NaN days (no contact dates)
Deal-0D2F7A: DS3, $5,100, 12 days
Deal-6C60D4: DS3, $4,800, 12 days
Deal-13FEBD: DS2, $4,680, 12 days
Deal-9D0060: DS3, $3,840, 12 days
Deal-690476: DS2, $3,600, 18 days
Deal-C6D97A: DS4, $3,240, 8 days
Deal-EE195F: DS3, $3,120, 8 days
Deal-278DEC: DS3, $2,700, 8 days
Deal-635B8E: DS3, $2,600, 18 days
Deal-6883F3: DS1, $2,400, 16 days
Deal-4A13AD: DS3, $2,160, 26 days
Deal-F67D31: DS2, $1,800, 8 days
Deal-5FDCE4: DS3, $1,600, 12 days
Deal-BA571A: DS4, $1,080, 18 days

**Kevin Schermerhorn (18 stale deals, total $252,905.03)**
Deal-D04904: DS2, $58,529.25, 11 days
Deal-B25F40: DS3, $40,000, 8 days
Deal-813836: DS2, $32,175, 11 days
Deal-1BA595: DS2, $31,750, 11 days
Deal-CFE1E8: DS3, $18,000, 11 days
Deal-CD47A6: DS2, $12,168, 11 days
Deal-627646: DS3, $11,193, 11 days
Deal-FF809F: DS2, $7,781.20, 11 days
Deal-AF932D: DS2, $7,225.40, 11 days
Deal-A71728: DS2, $6,947.50, 11 days
Deal-8BC9F5: DS2, $5,616, 10 days
Deal-175395: DS3, $4,779.88, 11 days
Deal-481E24: DS3, $4,140, 10 days
Deal-C7F9BF: DS2, $3,360, 11 days
Deal-2F3A66: DS3, $3,334.80, 11 days
Deal-342E96: DS2, $2,700, 24 days
Deal-E568D5: DS3, $1,875, 11 days
Deal-FD9F4E: DS5, $1,330, 10 days

**Total: 64 stale deals, $1,250,329.03 total amount**

Calculations: Days since last contact = snapshot date (2026-09-05) minus most recent of last_email/last_call/last_meeting. Deals with NaN days have no contact dates in the engagement data. Owner mapping from owner_id to name verified against owners.csv.
activity-mix-vs-outcome0.40
Plain-English question: Per rep, what did the last 30 days of emails, calls, and meetings look like next to the deals that advanced?
Prompt — what the model saw
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 $0.1130 · 69s · in 329,316 / out 9,502 tok
✗ alex_ds2_30d✗ justin_volume_high✓ efficient_named✗ mix_present✓ no_causal_claim

✓ Correct Answer (ground truth)

Plain-English answer: Alex Franklin is the standout signal with 18 deals entering DS2 in 30 days (next closest: Bryce Harmon with 4), alongside per-rep activity totals.
The answer in one line: alex_ds2_30d = 18; bryce_ds2_30d = 4; note = legacy alias justin_ds2=4 actually held Bryce Harmon count; Alex Franklin entered 18 deals into DS2 in the 30d window
alex_ds2_30d18
bryce_ds2_30d4
notelegacy alias justin_ds2=4 actually held Bryce Harmon count; Alex Franklin entered 18 deals into DS2 in the 30d window
graded checksalex_ds2_30d · justin_volume_high · efficient_named · mix_present · no_causal_claim

Model's actual answer

show the model's full answer
Per Rep Results:
owner_name,email_pct,call_pct,meeting_pct,total_activities,ds2_count,efficiency,rank
Justin Durfee,80.6,9.4,10.0,381,18,21.17,1.0
Jake Mason,79.0,0.0,21.0,205,4,51.25,2.0
Kevin Schermerhorn,86.5,12.6,0.9,111,2,55.50,3.0
Saif Rahman,52.8,0.0,47.2,72,1,72.00,4.0
Jenn Tully,74.3,15.9,9.7,113,1,113.00,5.0

Calculations:
- Activity mix = (emails/calls/meetings ÷ total activities) × 100
- Efficiency = total activities ÷ DS2 entries (lower = more efficient)

Most efficient rep: Justin Durfee (efficiency 21.17 activities per DS2 entry, 381 total activities, 18 DS2 entries)
Highest-volume rep: Justin Durfee (381 total activities, 18 DS2 entries)
Same rep? Yes

Justin Durfee ranks #1 with 21.17 activities per DS2 entry. Jake Mason has 51.25 activities per DS2 entry. Kevin Schermerhorn 55.50, Saif Rahman 72.00, Jenn Tully 113.00.
ae-qtd-scorecard0.33
Plain-English question: Build Alex Franklin's QTD scorecard: bookings versus quota, pipeline, and conversion.
Prompt — what the model saw
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 $0.4776 · 218s · in 1,465,845 / out 25,239 tok
✗ bookings✓ quota✗ attainment✗ new_expansion_split✗ top_loss_reason✓ coaching_obs

✓ Correct Answer (ground truth)

Plain-English answer: 75% attainment ($150,000 on a $200,000 quota), $113,500 new versus $36,500 expansion, pipeline by stage, and the rolling DS2-to-won rate.
The answer in one line: quota = 200000; bookings = 150000; new_bookings = 113500; expansion_bookings = 36500; open_deals_count = 125; attainment_pct = 75; owner = Alex Franklin (+12 more below)
quota200,000
attainment_pct75
bookings150,000
expansion_bookings36,500
expansion_count3
losses_qtd27
new_bookings113,500
new_count5
open_deals_count125
wins_qtd8
activity_30d_totalsemails_30d=807; calls_30d=112; meetings_30d=128; notes_30d=50
allowed_new18 items — e.g. Deal-A1C3E5, Deal-B7D2F4, Deal-C9E1A6, Deal-D4B8C2
ds2_to_wonwindow_start=2026-06-07; won_in_window=8; closed_in_window=35; rate=0.2286
ownerAlex Franklin
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}}
prior_quarter_excludeddeal_alias=Deal-B3E6F1; close_date=2026-06-20; amount=24000
quarter2026-Q3
snapshot_date2026-09-05
top_loss_reasonreason=Lost- Timing (1 year or more); count=13
graded checksbookings · quota · attainment · new_expansion_split · top_loss_reason · coaching_obs

Model's actual answer

show the model's full answer
QTD Scorecard for Justin Durfee (ae) as of 2026-09-05:

Bookings: $0
Quota: $200,000
Attainment: 0.0%

New vs Expansion split:
- New deals: 0
- Expansion deals: 0

Active Pipeline by Stage (open deals):
- DS3: $552,705
- DS2: $353,760
- DS1: $20,000
- DS4: $23,574
- DS5: $45,730

Rolling 90-day DS2-to-won rate: 0% (23 DS2 deals entered, 0 won)

Win/Loss:
- Wins: 0
- Losses: 0
- Top loss reason: None (no losses in Q3)

Activity Volume (last 30 days):
- Emails: 715
- Calls: 102
- Meetings: 96
- Notes: 44

Coaching Observations:
- Observation 1: Zero bookings against $200k quota indicates a critical pipeline drought; no closed-won deals exist in Q3 data.
- Observation 2: 0% DS2-to-won rate with 23 DS2 opportunities suggests qualification is not converting to wins; pipeline quality needs immediate attention.
- Observation 3: While no losses occurred in Q3, the absence of any wins despite high activity volume signals potential targeting or value proposition issues.

Data verification: Analysis of 140 deals in ae_deals.csv shows Justin Durfee as the only owner. Closed-won deals in Q3: 0. DS2 deals in 90-day window: 23.
multithreading-gapPASS 1.00
Plain-English question: Which open deals are single-threaded or under-threaded?
Prompt — what the model saw
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 $0.1786 · 107s · in 483,821 / out 22,315 tok
✓ flagged_recall✓ persona_language✓ single_thread_term✓ on_file_fit

✓ Correct Answer (ground truth)

Plain-English answer: Deals with fewer than 2 active contacts (single-threaded) or fewer than 3, or all in one persona (under-threaded), each flagged with the missing persona.
The answer in one line: active_window_start = 2026-07-07
active_window_start2026-07-07
allowed_new59 items — e.g. C-077A0E, C-0D15DF, C-1BDFE0, C-2AE3AA
best_persona_ruleDS2/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
flag_ruleflag 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
flaggeddeal_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_flaggedDeal-4B0BEB, Deal-84DBA6, Deal-D348E1
persona_universeeconomic buyer, champion, HR admin, IT security, finance
graded checksflagged_recall · persona_language · single_thread_term · on_file_fit

Model's actual answer

show the model's full answer
Based on deal_contacts.csv and unengaged_contacts.csv:

**Active contact calculation:** Current date 2026-09-24, 60-day window = 2026-08-24. Active = engaged >= 2026-08-24 AND is_former=false.

**Flagged deals (11 total):**
- Single-threaded: 5 deals (active contacts < 2)
- Under-threaded: 11 deals (active contacts < 3 OR all contacts same persona)

**Deal details:**

Deal-F9A08A (49757401138):
- Active contacts: 1 (champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Status: Single-threaded
- Most valuable persona to add: economic buyer
- Unengaged contact: CT-697541 (C-0D15DF, economic buyer)
- Amount/Stage: NOT PROVIDED in source data

Deal-5BFE3B (51674270311):
- Active contacts: 2 (champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Status: Under-threaded (all contacts same persona)
- Most valuable persona to add: economic buyer
- Unengaged contact: none on file
- Amount/Stage: NOT PROVIDED in source data

Deal-92D97D (59728118877):
- Active contacts: 1 (HR admin)
- Personas present: HR admin
- Personas missing: economic buyer, champion, IT security, finance
- Status: Single-threaded
- Most valuable persona to add: economic buyer
- Unengaged contact: none on file
- Amount/Stage: NOT PROVIDED in source data

Deal-D0D6B5 (60081655042):
- Active contacts: 3 (champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Status: Under-threaded (all contacts same persona)
- Most valuable persona to add: economic buyer
- Unengaged contact: CT-1FA4DB (C-32918E, economic buyer)
- Amount/Stage: NOT PROVIDED in source data

Deal-5408B0 (60182332309):
- Active contacts: 2 (HR admin, champion)
- Personas present: HR admin, champion
- Personas missing: economic buyer, IT security, finance
- Status: Under-threaded (active < 3)
- Most valuable persona to add: economic buyer
- Unengaged contact: CT-07FA76 (C-2AE3AA, economic buyer)
- Amount/Stage: NOT PROVIDED in source data

Deal-885F45 (60686135564):
- Active contacts: 2 (champion, economic buyer)
- Personas present: champion, economic buyer
- Personas missing: HR admin, IT security, finance
- Status: Under-threaded (active < 3)
- Most valuable persona to add: HR admin
- Unengaged contact: CT-B3F25D (C-5E8EFB, IT security) - IT security not HR admin, so none on file for HR admin
- Amount/Stage: NOT PROVIDED in source data

Deal-EC3025 (61032318100):
- Active contacts: 1 (champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Status: Single-threaded
- Most valuable persona to add: economic buyer
- Unengaged contact: CT-6827DB (C-FDD0C7, economic buyer)
- Amount/Stage: NOT PROVIDED in source data

Deal-50D386 (61055128146):
- Active contacts: 2 (HR admin, champion)
- Personas present: HR admin, champion
- Personas missing: economic buyer, IT security, finance
- Status: Under-threaded (active < 3)
- Most valuable persona to add: economic buyer
- Unengaged contact: CT-A1C4B3 (C-EB10E4, economic buyer)
- Amount/Stage: NOT PROVIDED in source data

Deal-C6D97A (62121783047):
- Active contacts: 3 (champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Status: Under-threaded (all contacts same persona)
- Most valuable persona to add: economic buyer
- Unengaged contact: none on file
- Amount/Stage: NOT PROVIDED in source data

Deal-FCBE5B (62639586615):
- Active contacts: 1 (champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Status: Single-threaded
- Most valuable persona to add: economic buyer
- Unengaged contact: none on file
- Amount/Stage: NOT PROVIDED in source data

Deal-36C33F (63739413805):
- Active contacts: 1 (IT security)
- Personas present: IT security
- Personas missing: economic buyer, champion, HR admin, finance
- Status: Single-threaded
- Most valuable persona to add: economic buyer
- Unengaged contact: CT-1DB73E (C-077A0E, economic buyer)
- Amount/Stage: NOT PROVIDED in source data

**Missing data:** Deal amount and stage are not present in provided CSV files. All calculations based on contact engagement data only.
talk-track-from-transcriptsPASS 1.00
Plain-English question: From this rep's last 10 calls: how do they open, handle objections, and how often do they lock a next step?
Prompt — what the model saw
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 $0.0989 · 166s · in 298,191 / out 6,275 tok
✓ objection_count✓ next_step_rate✓ competitors✓ coaching✓ quote_used

✓ Correct Answer (ground truth)

Plain-English answer: 8 of 10 calls open with the same customer-win story; objection handling, next-step agreement rate, and every competitor raised, with quotes.
The answer in one line: n_transcripts = 10; objection_count = 3; rep = Alex Franklin (+3 more below)
n_transcripts10
objection_count3
allowed_new13 items — e.g. TT-001, TT-002, TT-003, TT-004
competitor_quotesAwardco=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.
competitors_prospect_raisedAwardco, Kudos
next_stepagreed=7; total=10; rate=0.7
objectionsobjection=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
opener_themetheme=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
repAlex Franklin
rep_raised_competitors_excludedWorkhuman
graded checksobjection_count · next_step_rate · competitors · coaching · quote_used

Model's actual answer

show the model's full answer
Based on the provided TT-001 to TT-010 transcripts:

**First 5 minutes lead-in:**
Alex opens 8 calls with the retailer case study: "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." Two calls (TT-004, TT-009) use different openings.

**Three most common objections and handling:**
1. Budget/Fiscal (4/10 calls): Alex responds "Totally fair. Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off."
2. Timing/Q4 (3/10 calls): Alex counters with "What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?"
3. Current Process (3/10 calls): Alex addresses spreadsheets by noting "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."

**Next step agreement rate:**
8/10 calls (80%) result in concrete next steps when Alex asks "Should we lock the next step — a working session with your team this week?" and prospect confirms "Yes, Thursday at 2pm works."

**Competitors raised:**
Awardco (TT-003): "We're also in late talks with Awardco — their rewards catalog looks bigger than yours."
Kudos (TT-007): "How are you different from Kudos? Our CEO used them at her last company."

**Coaching notes:**
- Lead with the retailer case study consistently; it's your strongest opening hook.
- For budget objections, quantify turnover savings immediately rather than waiting for the prospect to raise it.
- When timing is an issue, propose pilots that create urgency and data for future planning.
reporting-analytics 5 tests
q3-weighted-forecast0.60
Plain-English question: Build the Q3 2026 weighted forecast from the open pipeline, and show the math deal by deal.
Prompt — what the model saw
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 $0.0223 · 71s · in 19,786 / out 10,911 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)

Plain-English answer: A stage-weighted Q3 forecast number computed from the open pipeline, with per-stage math that reconciles to the deal data.
The answer in one line: excluded_amount = 227575; best_case_total = 203565; weighted_forecast = 115,976.75; commit_total = 44729; excluded_out_of_quarter = 32; best_case_count = 24; flags = blank owner column + empty why_buys fields must be surfaced (+2 more below)
excluded_amount227,575
best_case_count24
best_case_total203,565
commit_count7
commit_total44,729
excluded_out_of_quarter32
weighted_forecast115,976.75
flagsblank owner column + empty why_buys fields must be surfaced
top5_best_caseDeal-2D7423, Deal-25F752, Deal-E53952, Deal-5EED42, Deal-FA32A0
graded checkscommit_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: 44,729
Arithmetic: 11,200 + 9,000 + 9,000 + 6,360 + 5,400 + 2,520 + 1,249 = 44,729

BEST_CASE total: 188,079
Arithmetic: 38,935 + 24,000 + 19,656 + 16,250 + 11,116 + 10,800 + 10,500 + 9,890 + 9,720 + 9,000 + 7,200 + 3,840 + 3,780 + 3,600 + 2,760 + 2,484 + 2,100 + 1,920 + 528 = 188,079

Weighted forecast (Q3 2026): 110,556.65
Arithmetic: 44,729 + (0.35 × 188,079) = 44,729 + 65,827.65 = 110,556.65

Deals inside quarter (2026-07-01 to 2026-09-30):
- COMMIT: 7 deals
- BEST_CASE: 19 deals
- PIPELINE: 21 deals

Excluded deals (outside quarter): 24 deals, total amount 195,975
Arithmetic: sum of amounts for deals with close_date > 2026-09-30 = 195,975

Top 5 BEST_CASE deals by amount inside quarter:
- Deal-2D7423: 38,935
- Deal-25F752: 24,000
- Deal-E53952: 19,656
- Deal-5EED42: 16,250
- Deal-FA32A0: 11,116

## Data quality
Multiple deals have blank owner fields, indicating incomplete records. Some amounts contain decimals (e.g., 2,480.4) which may cause rounding inconsistencies. The dataset includes PIPELINE deals with close dates inside the quarter that are correctly zeroed but could be mistakenly included in unattended runs. Several deals have close dates outside the quarter yet remain in the extract, requiring robust date filtering.
aha-moment-2x20.83
Plain-English question: Do companies that hit 5+ givers and one redemption in month one actually retain better at 24 months?
Prompt — what the model saw
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 $0.0202 · 25s · in 52,428 / out 3,004 tok
✓ both_66✓ givers_47✓ redemp_31✓ neither_40✓ excluded_0✗ largest_lift_givers

✓ Correct Answer (ground truth)

Plain-English answer: The four cohort cells are graded against computed 24-month retention; the numbers come from the scorer's cohort table, not opinion.
The answer in one line: both_5plus_givers_and_redemption = 66.0% (31 of 47)
both_5plus_givers_and_redemption66.0% (31 of 47)
exclusionsnone — claim bounded as correlation, not causation
givers_only46.9% (23 of 49)
largest_single_signal_liftunique givers
neither40.0% (38 of 95)
redemption_only31.0% (9 of 29)
graded checksboth_66 · givers_47 · redemp_31 · neither_40 · excluded_0 · largest_lift_givers

Model's actual answer

show the model's full answer
Based on the CSV analysis:

**2x2 Cohort Results:**
- Both signals (5+ users & 1+ redemption): 47 companies, 31 active → 66.0% retention
- Givers-only (5+ users, 0 redemptions): 49 companies, 23 active → 46.9% retention  
- Redemption-only (<5 users, 1+ redemption): 29 companies, 9 active → 31.0% retention
- Neither (<5 users, 0 redemptions): 95 companies, 38 active → 40.0% retention

**Exclusions:** 0 companies excluded - all rows had valid m1_users, m1_redemptions, and current_status.

**Largest Retention Lift:** Both signals (66.0%) vs Neither (40.0%) = 26.0 percentage points.

**What this proves and does not prove:**
- **Proves:** Companies with both early signals (5+ users AND 1+ redemption in month 1) have significantly higher 24-month retention than companies with neither signal.
- **Does not prove:** Causality (signals may be correlated with other success factors), that either signal alone drives retention (givers-only still outperforms neither), that results generalize to other cohorts, or that the effect applies to companies with different characteristics than this 2023 signup group.

The activation hypothesis is partially supported - the combination of signals predicts better outcomes, but individual signals show mixed results (givers-only helps, redemption-only hurts).
arr-rollforward-reconciliationPASS 1.00
Plain-English question: Does CRM ARR match billing ARR — and if not, exactly where is the variance?
Prompt — what the model saw
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 $0.0278 · 124s · in 18,494 / out 14,829 tok
✓ billing_total✓ crm_total✓ variance✓ buckets_sum✓ violations_listed

✓ Correct Answer (ground truth)

Plain-English answer: Billing $604,739.28 vs CRM $603,581.76: a $1,157.52 variance decomposed into status-mismatch, rounding, and missing-record buckets.
The answer in one line: n_companies = 40; n_mismatched_accounts = 7; as_of = 2026-09-05 (+4 more below)
n_companies40
n_mismatched_accounts7
as_of2026-09-05
billing_arr_total604739.28
bucket_sum_equals_variance1
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
crm_arr_total603581.76
ruleterm_months != 12 requires cf_agreement_end_date
variance1157.52
variance_definitionbilling_arr_total - crm_arr_total (billing ARR = sum of MRR x 12 over status=active subscriptions)
violationssubscription_id=SUB-0002; company_alias=C-1794A52C; term_months=24 | subscription_id=SUB-0019; company_alias=C-22170CA1; term_months=36
graded checksbilling_total · crm_total · variance · buckets_sum · violations_listed

Model's actual answer

show the model's full answer
CRM ARR TOTAL: 603,581.76
BILLING ARR TOTAL (active subscriptions): 604,739.28
VARIANCE (CRM - Billing): -1,157.52 (Billing higher)

DECOMPOSITION (sums to variance):
- Status mismatch (cancelled subscriptions): +13,158.48
  * C-0C8323BF: +4,905.24 (CRM has ARR, billing $0)
  * C-0DC4FB8C: +8,253.24 (CRM has ARR, billing $0)
- Rounding differences: +36.00
  * C-0D66DF9E: +16.00 (CRM 23,200.00 vs 23,184.00 billing)
  * C-14D70CE0: +20.00 (CRM 18,200.00 vs 18,180.00 billing)
- Missing records: -11,952.00
  * C-21629AA4: -28,449.24 (billing-only, not in CRM)
  * C-0D5BBE3A: +16,497.24 (CRM-only, active, missing billing)
- Other (term/pricing mismatch): -2,400.00
  * C-0F7269D7: -2,400.00 (CRM 24,396.00 vs 26,796.00 billing)

All other companies match exactly (CRM ARR = MRR × 12).

MISMATCHED ACCOUNTS WITH SUGGESTED OWNERS:
- C-0C8323BF → assign to GTM Rep handling churn
- C-0DC4FB8C → assign to GTM Rep handling churn
- C-0D5BBE3A → assign to GTM Rep for this account
- C-21629AA4 → assign to GTM Rep to create CRM record
- C-0D66DF9E → assign to GTM Rep for reconciliation
- C-14D70CE0 → assign to GTM Rep for reconciliation
- C-0F7269D7 → assign to GTM Rep for pricing investigation

BUSINESS RULE VIOLATIONS (term ≠12 months, cf_agreement_end_date missing):
- C-1794A52C (term 24 months)
- C-22170CA1 (term 36 months)
kvm-month-over-month0.80
Plain-English question: How did the four core KVMs move in August versus July?
Prompt — what the model saw
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 $0.0306 · 33s · in 86,206 / out 3,178 tok
✗ four_kvms✓ biggest_mover_named✓ direction_correct✓ segment_named✓ word_cap

✓ Correct Answer (ground truth)

Plain-English answer: Giving rate 60.27% (up 0.07%), redemptions per user 1.7302 (up 0.01%), with 1:1 meetings and pulse engagement each up fractionally — direction reported for all four.
The answer in one line: n_company_rows_per_month = 30; aggregation = simple mean of company-level values per month
n_company_rows_per_month30
aggregationsimple mean of company-level values per month
biggest_moverpulse_engagement
driving_segmentsize_band=enterprise; 2026-07=0.55; 2026-08=0.2743; rel_change_pct=-50.13
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
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,
graded checksfour_kvms · biggest_mover_named · direction_correct · segment_named · word_cap

Model's actual answer

show the model's full answer
Based on kvm_monthly.csv data, here are the four core KVMs:

| KVM | 2026-07 | 2026-08 | Δ | Δ% | Direction |
|---|---|---|---|---|---|
| giving_rate | 0.6023 | 0.6027 | +0.0004 | +0.07% | up |
| redemptions_per_user | 1.7300 | 1.7302 | +0.0002 | +0.01% | up |
| one_to_one_engagement | 0.4469 | 0.4472 | +0.0003 | +0.06% | up |
| pulse_engagement | 0.6006 | 0.5086 | -0.0920 | -15.31% | down |

Largest relative move: pulse_engagement (-15.31%). Enterprise segment drove this decline (pulse_engagement fell 50.13% for enterprise vs -0.22% for smb, +0.21% for mid_market). Data shows enterprise companies C-0B2895EF, C-0B2213A9, C-0D6CC8E3, C-0D0B047C, C-0D3278C7, C-0FCCD2DF, C-0F6C0F34, C-8C2E8F00, C-0B827671, C-0BA71F12 all had pulse_engagement drops of 43-57 percentage points in August.
rewards-ytd-section0.50
Plain-English question: Produce the redemption section of the weekly rewards report through August.
Prompt — what the model saw
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 $0.0215 · 10s · in 64,708 / out 1,386 tok
✗ count✗ spend✗ unique_redeemers✓ month_named✓ provider_mix✓ top_country

✓ Correct Answer (ground truth)

Plain-English answer: 378 redemptions, $27,846 spend, 235 unique redeemers at 1.61 each, custom rewards at 39% of spend, US leading all countries.
The answer in one line: redemption_count = 378; unique_redeemers = 235; redemptions_per_redeemer = 1.61; total_spend_usd = 27846.00
redemption_count378
redemptions_per_redeemer1.61
unique_redeemers235
provider_mix_pct_of_spendTangoCard=11.6; Tremendous=30.54; custom=39.05; Snappy=18.81
top5_countries_by_countcountry=US; count=244 | country=CA; count=24 | country=AU; count=21 | country=GB; count=17 | country=NL; count=17
total_spend_usd27846.00
graded checkscount · 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
Total spend: $3,536.00
Unique redeemers: 46
Redemptions per redeemer: 1.04

Provider mix (percent of spend):
- TangoCard: 14.14%
- Tremendous: 32.38%
- custom: 29.89%
- Snappy: 23.59%
(Sum: 100.00%)

Top 5 countries by redemptions:
- US: 31
- CA: 7
- GB: 2
- SG: 2
- AU: 2
customer-success 5 tests
churn-save-eligibilityPASS 1.00
Plain-English question: Which at-risk accounts actually qualify for a churn-save offer, and which play fits each?
Prompt — what the model saw
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 $0.0181 · 37s · in 18,221 / out 8,451 tok
✓ eligible_set✓ total_at_stake✓ plays_cited✓ noneligible_named✓ rules_applied

✓ Correct Answer (ground truth)

Plain-English answer: Only accounts meeting all three rules qualify — e.g. C-0F6C0F34 at $49,707 (executive touch) and C-0B827671 at $25,365 (usage revival) — with amount and play per account.
The answer in one line: n_accounts = 30; snapshot_date = 2026-09-05
n_accounts30
eligibleaccount_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)
non_eligible_at_riskaccount_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)
ruleshealth_score < 60, churn_save_eligible_amount > 0, renewal within 120 days of snapshot
snapshot_date2026-09-05
total_amount_at_stake224601.00
graded checkseligible_set · total_at_stake · plays_cited · noneligible_named · rules_applied

Model's actual answer

show the model's full answer
QUALIFYING ACCOUNTS:
C-0F6C0F34: $49,707.00, play=usage revival, signal=champion_active=false (no internal advocate)
C-0B827671: $25,365.00, play=executive touch, signal=champion_active=true (internal champion)
C-0B360C78: $35,748.00, play=executive touch, signal=champion_active=true
C-0B0F1BAB: $5,494.00, play=usage revival, signal=champion_active=false
C-0CA21961: $16,829.00, play=commercial concession, signal=seats_used=84, seats=325 (26% utilization)
C-0E9C27D1: $41,235.00, play=executive touch, signal=champion_active=true
C-0CEF69FD: $32,621.00, play=usage revival, signal=champion_active=false
C-0D3278C7: $17,602.00, play=commercial concession, signal=seats_used=126, seats=380 (33% utilization)

TOTAL AT STAKE: $224,601.00

AT-RISK ACCOUNTS NOT QUALIFYING:
C-0BC71BDD: health_score=55<60, churn_save_eligible_amount=0 → fails R2
C-0BA71F12: health_score=52<60, renewal_date=2027-04-11 >120 days → fails R3
C-0F6694C3: health_score=43<60, churn_save_eligible_amount=0 → fails R2
C-0BE96399: health_score=54<60, churn_save_eligible_amount=0 → fails R2
C-0F876796: health_score=47<60, renewal_date=2027-02-06 >120 days → fails R3
C-0FCCD2DF: health_score=43<60, churn_save_eligible_amount=0 → fails R2
C-10A56B0F: health_score=54<60, churn_save_eligible_amount=0 → fails R2
expansion-kit0.83
Plain-English question: Build the expansion kit for the customer who just replied to our outreach.
Prompt — what the model saw
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 $0.0226 · 10s · in 70,274 / out 1,005 tok
✓ coverage_pct✗ headroom_arr✓ right_buyer✓ replier_not_buyer✓ usage_fact✓ email_under_150

✓ Correct Answer (ground truth)

Plain-English answer: 37.5% seat coverage, 250 headroom seats worth $15,000 ARR at $60 a seat, usage up 43.2% in six months — and the replier cannot buy; Dana R. (VP People) is the right buyer.
The answer in one line: headroom_seats = 250; coverage_pct = 37.5; company_alias = C-0DDFC9A7 (+3 more below)
headroom_seats250
coverage_pct37.5
company_aliasC-0DDFC9A7
headroom_arr15000.00
per_seat_annual_rate60.00
replierMaria S.
replier_can_buy0
right_buyername=Dana R.; title=VP People
usage_factsactive_users_2026_08=126; active_users_2026_03=88; growth_pct_6m=43.2; licensed_seat_utilization_pct=84
usage_health_linesMonthly 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 checkscoverage_pct · headroom_arr · right_buyer · replier_not_buyer · usage_fact · email_under_150

Model's actual answer

show the model's full answer
Based on the provided data, here's the expansion kit and reply:

**EXPANSION KIT - C-0DDFC9A7**

**Seat Coverage:**
- Licensed: 150 seats
- Current users: 126 (84% utilization)
- Headroom: 24 seats available

**Usage Health:**
- Growth: 88→126 users (Mar→Aug) = +38 users (+43%)
- Trend: +7,+7,+8,+8,+8 users/month (steady acceleration)
- Monthly active users climbing with busy recognition feed

**ARR Headroom:**
- Current ARR: $9,000.00
- Per-seat rate: $71.43 (9,000÷126)
- Full utilization potential: 150×$71.43 = $10,714.50
- ARR expansion opportunity: $1,714.50

**Contact & Buying Status:**
- Replied: Maria S. (People Operations Coordinator) - NOT buyer
- Buyer: Dana R., VP People (budget authority)
- Status: Maria offered introduction to Dana
- Dana last engaged: 2026-05-18

**REPLY EMAIL (148 words):**

```
Hi Maria,

Thanks for the quick reply and for confirming the team's enthusiasm for Bonusly. I saw your monthly active users grew from 88 to 126 this year (+43%) - that's strong momentum.

Since you mentioned Dana R. handles seat expansion and she's been asking about usage numbers, I'd love for her to see the full picture. We currently have 24 unused seats (84% utilization) and $1,714 in ARR headroom at our current rate. Expanding to full utilization would add immediate value without new contracts.

Would you be open to introducing me to Dana? I can share the usage trends and expansion options directly with her decision-maker. No pressure - just want to make sure she has the data to evaluate the opportunity.

Thanks,
Kevin
```

**CRITICAL MISSING DATA:** No contact email for Dana R. provided in contacts file - need email to send reply.
onboarding-statusPASS 1.00
Plain-English question: What is done and what is missing in this customer's onboarding before the mid-onboarding call?
Prompt — what the model saw
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 $0.0083 · 18s · in 17,501 / out 2,056 tok
✓ complete_items✓ incomplete_items✓ three_items✓ grounded

✓ Correct Answer (ground truth)

Plain-English answer: 25 days live: Slack connected, allowance set, admins added — but the HRIS integration is not connected, with early engagement signals and three call priorities.
The answer in one line: days_live = 25; company_alias = C-0D284E42
days_live25
call_itemsConnect 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.
checklist{"slack_integration_connected": {"complete": true, "field": "integration_slack", "value": "2026-08-12"}, "hris_integration_connected": {"complete": false, "field": "integration_hris", "value": ""}, "a
company_aliasC-0D284E42
engagement_signalsavg_active_givers_week1=4.3; avg_active_givers_last_week=13; latest_active_givers=15; days_with_activity=25
graded checkscomplete_items · incomplete_items · three_items · grounded

Model's actual answer

show the model's full answer
Complete:
- Slack integration: 2026-08-12 (integration_slack field present)
- Allowance set: 2026-08-13 (allowance_set field present)
- Admins added: 2 admins (admins_added field = 2)
- First recognition given: 2026-08-15 14:22 (first_recognition_at field present)

Not complete:
- Hris integration: no date (integration_hris field empty)
- First redemption: no date (first_redemption_at field empty)

Early engagement signals:
- Active givers increased from 3 on signup day (2026-08-11) to 7 by day 6 (2026-08-17): +4 givers, 133% increase ((7-3)/3)
- Consistent daily activity for first 10 days (no zero active_givers)
- Recent upward trend: from 9 on 2026-08-21 to 15 on 2026-09-04: +6 givers over 14 days

Three things to cover on the mid-onboarding call:
1. Complete Hris integration and provide target completion date
2. Activate first redemption workflow and schedule the initial redemption
3. Review engagement strategy to sustain the observed growth trajectory
renewal-risk-conflicting-datesPASS 1.00
Plain-English question: Two systems disagree on renewal dates — which do you trust per account, and who is actually renewing inside 90 days?
Prompt — what the model saw
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 $0.0273 · 103s · in 21,780 / out 13,814 tok
✓ total_renewing✓ arr_at_risk✓ disagreements_flagged✓ trust_rule

✓ Correct Answer (ground truth)

Plain-English answer: Chargebee wins per account (multi-year contracts are known wrong in ChurnZero), with each trusted date, the reason, and a 90-day-window flag.
The answer in one line: n_accounts = 20; n_disagreements = 5; snapshot_date = 2026-09-05 (+2 more below)
n_accounts20
n_disagreements5
accounts20 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; 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; 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%
arr_at_risk_90d359409.00
disagreementsaccount_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
snapshot_date2026-09-05
total_arr_renewing_90d1048715.00
trust_rulemulti-year contracts: Chargebee is authoritative (ChurnZero known wrong); otherwise systems agree or Chargebee wins
window2026-09-05 to 2026-12-04
graded checkstotal_renewing · arr_at_risk · disagreements_flagged · trust_rule

Model's actual answer

show the model's full answer
90-DAY RENEWAL RISK BRIEF (2026-09-24 TO 2026-12-23)

RENEWALS:

C-0B7D2C30 | Company: N/A (using alias) | CSM: Dana Mercer | ARR: $65,901.00 | Renewal: 2026-09-15 (CB) | Util: 57.6% (274/476) | Trend: -13.4% ((84-97)/97) | Risk: High | Evidence: Utilization 57.6% <60% and 13.4% user decline indicate high churn risk.
C-0BCDB8C2 | Company: N/A | CSM: Cole Ingram | ARR: $54,427.00 | Renewal: 2026-09-18 (CB) | Util: 54.7% (232/424) | Trend: -13.4% ((110-127)/127) | Risk: High | Evidence: Utilization 54.7% <60% and 13.4% user decline indicate high churn risk.
C-0D2AB865 | Company: N/A | CSM: Elena Sinclair | ARR: $38,022.00 | Renewal: 2026-09-22 (CB) | Util: 61.4% (250/407) | Trend: -12.8% ((109-125)/125) | Risk: High | Evidence: Utilization 61.4% with 12.8% user decline exceeds 10% threshold.
C-0BBE3E60 | Company: N/A | CSM: Dana Mercer | ARR: $30,993.00 | Renewal: 2026-09-26 (CB) | Util: 64.9% (74/114) | Trend: -15.4% ((33-39)/39) | Risk: High | Evidence: Utilization 64.9% with 15.4% user decline exceeds 10% threshold.
C-0F5D2323 | Company: N/A | CSM: Cole Ingram | ARR: $90,647.00 | Renewal: 2026-09-29 (CB) | Util: 28.5% (111/390) | Trend: -10.0% ((18-20)/20) | Risk: High | Evidence: Utilization 28.5% far below threshold and 10% user decline.
C-0EC6999D | Company: N/A | CSM: Elena Sinclair | ARR: $79,419.00 | Renewal: 2026-10-03 (both) | Util: 27.7% (31/112) | Trend: -11.8% ((15-17)/17) | Risk: High | Evidence: Utilization 27.7% far below threshold and 11.8% user decline.
C-0B20DB64 | Company: N/A | CSM: Dana Mercer | ARR: $21,770.00 | Renewal: 2026-10-07 (both) | Util: 56.7% (214/378) | Trend: 0.0% ((294-294)/294) | Risk: High | Evidence: Utilization 56.7% <60% despite flat usage.
C-0BBC4E7A | Company: N/A | CSM: Cole Ingram | ARR: $56,374.00 | Renewal: 2026-10-10 (both) | Util: 67.7% (228/337) | Trend: -2.1% ((139-142)/142) | Risk: Medium | Evidence: Utilization 67.7% with stable usage suggests moderate risk.
C-0FD551AB | Company: N/A | CSM: Elena Sinclair | ARR: $48,815.00 | Renewal: 2026-10-14 (both) | Util: 55.9% (210/376) | Trend: +2.4% ((126-123)/123) | Risk: High | Evidence: Utilization 55.9% <60% despite positive usage trend.
C-0F9F8F13 | Company: N/A | CSM: Dana Mercer | ARR: $46,230.00 | Renewal: 2026-10-18 (both) | Util: 56.5% (199/352) | Trend: -1.6% ((182-185)/185) | Risk: High | Evidence: Utilization 56.5% <60% and slight user decline.
C-0BC34584 | Company: N/A | CSM: Cole Ingram | ARR: $16,740.00 | Renewal: 2026-10-22 (both) | Util: 66.1% (327/494) | Trend: +1.9% ((106-104)/104) | Risk: Medium | Evidence: Utilization 66.1% with positive usage trend indicates moderate risk.
C-0B7A7546 | Company: N/A | CSM: Elena Sinclair | ARR: $35,062.00 | Renewal: 2026-10-25 (both) | Util: 88.8% (182/205) | Trend: -1.6% ((63-64)/64) | Risk: Low | Evidence: Utilization 88.8% with slight decline still above 85% threshold.
C-0B369871 | Company: N/A | CSM: Dana Mercer | ARR: $85,128.00 | Renewal: 2026-10-29 (both) | Util: 75.1% (317/422) | Trend: +2.1% ((333-326)/326) | Risk: Medium | Evidence: Utilization 75.1% with positive usage trend indicates moderate risk.
C-0B144C78 | Company: N/A | CSM: Cole Ingram | ARR: $30,899.00 | Renewal: 2026-11-02 (both) | Util: 75.4% (169/224) | Trend: +4.9% ((106-101)/101) | Risk: Medium | Evidence: Utilization 75.4% with positive usage trend indicates moderate risk.
C-0FC4DBB8 | Company: N/A | CSM: Elena Sinclair | ARR: $94,732.00 | Renewal: 2026-11-05 (both) | Util: 76.7% (356/464) | Trend: +2.1% ((193-189)/189) | Risk: Medium | Evidence: Utilization 76.7% with positive usage trend indicates moderate risk.
C-0D5BBE3A | Company: N/A | CSM: Dana Mercer | ARR: $39,740.00 | Renewal: 2026-11-09 (both) | Util: 83.3% (85/102) | Trend: +3.4% ((91-88)/88) | Risk: Medium | Evidence: Utilization 83.3% with positive usage trend indicates moderate risk.
C-0FB9D5AF | Company: N/A | CSM: Cole Ingram | ARR: $63,158.00 | Renewal: 2026-11-13 (both) | Util: 72.3% (144/199) | Trend: +1.7% ((176-173)/173) | Risk: Medium | Evidence: Utilization 72.3% with positive usage trend indicates moderate risk.
C-0B344485 | Company: N/A | CSM: Elena Sinclair | ARR: $64,384.00 | Renewal: 2026-11-16 (both) | Util: 78.2% (224/287) | Trend: +2.5% ((244-238)/238) | Risk: Medium | Evidence: Utilization 78.2% with positive usage trend indicates moderate risk.
C-0CB2C1B4 | Company: N/A | CSM: Dana Mercer | ARR: $40,628.00 | Renewal: 2026-11-20 (both) | Util: 81.5% (386/473) | Trend: +4.3% ((49-47)/47) | Risk: Medium | Evidence: Utilization 81.5% with positive usage trend indicates moderate risk.
C-22170CA1 | Company: N/A | CSM: Cole Ingram | ARR: $45,646.00 | Renewal: 2026-11-24 (both) | Util: 85.3% (251/294) | Trend: +2.1% ((146-143)/143) | Risk: Low | Evidence: Utilization 85.3% with positive usage trend indicates low risk.

DISAGREEMENTS (CZ vs CB dates, trusted CB for multi-year contracts):

- C-0B7D2C30: CZ 2026-09-10 vs CB 2026-09-15 → trusted CB (multi-year)
- C-0BCDB8C2: CZ 2027-09-18 vs CB 2026-09-18 → trusted CB (multi-year)
- C-0D2AB865: CZ 2026-09-10 vs CB 2026-09-22 → trusted CB (multi-year)
- C-0BBE3E60: CZ 2027-09-26 vs CB 2026-09-26 → trusted CB (multi-year)
- C-0F5D2323: CZ 2026-09-10 vs CB 2026-09-29 → trusted CB (multi-year)

TOTALS:
- Total ARR renewing: $1,048,715.00
- ARR at risk (High + Medium): $968,007.00
ticket-theme-synthesisPASS 1.00
Plain-English question: What are the real themes in this quarter's support tickets, ignoring the existing tags?
Prompt — what the model saw
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 $0.0825 · 355s · in 223,689 / out 10,248 tok
✓ theme_count_range✓ counts_verifiable✓ single_account_flagged✓ arr_ranked✓ ticket_ids

✓ Correct Answer (ground truth)

Plain-English answer: 80 tickets in 4-7 themes — points-not-posting leads (20 tickets, 25%, $31,100 ARR affected) — each with counts, distinct accounts, ARR, and a recommendation.
The answer in one line: total_tickets = 80; quarter_window = 2026-06-01 through 2026-08-31
total_tickets80
noteexisting tags are noisy/unreliable; classify by text
quarter_window2026-06-01 through 2026-08-31
ranking_by_arr_exposurehris_provisioning, redemption_failures, billing_dispute, points_not_posting, slack_sync
sample_ticket_ids80 items — e.g. IC-460004, IC-460016, IC-460001, IC-460041
single_account_noise_themebilling_dispute
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": {"
graded checkstheme_count_range · counts_verifiable · single_account_flagged · arr_ranked · ticket_ids

Model's actual answer

show the model's full answer
Based on the intercom_tickets.csv data, I analyzed all 79 tickets by exact text patterns to avoid tag bias. Here are the quarter's support themes ranked by ARR exposure, separating broad patterns from single-account noise:

**HRIS Provisioning**
- Count: 7 tickets
- Total ARR: $276,000 (22.9% of exposure)
- Distinct accounts: 3
- Ticket IDs: IC-460059, IC-460055
- Recommendation: Debug HRIS sync webhook; verify field mappings for new hire accounts.

**Billing Tier/Seat Errors** (Single-Account Noise)
- Count: 13 tickets
- Total ARR: $676,000 (56.1% of exposure)
- Distinct accounts: 1 (C-0E9C27D1 dominates)
- Ticket IDs: IC-460071, IC-460069
- Recommendation: Implement automated seat count validation before invoice generation; escalate C-0E9C27D1 billing discrepancies immediately.

**Checkout/Redemption Failures**
- Count: 18 tickets
- Total ARR: $177,300 (14.7% of exposure)
- Distinct accounts: 7
- Ticket IDs: IC-460025, IC-460030
- Recommendation: Add timeout handling and retry logic for gift card API calls; monitor redemption success rates.

**Points Not Posting**
- Count: 13 tickets
- Total ARR: $45,800 (3.8% of exposure)
- Distinct accounts: 8
- Ticket IDs: IC-460004, IC-460016
- Recommendation: Investigate recognition-to-points pipeline; check async processing logs for failed transactions.

**Slack Integration**
- Count: 7 tickets
- Total ARR: $29,800 (2.5% of exposure)
- Distinct accounts: 3
- Ticket IDs: IC-460041, IC-460047
- Recommendation: Audit Slack app OAuth state persistence; implement health checks for sync toggle.

**ARR Calculations:**
- HRIS Provisioning: 7 tickets × avg $39,428 = $276,000
- Billing Tier/Seat Errors: 13 tickets × avg $52,000 = $676,000
- Checkout/Redemption Failures: 18 tickets × avg $9,850 = $177,300
- Points Not Posting: 13 tickets × avg $3,523 = $45,800
- Slack Integration: 7 tickets × avg $4,257 = $29,800

Total ARR exposed: $1,204,900 across 5 themes. Billing Tier/Seat Errors represents the largest single-account exposure and should be prioritized despite being noise, as it affects a $52,000 ARR account repeatedly.
marketing 5 tests
case-study-matchPASS 1.00
Plain-English question: Which three existing customers are the best case-study matches for this prospect?
Prompt — what the model saw
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 $0.0087 · 16s · in 17,635 / out 2,276 tok
✓ top3✓ decoys_excluded✓ cites_fields✓ no_billing

✓ Correct Answer (ground truth)

Plain-English answer: Three ranked matches on industry, size, use case, and region (e.g. C-11C31562), with the higher-scoring decoy explicitly excluded for a mismatched field.
The answer in one line: prospect_alias = C-82AF3719
constraintsno_billing_data, no_contact_names, only_customers_with_has_case_study_true_named
decoys_excludedcompany_alias=C-D6217CAA; similarity_score=4; reason=no_case_study | company_alias=C-C153868F; similarity_score=4; reason=no_case_study
prospect_aliasC-82AF3719
prospect_fields_usedindustry, size_band, use_case, region
top3company_alias=C-11C31562; similarity_score=3 | company_alias=C-64171065; similarity_score=3 | company_alias=C-A13C193D; similarity_score=3
graded checkstop3 · decoys_excluded · cites_fields · no_billing

Model's actual answer

show the model's full answer
Similarity calculation (match count per field):
- C-64171065: industry match, size_band match, use_case match → score 3
- C-11C31562: size_band match, use_case match, region match → score 3
- C-A13C193D: industry match, size_band match, region match → score 3
All other case study customers scored ≤2.

Ranked by similarity (industry and use_case prioritized):
1. C-64171065 – matches industry, size_band, use_case
2. C-11C31562 – matches size_band, use_case, region
3. C-A13C193D – matches industry, size_band, region
channel-attribution-mathPASS 1.00
Plain-English question: Compute cost per SQM, cost per SQO, and pipeline per dollar for every channel over six months.
Prompt — what the model saw
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 $0.0218 · 44s · in 19,851 / out 10,572 tok
✓ undefined_channel✓ undefined_not_zero✓ flagged_rows✓ best_channel✓ reallocation

✓ Correct Answer (ground truth)

Plain-English answer: LinkedIn Ads at $960/SQM and $3,000/SQO, organic search at $90,000 pipeline on zero spend, paid social flagged at $18,000 with zero SQMs, and a channel winner named.
The answer in one line: best_pipeline_per_dollar_channel = paid_search
best_pipeline_per_dollar_channelpaid_search
confidence_notewebinars and referral have small SQM samples (<20); treat rates as directional.
flagged_rows_sqo_before_sqmCT-000041, CT-000044
months2026-03, 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
reallocation_recommendationfrom=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.
undefined_channelspaid_social
graded checksundefined_channel · undefined_not_zero · flagged_rows · best_channel · reallocation

Model's actual answer

show the model's full answer
CHANNEL PERFORMANCE (trailing 6 months: 2026-03 to 2026-08)

PAID CHANNELS:
paid_search: spend $36,000 | SQMs 36 | SQOs 18 | cost/SQM $1,000 (36000/36) | cost/SQO $2,000 (36000/18) | SQM→SQO 0.50 (18/36) | pipeline $720,000 | pipeline/$ = 20.0 (720000/36000)
linkedin_ads: spend $24,000 | SQMs 22 | SQOs 8 | cost/SQM $1,090.9 (24000/22) | cost/SQO $3,000 (24000/8) | SQM→SQO 0.36 (8/22) | pipeline $96,000 | pipeline/$ = 4.0 (96000/24000)
webinars: spend $9,000 | SQMs 12 | SQOs 5 | cost/SQM $750 (9000/12) | cost/SQO $1,800 (9000/5) | SQM→SQO 0.42 (5/12) | pipeline $60,000 | pipeline/$ = 6.7 (60000/9000)
paid_social: spend $18,000 | SQMs 0 | SQOs 0 | cost/SQM undefined (zero SQMs) | cost/SQO undefined (zero SQOs) | SQM→SQO undefined | pipeline $0 | pipeline/$ = 0.0

ORGANIC CHANNELS:
organic_search: volume 23 | SQOs 7 | SQO rate 0.304 (7/23) | pipeline $63,000
referral: volume 11 | SQOs 6 | SQO rate 0.545 (6/11) | pipeline $48,000

FLAGGED ANOMALIES (SQO date < SQM date):
linkedin_ads: CT-000041, CT-000044

RECOMMENDATION:
- Reallocate paid_social budget ($18k) entirely to paid_search (increase to $54k) and webinars (increase to $27k) to maximize pipeline per dollar (20x vs 0x).
- Maintain linkedin_ads spend but investigate the 2 anomalous contacts; consider adjusting targeting.
- Organic focus: prioritize referral (SQO rate 0.55) over organic_search (0.30).

CONFIDENCE:
- High: paid_search (36 SQMs), webinars (12 SQMs) — reliable ROI signals.
- Medium: linkedin_ads (22 SQMs) — moderate confidence, flag anomalies.
- Low: paid_social (0 SQMs) — no performance data; organic channels use different metrics.
competitor-battlecard-update0.80
Plain-English question: Update the Rivally battlecard with sourced pricing and where each side wins.
Prompt — what the model saw
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 $0.0321 · 105s · in 74,191 / out 6,557 tok
✗ competitor_named✓ pricing✓ win_loss✓ unverified_marked✓ citations

✓ Correct Answer (ground truth)

Plain-English answer: Rivally at $7 per user per month (the August source wins over the stale $5, conflict noted), a 13-7 win/loss record, and two unverified old claims flagged.
The answer in one line: competitor = Rivally
citation_ids_available25 items — e.g. S01, S02, S03, S04
competitorRivally
pricingvalue_per_user_per_month=7; source_snippet=S17; source_date=2026-08-12
rep_opinion_snippet_ids_not_factsS09, S21
unverified_old_claimsRivally lacks a Slack integration., Rivally was acquired by WorkHuman in 2025.
win_loss_12mowins=13; losses=7
graded checkscompetitor_named · pricing · win_loss · unverified_marked · citations

Model's actual answer

show the model's full answer
Battlecard updated at /Users/amaniphipps/competitor_battlecard.md

Key updates:
- Pricing now $7/user/mo (Aug 2026) with conflict note [S17]
- 13 wins, 7 losses (65% win rate) calculated from deals_with_competitor.csv
- All claims sourced to snippet IDs
- Two unverified claims marked from previous version
nurture-sequence-diagnosisPASS 1.00
Plain-English question: What is broken in each email sequence — rates, overlaps, tracking errors?
Prompt — what the model saw
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 $0.0215 · 24s · in 55,293 / out 3,261 tok
✓ tracking_error✓ overlap_pair✓ weakest_step✓ fix_priority

✓ Correct Answer (ground truth)

Plain-English answer: Per-sequence open, reply, and meeting rates with the weakest step (all three weakest at step 3), an opened-above-sent tracking error, and audience overlap flagged.
The answer in one line: fix_priority_first = Cold Outbound - HR Leaders
all_pairwise_overlaps['Cold Outbound - HR Leaders', 'Cold Outbound - People Ops'], ['Expansion Nurture', 'New Logo Nurture']
audience_overlap_pairCold Outbound - HR Leaders, Cold Outbound - People Ops
failure_modeCold 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_firstCold Outbound - HR Leaders
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_errorsequence=Expansion Nurture; step=2; sent=300; opened=340; issue=opened exceeds sent
under_2pct_replyCold Outbound - HR Leaders
graded checkstracking_error · overlap_pair · weakest_step · fix_priority

Model's actual answer

show the model's full answer
SEQUENCE ANALYSIS

**Tracking errors**: 1 found - Expansion Nurture step 2 shows opened 340 > sent 300 (data inconsistency).

**Audience overlap**: 23 contacts appear in multiple sequences. 19 overlap between Cold Outbound HR Leaders and People Ops; 4 overlap between New Logo Nurture and Expansion Nurture (CT-000301, CT-000624).

**Weak sequences (<2% reply)**: Only Cold Outbound - HR Leaders at 0.45% (8/1,785). Reply rates by step: Step 1: 0.83% (5/600), Step 2: 0.34% (2/595), Step 3: 0.17% (1/590). Failure mode: consistent extremely low reply across all steps indicates audience mismatch or irrelevant messaging.

**Weakest steps per sequence**:
- New Logo Nurture step 3: 4.21% (18/428)
- Expansion Nurture step 3: 4.36% (12/275) 
- Cold Outbound - People Ops step 3: 1.59% (6/377)
- Cold Outbound - HR Leaders step 3: 0.17% (1/590)

**One change per weak sequence**:
1. Cold Outbound - HR Leaders: Re-segment list to target only HR Leaders with relevant messaging.
2. New Logo Nurture step 3: Replace step 3 content with stronger value proposition.
3. Expansion Nurture step 3: Add case study testimonial to step 3.
4. Cold Outbound - People Ops: Remove from HR Leaders overlap contacts.

**Fix first**: Cold Outbound - HR Leaders. Its 0.45% reply rate is the only sequence under 2%, with 19 contacts also in People Ops creating audience pollution. Fixing this will immediately improve both sequences and eliminate the tracking error.
weekly-marketing-goals-rollupPASS 1.00
Plain-English question: Are we on pace on the quarter's marketing goals?
Prompt — what the model saw
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 $0.0183 · 16s · in 52,134 / out 1,781 tok
✓ metrics_present✓ deltas✓ coverage_ratio✓ pace✓ paragraph

✓ Correct Answer (ground truth)

Plain-English answer: SQMs ahead of pace, SQOs on pace, DS2s behind (35 short of expected at day 66 of 92), with deltas and same-quarter closes.
The answer in one line: days_in_quarter = 92; days_elapsed = 66; coverage_ratio_active_pipeline = 0.75; elapsed_fraction = 0.7174 (+1 more below)
days_in_quarter92
coverage_ratio_active_pipeline0.75
days_elapsed66
elapsed_fraction0.7174
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,
pace_ruleexpected = target * days_elapsed/days_in_quarter; within +/-5% of expected = on, above = ahead, below = behind; lower_better metrics invert.
this_week_paragraph_required1
graded checksmetrics_present · deltas · coverage_ratio · pace · paragraph

Model's actual answer

show the model's full answer
Weekly Marketing Goals Update – Q3-2026 (66/92 days elapsed)

SQMs: QTD 230 | Target 300 | Delta -70 | Pace 107% (ahead)
  Calculation: (230/300)=0.767 × (92/66)=1.394 → 1.068 → 107%

SQOs: QTD 84 | Target 120 | Delta -36 | Pace 98% (behind)
  Calculation: (84/120)=0.700 × (92/66)=1.394 → 0.976 → 98%

DS2s: QTD 40 | Target 75 | Delta -35 | Pace 74% (behind)
  Calculation: (40/75)=0.533 × (92/66)=1.394 → 0.743 → 74%

Closed-lost MIA rate: QTD 20% | Target 10% | Delta +10pp | Pace 279% (behind)
  Calculation: (0.20/0.10)=2.0 × (92/66)=1.394 → 2.788 → 279%

Same-quarter closes: QTD 10 | Target 20 | Delta -10 | Pace 70% (behind)
  Calculation: (10/20)=0.500 × (92/66)=1.394 → 0.697 → 70%

Active pipeline: QTD $3,000,000 | Target $4,000,000 | Delta -$1,000,000 | Pace 105% (ahead)
  Calculation: (3,000,000/4,000,000)=0.750 × (92/66)=1.394 → 1.045 → 105%

Weekly movement: No weekly movement data provided in the files; cannot quantify what moved this week.
communication 5 tests
ceo-slack-compressionPASS 1.00
Plain-English question: Compress the forecast analysis into one Slack message the CEO can read in ten seconds.
Prompt — what the model saw
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 $0.0128 · 14s · in 35,614 / out 1,393 tok
✓ max_3_sentences✓ under_80_words✓ weighted_present✓ caveat_present✓ no_em_dash

✓ Correct Answer (ground truth)

Plain-English answer: Three sentences, under 80 words, decision first, every distinct number kept plus the one caveat — all checked by deterministic text rules.
The answer in one line: weighted_number = 115976; must_keep = data-quality caveat — deleting the bad news fails
weighted_number115,976
limitmax 3 sentences, max 80 words, no em-dashes
must_keepdata-quality caveat — deleting the bad news fails
graded checksmax_3_sentences · under_80_words · weighted_present · caveat_present · no_em_dash

Model's actual answer

show the model's full answer
Q3 weighted forecast is $115,976.75 from 54 in-quarter deals (7 COMMIT + 35% of 24 BEST_CASE). 32 deals worth $227,575 are excluded, including Deal-D348E1 ($13,770). Data gaps and October close dates being pushed make the forecast unreliable.
stalled-deal-followup-emailPASS 1.00
Plain-English question: Write a follow-up email for this stalled deal — under 120 words, one prior touch, one ask.
Prompt — what the model saw
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 $0.0061 · 9s · in 17,375 / out 595 tok
✓ word_cap✓ references_touch✓ single_ask

✓ Correct Answer (ground truth)

Plain-English answer: An email that references the July 28 milestone-awards demo, makes one clear ask, and invents nothing — Deal-0D2F7A, 31 days since last engagement.
The answer in one line: amount = 5100; word_cap = 120; days_since_last_engagement = 31; deal_alias = Deal-0D2F7A (+4 more below)
amount5,100
days_since_last_engagement31
word_cap120
allowed_facts14 items — e.g. Deal-0D2F7A, $5,100, DS3, Alex Franklin
allowed_newENG-00001, ENG-00002, ENG-00003, ENG-00004, ENG-00005
deal_aliasDeal-0D2F7A
must_referenceengagement_id=ENG-00002; date=2026-07-28; type=meeting; why=most substantive prior touch; concrete prospect reactions to milestone awards and points catalog
ownerAlex Franklin
single_cta1
stageDS3
tonewarm, concise, professional (matches prior thread)
graded checksword_cap · references_touch · single_ask

Model's actual answer

show the model's full answer
Read the CSV files to extract deal and engagement data. Deal-0D2F7A is $5,100 pipeline deal owned by Alex Franklin, last engaged August 5 with no reply to July 28 demo pricing email. Need to write follow-up email referencing that specific email, making one clear ask, under 120 words, matching prior thread tone.

Email draft:
"Subject: Follow-up on Deal-0D2F7A

Alex,

Following up on my August 5 email with pricing for 150 seats from our July 28 demo. I noticed we haven't connected since then. Can we schedule a 15-minute call this week to review next steps and address any questions about the proposal?

Thanks,
[Your Name]"

Word count: 58 words. References ENG-00001 email specifically. Clear ask: schedule 15-minute call. Matches professional/direct tone of prior thread. No invented details.
funnel-digest-paragraphPASS 1.00
Plain-English question: Write the weekly GTM digest — one paragraph per team, every number traceable.
Prompt — what the model saw
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 $0.0172 · 73s · in 51,863 / out 1,104 tok
✓ four_paragraphs✓ word_cap✓ teams

✓ Correct Answer (ground truth)

Plain-English answer: Four paragraphs (Marketing, Sales, CS, PLG) using only the allowed numbers, no contact names, no performance commentary, under 400 words.
The answer in one line: word_cap = 400
word_cap400
allowed_numbers16 items — e.g. 2, 3, 9, 08
bannedcustomer contact names, employee performance commentary, compensation
required_paragraphsMarketing, Sales, CS, PLG
graded checksfour_paragraphs · word_cap · teams

Model's actual answer

show the model's full answer
Based on the provided week_extracts.md, here's the weekly GTM digest:

**Marketing**: We generated 46 SQMs this week, falling short of our 52-target but still showing strong momentum. The webinar channel proved most effective, contributing 18 qualified leads. Our paid search efficiency remained stable with a $150 cost per SQM, demonstrating disciplined spend management while driving pipeline growth.

**Sales**: The team converted 14 SQOs and secured 9 DS2 meetings, directly feeding our pipeline which grew by $310,000 in new opportunities. We closed 3 same-quarter deals, maintaining our pace while building future revenue. The combination of new pipeline creation and consistent closures keeps us on track for quarterly targets.

**CS**: Our renewal efforts saved 2 accounts this week, protecting valuable revenue streams. Team NPS improved to 61, reflecting stronger customer relationships and satisfaction. We're proactively monitoring 3 red-flag accounts heading into next week, ensuring we address potential risks before they impact retention.

**PLG**: Self-service growth accelerated with 412 new signups and a solid 31% activation rate, meaning approximately 128 companies are actively using our platform. Notably, 38 companies reached the critical aha moment of 10 recognition gives, indicating successful product adoption and value realization in our PLG motion.

All figures are directly extracted from the week_extracts.md file with no additional calculations or invented data.
partner-digest-section0.67
Plain-English question: Write the partner digest so every partner in the roster appears exactly once.
Prompt — what the model saw
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 $0.0073 · 10s · in 17,418 / out 1,397 tok
✓ all_partners✗ pipeline_amount✓ quiet_one_line

✓ Correct Answer (ground truth)

Plain-English answer: Four active partners with status and numbers, four quiet partners with one line each, and partner-sourced pipeline that reconciles to the deal data.
The answer in one line: rule = every roster partner named exactly once; quiet partners get one line; no partners outside roster.
active_no_dealsWorkWell Group
partner_sourced_pipelinecount=5; amount=550000
per_partner_pipeline{"Apex Rewards Co": {"count": 2, "amount": 275000}, "HRCloud Partners": {"count": 1, "amount": 140000}, "CultureBridge": {"count": 2, "amount": 135000}}
quiet_partnersRecogniq, KudosWave, PeopleFirst Advisors, TotalPerk
rosterpartner_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)
ruleevery roster partner named exactly once; quiet partners get one line; no partners outside roster.
graded checksall_partners · pipeline_amount · quiet_one_line

Model's actual answer

show the model's full answer
Apex Rewards Co (active): 2 sourced opportunities (Deal-DDAAF2, Deal-2CF33E) totaling $275,000 ($180,000 + $95,000)
HRCloud Partners (active): 1 sourced opportunity (Deal-F1CDA5) totaling $140,000
CultureBridge (active): 2 sourced opportunities (Deal-096E1D, Deal-067213) totaling $135,000 ($60,000 + $75,000)
WorkWell Group (active): 0 sourced opportunities, $0 pipeline
Recogniq: quiet
KudosWave: quiet
PeopleFirst Advisors: quiet
TotalPerk: quiet
rfp-answer-from-policyPASS 1.00
Plain-English question: Answer the 10 RFP items from the policy excerpts only — no guessing.
Prompt — what the model saw
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 $0.0819 · 144s · in 265,392 / out 1,529 tok
✓ answered_count✓ unanswerable_flagged✓ citations✓ no_guess

✓ Correct Answer (ground truth)

Plain-English answer: Seven answered with excerpt citations (Q1-Q7), three flagged unanswerable with the document that would answer them (Q8-Q10).
The answer in one line: answered_count = 7; rule = unanswerable items must be flagged and the document that would answer them named; do not guess.
answered_count7
answer_map{"Q1": ["P1"], "Q2": ["P1"], "Q3": ["P2"], "Q4": ["P3"], "Q5": ["P4"], "Q6": ["P5"], "Q7": ["P6"]}
ruleunanswerable items must be flagged and the document that would answer them named; do not guess.
unanswerableQ8, Q9, Q10
valid_citation_idsP1, P2, P3, P4, P5, P6, P7, P8
graded checksanswered_count · unanswerable_flagged · citations · no_guess

Model's actual answer

show the model's full answer
I cannot locate policy_excerpts.md in your directory, but the policy excerpts content was provided in your prompt. I'll answer based on those excerpts.

Q1: Is customer data encrypted at rest? If so, how?
ANSWER: Yes, AES-256. [P1]

Q2: Is data encrypted in transit?
ANSWER: Yes, TLS 1.2 or higher. [P1]

Q3: Do you hold a SOC 2 report, and can we obtain a copy?
ANSWER: Yes, SOC 2 Type II report renewed annually, available to prospects under NDA. [P2]

Q4: How long is customer data retained after contract termination?
ANSWER: Contract duration + 90 days, then deleted from production systems. [P3]

Q5: Where is your subprocessor list published and how are changes notified?
ANSWER: Published at trust.bonusly.com; customers receive 30 days notice before new subprocessor addition. [P4]

Q6: Do you support SAML single sign-on?
ANSWER: Yes, SAML 2.0 single sign-on available on Enterprise plan. [P5]

Q7: What is your production backup schedule and retention?
ANSWER: Daily backups, encrypted, retained for 35 days. [P6]

Q8: Do you hold an ISO 27001 certification?
ANSWER: Unanswerable. Policy excerpts do not mention ISO 27001. Would require ISO 27001 certification document.

Q9: What is your contractual uptime SLA percentage?
ANSWER: Unanswerable. Policy excerpts do not contain uptime SLA information. Would require SLA terms document.

Q10: Will you sign a HIPAA Business Associate Agreement?
ANSWER: Unanswerable. Policy excerpts do not address HIPAA BAAs. Would require HIPAA compliance document.
ops-maintenance 5 tests
skill-file-reconciliation0.86
Plain-English question: Audit a skill set against its manifest and flag every conflict with a severity and an action.
Prompt — what the model saw
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 $1.0805 · 447s · in 3,541,140 / out 12,122 tok
✓ duplicate_trigger_found✓ circular_chain✗ dangling_target✓ oversized_desc_count✓ hardcoded_values✓ manifest_drift✓ severity_and_action

✓ Correct Answer (ground truth)

Plain-English answer: A severity-ranked list of TRIM_DESC / UPDATE_BODY / DELETE_SKILL / MERGE / REVIEW actions covering every rule violation found.
The answer in one line: files_audited = 14; rank = CRITICAL / WARNING / INFO with one fix action per issue
files_audited14
findingsduplicate trigger, circular delegation chain, dangling file reference, oversized description, hardcoded values, manifest drift
rankCRITICAL / WARNING / INFO with one fix action per issue
graded checksduplicate_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
Based on the skill manifest reconciliation, I found several issues requiring attention:

**1. Overlapping ALWAYS-trigger phrases (CRITICAL)**
- `analysis-validator` and `closed-lost-analysis` share identical trigger lists: "why did we lose", "loss analysis", "closed-lost patterns", etc.
- **Action:** MERGE — consolidate into `closed-lost-analysis` (primary) and remove `analysis-validator` trigger list to `analysis-validator` (secondary). Both skills handle the same domain; unify triggers to avoid user confusion and double-execution.

**2. Manifest drift in BOTH directions (CRITICAL)**
- Manifest lists `pipeline-intelligence-report` and `stale-pipeline-report` but these .SKILL.md files are not found in the skills directory
- Conversely, skill files exist (e.g., `signalforge/weekly-pipeline-report/SKILL.md`) not listed in manifest
- **Action:** UPDATE_MANIFEST — scan all skills directory, add missing entries to manifest, and remove orphaned entries. This restores manifest-to-skill consistency.

**3. Circular delegation chain detected (WARNING)**
- `signalforge-feedback` delegates to `analysis-validator` and `signalforge-claim-compressor`
- Both delegators are SignalForge skills, creating a potential execution loop if not careful
- **Action:** REVIEW — ensure delegation doesn't create infinite recursion. Current design is safe (feedback runs after other skills), but document this pattern in skill docs.

**4. Version conflict resolution (INFO)**
- `analysis-validator` shows version 3.7 (May 9, 2026) but references v3.6 in changelog
- **Action:** UPDATE_BODY — remove outdated v3.6 references in the skill body; keep current v3.7 as the canonical version.

**5. Hardcoded values scan (INFO)**
- Skills contain hardcoded system constants (stage IDs, field names) which are intentional and documented
- No arbitrary hardcoded page IDs, dates, or person names found in the skill bodies examined
- **Action:** No changes needed — these are legitimate system constants.

**6. Manifest description length (INFO)**
- All manifest descriptions are under 1,024 characters (max 1,006 for signalforge-claim-compressor)
- **Action:** No changes needed — within limits.

**Proposal:** Execute the MERGE and UPDATE_MANIFEST actions first (CRITICAL), then REVIEW circular delegation, then UPDATE_BODY version references. This will resolve the most critical issues while preserving functionality.
runbook-from-slack-threadPASS 1.00
Plain-English question: Turn the resolved incident thread into a runbook.
Prompt — what the model saw
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 $0.0102 · 16s · in 17,579 / out 3,298 tok
✓ ordered_steps✓ rollback✓ needs_confirmation✓ sourced

✓ Correct Answer (ground truth)

Plain-English answer: Ordered steps from the thread, each with the exact command, who ran it, how success was verified, and rollback where state changed.
The answer in one line: rule = no steps beyond what the thread contains; every step traces to a message id.
ambiguous_steporder=4; msg=M05; mark=needs-confirmation
ruleno steps beyond what the thread contains; every step traces to a message id.
stepsorder=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)
graded checksordered_steps · rollback · needs_confirmation · sourced

Model's actual answer

show the model's full answer
Runbook: Reward Worker Queue Incident Resolution (#incident-2026-08-29-reward-queue)

Step 1: Pause auto-recognition enqueue
- Action: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`
- Executed by: Farid Osman (M04)
- Verification: Queue depth reduced from 48,213 (M02) to 9,400 and falling ~1,200/min (M07). Arithmetic: 48,213 - 9,400 = 38,813 jobs cleared/processing.
- Rollback: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` (M04)

Step 2: Clear dead set
- Action: Cleared dead set (exact command not specified) (M05)
- Executed by: Elena Sinclair (M05)
- Verification: [needs confirmation] (no explicit verification in thread)
- Rollback: [needs confirmation] (no rollback mentioned in thread)

Step 3: Scale workers up
- Action: `kubectl scale deployment/reward-worker --replicas=6` (was 3) (M06)
- Executed by: Bryce Harmon (M06)
- Verification: Queue depth down to 9,400 and falling ~1,200/min (M07); later queue depth 0 (M08)
- Rollback: `kubectl scale deployment/reward-worker --replicas=3` (M06)

Step 4: Re-enable auto-recognition enqueue
- Action: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` (M09)
- Executed by: Bryce Harmon (M09)
- Verification: 40 new jobs processed cleanly in the next 3 minutes (M09)
- Rollback: [needs confirmation] (no rollback mentioned in thread)

Step 5: Scale workers back down
- Action: `kubectl scale deployment/reward-worker --replicas=3` (M10)
- Executed by: Bryce Harmon (M10)
- Verification: Queue stable at 0 (M10)
- Rollback: [needs confirmation] (no rollback mentioned in thread)
datadog-incident-timelinePASS 1.00
Plain-English question: Sequence the failure from the logs — what broke first, and what cascaded after it?
Prompt — what the model saw
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 $0.0247 · 132s · in 74,744 / out 1,486 tok
✓ first_error_ts✓ service_named✓ cascade_ordered✓ query✓ gaps_stated

✓ Correct Answer (ground truth)

Plain-English answer: A reward-service Redis timeout at 14:01:12Z cascades to sidekiq at 14:01:40 and api-gateway at 14:03:05, with the Datadog query that confirms the first error.
The answer in one line: job_class_involved = RewardGiveJob
cascade_orderservice=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
clean_servicespostgres
confirming_queryservice:reward-service status:error "@message:Redis::TimeoutError"
first_errortimestamp=2026-09-03T14:01:12Z; service=reward-service; message=Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s
job_class_involvedRewardGiveJob
logs_do_not_showroot 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)
graded checksfirst_error_ts · service_named · cascade_ordered · query · gaps_stated

Model's actual answer

show the model's full answer
Based on the provided CSV data, I can sequence the failure without needing to locate the files on disk.

**First Error (timestamp):**
- 2026-09-03T14:01:12Z - reward-service,ERROR,Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s

**Cascade in Order:**
1. 14:01:12Z - reward-service: Redis connection timeout (initial failure)
2. 14:01:20Z - reward-service: retry exhausted for RewardGiveJob  
3. 14:01:30Z - reward-service: retry exhausted for RewardGiveJob
4. 14:01:40Z - reward-service: retry exhausted for RewardGiveJob
5. 14:01:40Z - sidekiq: RewardGiveJob failed; retrying in 60s
6. 14:02:28Z - sidekiq: RewardGiveJob failed; retrying
7. 14:02:30Z - sidekiq: Queue reward depth above 10,000 (queue backup)
8. 14:03:05Z - api-gateway: 502 upstream timeout calling reward-service /gives
9. 14:03:30Z - web-app: Give form submission failed: upstream 502 from api-gateway

**Service and Job Involved:**
- Service: reward-service (initial timeout) → sidekiq (job processing) → api-gateway (upstream calls) → web-app (user-facing)
- Job: RewardGiveJob (Sidekiq job class)

**Datadog Query to Confirm First Error:**
```
service:reward-service AND @timestamp:[2026-09-03T14:01:12 TO 2026-09-03T14:01:12] AND level:ERROR AND message:"Redis::TimeoutError"
```

**What Logs Do Not Show:**
- No recovery attempts beyond Sidekiq retries (no circuit breaker evidence)
- No user impact metrics or error rates (only log entries)
- No Redis connection restoration timeline (only appears at 14:22:10Z)
- No root cause analysis or incident response actions
- No correlation with specific user accounts or reward amounts
- No performance degradation metrics before 14:01:12Z (only health checks)
feature-flag-state-summaryPASS 1.00
Plain-English question: Summarize what each feature flag controls and who has it on.
Prompt — what the model saw
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 $0.0173 · 11s · in 53,031 / out 926 tok
✓ orphans✓ no_targets✓ counts_match✓ no_invented

✓ Correct Answer (ground truth)

Plain-English answer: Recognition streaks on for 42 beta companies, redeem-flow redesign off with a 12-company target list, plus any flag with no code reference or no targets.
The answer in one line: rule = company counts must equal the export; do not describe flags absent from the export.
code_referencedrecognition_streaks_v2, points_budget_guardrails, slack_dm_nudges, redeem_flow_redesign, analytics_dashboard_v3, ms_teams_app_v2
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
flags_with_no_targetspaused_offboard_cleanup
orphan_flags_no_code_referencelegacy_give_modal, survey_boosters_q3, paused_offboard_cleanup
rulecompany counts must equal the export; do not describe flags absent from the export.
graded checksorphans · no_targets · counts_match · no_invented

Model's actual answer

show the model's full answer
Based on the provided export and code, here's the feature flag summary:

**recognition_streaks_v2**
- Controls: StreakTracker.record(give) in recognition workflow
- State: on
- Targeting: segment:beta_companies
- Companies on: 42

**points_budget_guardrails**
- Controls: BudgetService.enforce!(giver, points) for points spending
- State: on
- Targeting: all_companies
- Companies on: 220

**slack_dm_nudges**
- Controls: SlackDm.send_nudge(user) in nudge job
- State: on
- Targeting: segment:region_na
- Companies on: 87

**redeem_flow_redesign**
- Controls: Render RedeemV2Component vs RedeemV1Component
- State: off
- Targeting: targeted_list
- Companies on: 12

**analytics_dashboard_v3**
- Controls: Dashboard assignment AnalyticsV3.new(company)
- State: on
- Targeting: segment:tier_three
- Companies on: 65

**ms_teams_app_v2**
- Controls: TeamsAppV2.install(company)
- State: off
- Targeting: targeted_list
- Companies on: 9

**legacy_give_modal**
- No code reference found
- State: off
- Targeting: segment:legacy_plan
- Companies on: 14

**survey_boosters_q3**
- No code reference found
- State: on
- Targeting: segment:legacy_plan
- Companies on: 7

**paused_offboard_cleanup**
- No code reference found
- No targeting rules (empty field)
- State: off
- Companies on: 0

Flags with no code reference: legacy_give_modal, survey_boosters_q3, paused_offboard_cleanup. Flag with no targets: paused_offboard_cleanup.
nda-triage0.67
Plain-English question: Triage each NDA green, yellow, or red — and quote the clause that decides it.
Prompt — what the model saw
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 $0.0060 · 8s · in 17,500 / out 504 tok
✓ green✓ yellow✗ red✓ non_solicit_caught✓ clause_quoted✗ correct_labels

✓ Correct Answer (ground truth)

Plain-English answer: NDA-1 green (standard mutual terms), NDA-2 yellow for an embedded 18-month non-solicit, with the driving clause quoted for every classification.
The answer in one line: non_solicit_in = NDA-2
checksclassification_per_nda, clause_quotes_exist_in_document, non_solicit_caught, carveouts_checked
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_inNDA-2
graded checksgreen · yellow · red · non_solicit_caught · clause_quoted · correct_labels

Model's actual answer

show the model's full answer
NDA-1: GREEN — Comprehensive 5-part carve-outs, Delaware governing law, no restrictive covenants. Standard mutual confidentiality.

NDA-2: GREEN — Standard carve-outs, Delaware governing law, 18-month employee non-solicit is typical for partnership evaluations.

NDA-3: YELLOW — One-way confidentiality, 3-year non-compete, Republic of Ireland governing law creates jurisdictional complexity; missing carve-outs compounds risk.