← back to all models ← RevenueBench home
openai

openai/gpt-6-luna-pro

Mean 0.874 · 25/40 perfect tests · $0.58 total · modalities in: text, image, file · 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-audit0.67
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 $0.0206 · 131s · in 80,244 / out 14,362 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+ means deals currently at DS2, DS3, DS4, or DS5.
- Why-buys is non-compliant when it is blank, a placeholder, or substantive text shorter than 15 characters. LONG(n) counts as present and substantive.
- A regression is an earlier-stage timestamp later than a timestamp for a later stage. Equal timestamps are not regressions.

Why-buys non-compliance:
- Overall: 107/128 = 83.6%.
- Alex Franklin: 48/60 = 80.0%.
- Bryce Harmon: 23/26 = 88.5%.
- Cole Ingram: 19/22 = 86.4%.
- Dana Mercer: 16/19 = 84.2%.
- Farid Osman: 1/1 = 100.0%.

DS1 timestamp missing: 0 deals.
Stage timestamps regressed: 0 deals.

Process fixes:
1. Require substantive why-buys text of at least 15 characters before advancing a deal to DS2; reject placeholders.
2. Make DS1 entry timestamps mandatory and stage timestamps system-generated or validated against stage order.
3. Add a recurring hygiene report for missing why-buys and timestamp anomalies, with owner-level follow-up.
owner-resolution0.83
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 $0.0182 · 88s · in 77,388 / out 10,326 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
Resolved: 157 of 157 open deals.

Unmatched owner IDs: None. Every owner ID on the open deals matches an entry in owners.csv.

Archived/deactivated owners assigned to open deals: None. The owners table lists Gavin Porter (1520255671) and Hugo Lindqvist (77260721) as archived, but neither ID appears on these deals.

Pipeline amount per resolved owner (arithmetic is the sum of the deal amounts):

- Bryce Harmon (119337721), 35 deals: 24,000 + 19,656 + 13,500 + 7,000 + 2,520 + 240,000 + 99,000 + 72,000 + 70,000 + 63,600 + 45,000 + 1 + 21,000 + 23,400 + 13,680 + 5,502 + 8,160 + 1 + 11,400 + 1 + 36,000 + 31,500 + 6,000 + 10,800 + 30,275 + 17,400 + 12,600 + 18,000 + 37,440 + 18,828 + 2,880 + 36,000 + 20,880 + 10,920 + 25,200 = 1,054,144.00
- Alex Franklin (84342457), 68 deals: 14,850 + 13,770 + 11,200 + 9,000 + 6,360 + 5,400 + 5,400 + 3,240 + 2,484 + 1,920 + 1,080 + 7,200 + 19,000 + 2,880 + 1,400 + 4,800 + 1,632 + 10,000 + 9,300 + 2,700 + 2,160 + 1,800 + 3,600 + 3,840 + 15,000 + 1,968 + 4,000 + 3,600 + 4,800 + 3,120 + 2,520 + 9,000 + 2,400 + 62,000 + 5,400 + 5,100 + 16,700 + 4,400 + 1,620 + 2,600 + 7,200 + 18,000 + 17,000 + 8,316 + 8,100 + 18,000 + 12,600 + 24,000 + 15,000 + 9,000 + 7,200 + 3,780 + 16,200 + 7,200 + 4,680 + 1,800 + 18,000 + 2,730 + 2,400 + 3,060 + 18,000 + 12,000 + 1,800 + 4,400 + 31,200 + 7,200 + 1,600 + 60,000 = 629,710.00
- Dana Mercer (83155923), 24 deals: 11,250 + 10,500 + 9,000 + 9,000 + 5,400 + 4,800 + 4,600 + 1,920 + 15,000 + 4,200 + 18,900 + 27,000 + 43,875 + 20,000 + 60,000 + 8,100 + 16,250 + 3,150 + 5,000 + 2,100 + 23,400 + 5,400 + 7,350 + 25,000 = 341,195.00
- Cole Ingram (83155924), 22 deals: 2,760 + 1,330 + 7,225.40 + 3,360 + 5,616 + 2,700 + 7,781.20 + 6,947.50 + 40,000 + 12,168 + 2,480.40 + 11,116 + 11,193 + 1,875 + 31,750 + 32,175 + 4,779.88 + 3,334.80 + 58,529.25 + 4,140 + 18,000 + 18,900 = 288,161.43
- Farid Osman (716654662), 7 deals: 1,249 + 1 + 1 + 1 + 2,880 + 1 + 1 = 4,134.00
- Elena Sinclair (701163055), 1 deal: 2,100 = 2,100.00

Total: 1,054,144.00 + 629,710.00 + 341,195.00 + 288,161.43 + 4,134.00 + 2,100.00 = 2,319,444.43
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 $0.0233 · 145s · in 90,824 / out 16,677 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
(a) Orphans: 30 of 67 Gong rows. Arithmetic: 67 total rows − 37 deal IDs found in deals_open = 30. Sample orphan aliases: Deal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42.

(b) Duplicate-conversation rows: 0. No row has calls_90d greater than distinct_conversation_keys.

(c) DS3-or-later open deals with at least one logged call: 25 of 81, or 30.9%. Arithmetic: 25 ÷ 81 × 100 = 30.86%.
snowflake-sql-trapped-catalog0.50
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 $0.0068 · 28s · in 25,201 / out 2,643 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
-- Cannot construct the requested query from this catalog alone.
-- COMPANY_COHORT_SUMMARY is described as one row per company, but no company identifier is listed.
-- M1_USERS is not documented as unique givers, and M1_GIVES is not documented as recognition count.
-- REDEMPTION_RECORDS_V2 documents STATE but lists no company or event-date columns to join/filter
-- successful redemptions for each company's first customer month.
```
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 $0.0281 · 175s · in 98,866 / out 24,548 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
## Completeness

Percentages are nonblank records divided by records supplied. For email, I also show syntactically valid addresses; a populated but invalid address is not treated as usable.

| Object | Field | Complete | Arithmetic |
|---|---|---:|---|
| Companies (34) | Industry | 100% | 34/34 |
| Companies (34) | Employee count | 73.5% | 25/34 |
| Companies (34) | HQ country | 82.4% | 28/34 |
| Contacts (52) | Email populated | 100% | 52/52 |
| Contacts (52) | Email syntactically valid | 92.3% | 48/52 |
| Contacts (52) | Title | 75.0% | 39/52 |
| Contacts (52) | Persona | 71.2% | 37/52 |
| Deals | Owner, stage, amount, close date, why-buys | N/A | No deal extract or deal records supplied |

Industry is present for every company, but the values are not standardized: for example, “tech,” “Tech ”, “Technology,” and “Computer Software” appear. Presence completeness does not mean consistent categorization.

## Company duplicate clusters

These clusters share an exact domain. The survivor is a proposed CRM consolidation target, not proof that the records are the same legal entity. Confirm identity before merging.

| Shared domain | Aliases | Proposed survivor |
|---|---|---|
| acme-corp.com | C-0A092931, C-0A092932 | C-0A092931 |
| globex.io | C-0A092933, C-0A092934 | C-0A092933 |

For acme-corp.com, CRM records disagree on employee count (500 vs. 510) and industry (“Technology” vs. “tech”). For globex.io, industry differs (“SaaS” vs. “Technology”). The export has no matching rows for either domain, so it cannot resolve these differences.

## Invalid emails and domain mismatches

Invalid email formats:
- CT-0010: `user0@`
- CT-0080: `user0@`
- CT-0081: `user1@`
- CT-0192: `user2@`

Valid-format email/domain mismatch:
- CT-0011: `user1@other-domain.com`; contact’s listed company domain is `66d1fc.com`.

The extract does not establish whether CT-0011’s email is wrong or whether the contact is associated with the wrong company; verify before changing either value.

## Enrichment matches and disagreements

The enrichment export has a matching domain for 25 of 34 company records. Eight missing employee counts can be filled from matching rows:

| Company alias | CRM employee count | Enrichment employee count |
|---|---:|---:|
| C-EC3025 | Missing | 400 |
| C-96039F | Missing | 400 |
| C-44EA29 | Missing | 400 |
| C-D04904 | Missing | 400 |
| C-B23205 | Missing | 400 |
| C-60C75F | Missing | 400 |
| C-7BBDFA | Missing | 400 |
| C-50D386 | Missing | 400 |

One employee count remains missing without a matching enrichment row: C-93C8BF. Do not fill it from this export.

No missing HQ-country value can be filled: the matching enrichment rows for C-2D1F1B, C-D73B89, C-44EA29, C-D04904, and C-2C60E5 also have no HQ country. C-EE9FFB has no matching enrichment row.

Industry disagreements where both sources have a value:

| Company alias | CRM industry | Enrichment industry | Recommendation |
|---|---|---|---|
| C-66D1FC | tech | Computer Software | Prefer enrichment if the CRM field is intended to use the enrichment taxonomy; otherwise map both to an agreed CRM category. |
| C-EC3025 | Technology | Computer Software | Same |
| C-44EA29 | tech | Computer Software | Same |
| C-92D97D | Technology | Computer Software | Same |
| C-D04904 | Technology | Computer Software | Same |
| C-77A95A | Technology | Computer Software | Same |
| C-AA8DDA | Technology | Computer Software | Same |
| C-B25F40 | Technology | Computer Software | Same |
| C-60C75F | tech | Computer Software | Same |
| C-425E2A | Tech  | Computer Software | Same |

The export’s country values are consistent with CRM values where both are populated, allowing for variants such as “US,” “USA,” and “United States.” Those are formatting variants, not evidence of a country disagreement.

## Ten proposed fixes with pipeline amount at stake

The extract contains no deals, deal-to-company/contact links, or deal amounts. Therefore, I cannot identify or rank fixes by pipeline amount at stake, or attach a dollar value to any of these. These are ten actionable data-quality fixes from the supplied records, not a pipeline-ranked list:

1. Fill C-EC3025 employee count with 400 from its matching enrichment row.
2. Fill C-96039F employee count with 400 from its matching enrichment row.
3. Fill C-44EA29 employee count with 400 from its matching enrichment row.
4. Fill C-D04904 employee count with 400 from its matching enrichment row.
5. Fill C-B23205 employee count with 400 from its matching enrichment row.
6. Fill C-60C75F employee count with 400 from its matching enrichment row.
7. Fill C-7BBDFA employee count with 400 from its matching enrichment row.
8. Fill C-50D386 employee count with 400 from its matching enrichment row.
9. Correct or verify CT-0011’s company association/email-domain mismatch.
10. Verify and correct the invalid email addresses for CT-0010, CT-0080, CT-0081, and CT-0192.
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 $0.0173 · 165s · in 71,215 / out 19,059 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
Classifications

B = Bonusly; Buyer = buyer; Unknown = side not established by the text. I used the free-text reason to identify the primary cause; a competitor selection and its stated rationale can coexist.

Pricing — 5
- Buyer: Deal-7ED004, Deal-7B2236, Deal-C33D91, Deal-DAFB82, Deal-8A119B

Competitor — 21
- Buyer: Deal-F7F635, Deal-F97C37, Deal-422BA6, Deal-F1E8A6, Deal-ACE061, Deal-2D2F8D, Deal-0F96AA, Deal-1BCA50, Deal-A2C349, Deal-C7156E, Deal-8A0992, Deal-D0C698, Deal-EECC02, Deal-47F1A1, Deal-BF2A98, Deal-1E7DA9, Deal-286F9C, Deal-369281, Deal-9FCD0D, Deal-64B19A
- Unknown: Deal-381C8C

No decision — 31
- Buyer: Deal-13E9CF, Deal-E74A73, Deal-8E27DA, Deal-FAC17C, Deal-413C56, Deal-2A292B, Deal-7FBAC6, Deal-F325A5
- Unknown: Deal-AC944F, Deal-214060, Deal-21B045, Deal-988493, Deal-F308CA, Deal-4664E1, Deal-D48E0B, Deal-583ADB, Deal-E0441F, Deal-7CB44D, Deal-AFA56C, Deal-D1AABF, Deal-2BBA21, Deal-386F6E, Deal-55867E, Deal-3F86A0, Deal-096750, Deal-79E61A, Deal-AE7C4E, Deal-DAB4F1, Deal-B4B50F, Deal-5885B9

Timing — 22
- Buyer: Deal-DB0AAC, Deal-91A056, Deal-29326C, Deal-831B7B, Deal-39E25C, Deal-B3ABED, Deal-B6AC09, Deal-E6E80A, Deal-B038F0, Deal-175756, Deal-BB78F3, Deal-15DA99, Deal-F4AF5D, Deal-79B7A1, Deal-50E5D8, Deal-9F176A, Deal-5E64CE, Deal-69CF3D, Deal-ECBF89, Deal-D1A623, Deal-FEDBCB, Deal-2FEDDB

Product gap — 6
- Bonusly: Deal-242273, Deal-9048EB, Deal-3618CC, Deal-5AD03E, Deal-981AD4, Deal-DC77FE

Champion left — 0
- No supplied reason explicitly says a buyer-side champion left.

Other — 5
- Unknown: Deal-5DB9B0, Deal-ED9AE7, Deal-7CC678, Deal-ABD14C, Deal-381C8C

Counts and side split

Category counts: pricing 5 + competitor 21 + no decision 31 + timing 22 + product gap 6 + champion left 0 + other 5 = 90 deals.

Side split: buyer 56, unknown 28, Bonusly 6; 56 + 28 + 6 = 90.

Clear tag/free-text disagreements: 0 under a strict direct-contradiction standard. Some tags are broad or the text adds detail—such as Deal-59086317965 (Deal-9048EB)—but the text does not directly contradict the tag. Deal-60008683142 (Deal-47F1A1) says they are staying with WorkTango for another 12 months; that is consistent with a competitor outcome, even though it also indicates timing.

Two patterns most worth acting on

1. Timing and no-decision losses dominate: 22 + 31 = 53 of 90 deals. Prioritize a consistent revisit process for stated pauses, future dates, and internal-priority delays.
2. Competitor losses total 21; the text includes differentiation around capabilities, breadth, and integrations. Review those stated buyer needs against the product gaps identified in the six product-gap losses.
pipeline-tiering0.40
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 $0.0237 · 192s · in 154,184 / out 10,721 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":null,"ACTION":null,"BUILD":null,"REVIVE":null,"WATCH":null,"RISKY":null},"tier_examples":{"LOCK":[],"ACTION":[],"BUILD":[],"REVIVE":[],"WATCH":[],"RISKY":[]},"risky_deals":[],"lock_violations":null,"pipeline_shape":"The files provide the requested signals, but no rule defines how to combine them into six tiers or when forecast and engagement disagree. Exact counts, examples, and lock violations would require inventing scoring thresholds."}
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 $0.0067 · 33s · in 15,893 / out 4,896 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
[
  {
    "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": [
      "The HR team of three cannot keep up with anniversary and birthday awards manually.",
      "Recognition is tracked in a spreadsheet, and people slip through the cracks."
    ],
    "stakeholders": [
      "Prospect (VP People)",
      "Prospect (HR Admin)"
    ],
    "budget_signal": "“We have about $40k earmarked for engagement tools this fiscal year.”",
    "timeline_signal": "“Ideally we would have this live before open enrollment in November.”",
    "competitor_mentioned": "Achievers — “We looked at Achievers last year, but it was too heavy for a team our size.”",
    "next_step": "Security review agreed for September 12.",
    "objections": [
      "Needs SSO and audit logs for IT sign-off."
    ],
    "confidence": "High — the prospect explicitly stated the use case, budget, timing, competitor experience, concern, and agreed next step."
  },
  {
    "transcript_id": "TX-002",
    "deal_alias": "Deal-70BB30",
    "why-buys": [
      "“We want to tie recognition to retention for our hourly workforce — regretted turnover there is over 30%.”"
    ],
    "pain_points": [
      "Regretted turnover among the hourly workforce is over 30%."
    ],
    "stakeholders": [
      "Prospect (Head of Total Rewards)",
      "Prospect (CFO)"
    ],
    "budget_signal": "“Finance has approved a $25k pilot budget for this quarter.”",
    "timeline_signal": "“We want a decision by end of September.”",
    "competitor_mentioned": null,
    "next_step": "Send the pilot agreement; the prospect will route it to legal this week.",
    "objections": [
      "Workday integration must be “rock solid” — stated as the CFO’s “one condition.”"
    ],
    "confidence": "High — the prospect explicitly stated the business goal, budget, decision timing, condition, and next step."
  },
  {
    "transcript_id": "TX-003",
    "deal_alias": "Deal-530B50",
    "why-buys": [
      "“We need to make recognition visible across our 12 retail locations.”"
    ],
    "pain_points": [
      "Store managers have zero budget autonomy for on-the-spot recognition."
    ],
    "stakeholders": [
      "Prospect (People Ops Manager)"
    ],
    "budget_signal": null,
    "timeline_signal": "“Honestly there's no rush on our side until Q1.”",
    "competitor_mentioned": "Bucketlist — the prospect said the CEO used it at her last company and liked it.",
    "next_step": "Schedule a call with the CEO; the prospect will send two times.",
    "objections": [
      "The CEO has to be sold first because she decides anything people-related."
    ],
    "confidence": "High — the prospect explicitly stated the need, timing, decision-maker hurdle, competitor reference, and agreed next step."
  },
  {
    "transcript_id": "TX-004",
    "deal_alias": "Deal-180D02",
    "why-buys": [
      "“We want to consolidate three separate recognition tools into one.”"
    ],
    "pain_points": [
      "They are paying for three recognition tools.",
      "The tools do not connect to their HRIS."
    ],
    "stakeholders": [
      "Prospect (VP People)",
      "Prospect (IT Security Lead)"
    ],
    "budget_signal": "“If it's under $15k annually, I can approve it without going to the board.”",
    "timeline_signal": "“Our procurement cycle runs six to eight weeks minimum.” The IT Security Lead also said the security review took three months for their last vendor.",
    "competitor_mentioned": null,
    "next_step": null,
    "objections": [
      "The IT Security Lead cited the prior vendor's three-month security review as a hesitation.",
      "A follow-up with the CFO was not confirmed: “Maybe — I need to check her calendar, no promises.”"
    ],
    "confidence": "High — the prospect explicitly stated the consolidation need, approval threshold, procurement timing, and security concern; no follow-up was agreed."
  },
  {
    "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": [
      "Night-shift teams feel invisible.",
      "Night-shift teams' engagement scores run 20 points lower."
    ],
    "stakeholders": [
      "Prospect (HR Director)",
      "Prospect (People Ops Coordinator)"
    ],
    "budget_signal": "“We have $12k approved under our engagement line.”",
    "timeline_signal": "“We need this running before our January all-hands.”",
    "competitor_mentioned": "Nectar — “We're mid-pilot with Nectar right now, so you'd need to beat that experience.”",
    "next_step": "Present to the exec team on October 2.",
    "objections": [
      "The exec team is skeptical after a failed rollout two years ago.",
      "The prospect said the experience would need to beat the current Nectar pilot."
    ],
    "confidence": "High — the prospect explicitly stated the use cases, pain, budget, timing, competitor, concerns, and agreed next step."
  },
  {
    "transcript_id": "TX-006",
    "deal_alias": "Deal-EE195F",
    "why-buys": [
      "“I'd love to cut the admin time on service awards.”"
    ],
    "pain_points": [
      "The HR Manager personally spends five hours a month ordering and shipping plaques."
    ],
    "stakeholders": [
      "Prospect (HR Manager)"
    ],
    "budget_signal": "“Budget isn't the issue — time is.”",
    "timeline_signal": "“Our fiscal year resets in February, so a Q1 start is realistic.”",
    "competitor_mentioned": "Doing it internally — the prospect said they are comparing the option with “just doing it internally.”",
    "next_step": "Send the one-page overview; the prospect will forward it to the COO this week.",
    "objections": [
      "The COO usually prefers building things in-house."
    ],
    "confidence": "High — the prospect explicitly stated the pain, budget position, timing, alternative, objection, and agreed next step."
  }
]
next-to-close0.75
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 $0.0040 · 12s · in 11,338 / out 624 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
1. Deal-547B2B — $11,200. Clean redlines; signing page is out, and the VP People said they’ll sign tomorrow. Left: signature.

2. Deal-403845 — $9,000. Order form is with their finance team. Left: finance review; Slack gives no confirmation of approval or signature.

3. Deal-A2B47C — $6,360. Slack says it’s still warm and at a normal legal-review pace; CRM lists DS5/COMMIT with a 2026-09-11 close date. Left: legal review. Slack gives the same status for Deal-D348E1, so the CRM’s earlier close date distinguishes this pick.

Deal-2465CE is not included: despite CRM COMMIT, Slack says it’s blocked by a procurement freeze and lost champion.
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 $0.0061 · 24s · in 22,041 / out 2,026 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
## Real product gaps

- Deal-EC3025 — Prospect: “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.”  
  Classification: Real gap. Product docs do not list SCIM user provisioning as supported.  
  Amount: Not provided.

- Deal-D0D6B5 — Prospect: “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. Product docs do not list ADP Workforce Now as a supported integration.  
  Amount: Not provided.

## Other prospect-raised candidates

- Deal-CFE7F4 — Prospect: “I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?”  
  Classification: Plan gate. The custom report builder is Enterprise-only.  
  Amount: Not provided.

- Deal-84DBA6 — Prospect: “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.”  
  Classification: Rollout/enablement issue. Slack integration is supported on all plans; the prospect identifies lack of manager training.  
  Amount: Not provided.

TG-005 is excluded: the mobile-app limitation is stated by the rep, and the prospect says the web version should be fine for now. No deal amounts were provided, so deal values or totals cannot be calculated.
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 $0.0463 · 285s · in 177,168 / out 37,603 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
Snapshot: 2026-09-05. Stale means the latest of last_email, last_call, and last_meeting was more than 7 days before the snapshot. Days are calculated as 2026-09-05 minus that latest date; for example, 2026-08-28 is 8 days ago. Amount totals are the sums of the listed deal amounts; no currency was specified.

Alex Franklin — 19 stale deals; total amount: 112,856
| Deal alias | Stage | Amount | Days since last contact |
|---|---:|---:|---:|
| Deal-CC08D1 | DS1 | 24,000 | 16 |
| Deal-E73427 | DS3 | 18,000 | 10 |
| Deal-885F45 | DS2 | 9,300 | 12 |
| Deal-C2FF3C | DS1 | 8,316 | 10 |
| Deal-0D2F7A | DS3 | 5,100 | 12 |
| Deal-6C60D4 | DS3 | 4,800 | 12 |
| Deal-13FEBD | DS2 | 4,680 | 12 |
| Deal-819506 | DS1 | 4,400 | 8 |
| Deal-9D0060 | DS3 | 3,840 | 12 |
| Deal-690476 | DS2 | 3,600 | 18 |
| Deal-C6D97A | DS4 | 3,240 | 8 |
| Deal-EE195F | DS3 | 3,120 | 8 |
| Deal-278DEC | DS3 | 2,700 | 8 |
| Deal-635B8E | DS3 | 2,600 | 18 |
| Deal-6883F3 | DS1 | 2,400 | 16 |
| Deal-4A13AD | DS3 | 2,160 | 26 |
| Deal-F67D31 | DS2 | 1,800 | 8 |
| Deal-5FDCE4 | DS3 | 1,600 | 12 |

Bryce Harmon — 19 stale deals; total amount: 694,044
| Deal alias | Stage | Amount | Days since last contact |
|---|---:|---:|---:|
| Deal-2D1F1B | DS1 | 240,000 | 81 |
| Deal-66D1FC | DS1 | 99,000 | 16 |
| Deal-950043 | DS1 | 70,000 | 19 |
| Deal-B23205 | DS1 | 45,000 | 16 |
| Deal-7BBDFA | DS3 | 37,440 | 46 |
| Deal-332637 | DS2 | 36,000 | 9 |
| Deal-1BEEBF | DS1 | 31,500 | 19 |
| Deal-A414F6 | DS1 | 25,200 | 19 |
| Deal-C5658B | DS1 | 23,400 | 16 |
| Deal-40522D | DS3 | 21,000 | 19 |
| Deal-C1FA6D | DS1 | 18,000 | 16 |
| Deal-01E193 | DS1 | 12,600 | 8 |
| Deal-F0EBBB | DS3 | 11,400 | 24 |
| Deal-927338 | DS1 | 10,920 | 18 |
| Deal-E25A09 | DS1 | 6,000 | 9 |
| Deal-C9C286 | DS2 | 5,502 | 9 |
| Deal-BA571A | DS4 | 1,080 | 18 |
| Deal-012CB1 | DS1 | 1 | 23 |
| Deal-3795AD | DS2 | 1 | 8 |

Cole Ingram — 18 stale deals; total amount: 252,905.03
| Deal alias | Stage | Amount | Days since last contact |
|---|---:|---:|---:|
| Deal-D04904 | DS2 | 58,529.25 | 11 |
| Deal-B25F40 | DS3 | 40,000 | 8 |
| Deal-813836 | DS2 | 32,175 | 11 |
| Deal-1BA595 | DS2 | 31,750 | 11 |
| Deal-CFE1E8 | DS3 | 18,000 | 11 |
| Deal-CD47A6 | DS2 | 12,168 | 11 |
| Deal-627646 | DS3 | 11,193 | 11 |
| Deal-FF809F | DS2 | 7,781.2 | 11 |
| Deal-AF932D | DS2 | 7,225.4 | 11 |
| Deal-A71728 | DS2 | 6,947.5 | 11 |
| Deal-8BC9F5 | DS2 | 5,616 | 10 |
| Deal-175395 | DS3 | 4,779.88 | 11 |
| Deal-481E24 | DS3 | 4,140 | 10 |
| Deal-C7F9BF | DS2 | 3,360 | 11 |
| Deal-2F3A66 | DS3 | 3,334.8 | 11 |
| Deal-342E96 | DS2 | 2,700 | 24 |
| Deal-E568D5 | DS3 | 1,875 | 11 |
| Deal-FD9F4E | DS5 | 1,330 | 10 |

Dana Mercer — 16 stale deals; total amount: 279,495
| Deal alias | Stage | Amount | Days since last contact |
|---|---:|---:|---:|
| Deal-44EA29 | DS2 | 60,000 | 10 |
| Deal-E51FB7 | DS2 | 43,875 | 12 |
| Deal-B42F46 | DS1 | 27,000 | 19 |
| Deal-BA3DDC | DS3 | 23,400 | 15 |
| Deal-9DDE86 | DS2 | 20,000 | 15 |
| Deal-215CCA | DS3 | 18,900 | 17 |
| Deal-5EED42 | DS3 | 16,250 | 11 |
| Deal-57887A | DS2 | 15,000 | 8 |
| Deal-944310 | DS4 | 10,500 | 33 |
| Deal-3974EB | DS4 | 9,000 | 8 |
| Deal-B7EBD1 | DS5 | 9,000 | 16 |
| Deal-F40F04 | DS2 | 8,100 | 15 |
| Deal-7599B8 | DS3 | 7,350 | 18 |
| Deal-87DDD1 | DS1 | 5,000 | 19 |
| Deal-F336B6 | DS3 | 4,200 | 15 |
| Deal-0660B4 | DS4 | 1,920 | 16 |

Elena Sinclair — 1 stale deal; total amount: 2,100
| Deal alias | Stage | Amount | Days since last contact |
|---|---:|---:|---:|
| Deal-57FF13 | DS1 | 2,100 | N/A |

Farid Osman — 3 stale deals; total amount: 2,882
| Deal alias | Stage | Amount | Days since last contact |
|---|---:|---:|---:|
| Deal-8BA24E | DS1 | 2,880 | 8 |
| Deal-03BA69 | DS1 | 1 | 11 |
| Deal-8FDCD2 | DS1 | 1 | 15 |

Data gaps: Deal-3EED2C (Alex Franklin, 7,200) and Deal-57FF13 (Elena Sinclair, 2,100) have no matching row in the engagements-by-deal table. Deal-57FF13 is shown above because it was the only open deal for Elena Sinclair, but its recency is unknown; neither missing row provides evidence to determine whether the deal had an email, call, or meeting in the last 7 days.
activity-mix-vs-outcome0.20
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 $0.0175 · 79s · in 122,602 / out 6,356 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
I can’t validly rank the reps for the 2026-09-05 snapshot: the engagement rows include activity dates after the snapshot—for example, Deal-60083610979 has a last_meeting of 2026-09-22, and Deal-62044573757 has a last_meeting of 2026-09-15. The emails_30d, calls_30d, and meetings_30d fields aren’t dated to show they reflect the 30 days ending 2026-09-05. Using them would mix periods, so the per-rep totals, activity mix, and efficiency ranking aren’t supported by this data.
ae-qtd-scorecardPASS 1.00
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 $0.0378 · 201s · in 145,699 / out 29,504 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 — Alex Franklin
As of 2026-09-05

Bookings vs. quota
- Bookings: 150,000 across 8 wins; quota: 200,000.
- Attainment: 150,000 ÷ 200,000 = 75%; 50,000 remains.
- New: 113,500 across 5 wins (113,500 ÷ 150,000 = 75.7%).
- Expansion: 36,500 across 3 wins (36,500 ÷ 150,000 = 24.3%).
- Excluded the pre-quarter win Deal-B3E6F1 (24,000; closed 2026-06-20).

Active pipeline by stage

| Stage | Deals | Amount |
|---|---:|---:|
| DS1 | 20 | 284,621 |
| DS2 | 28 | 353,760 |
| DS3 | 67 | 552,705 |
| DS4 | 5 | 23,574 |
| DS5 | 5 | 45,730 |
| Total | 125 | 1,260,390 |

Rolling 90-day DS2-to-won
- Cohort: deals entered DS2 from 2026-06-07 through 2026-09-05, inclusive.
- Won: 8 of 111 cohort deals; rate = 8 ÷ 111 = 7.2%.
- Cohort status: 8 won + 27 lost + 76 still open = 111.

QTD wins and losses
- Wins: 8.
- Losses: 27.
- Top recorded loss reason: “Lost- Timing (1 year or more)” on 13 of 27 losses; 13 ÷ 27 = 48.1%.

Last-30-day activity
Summed across the 161 deal-linked engagement rows provided:
- Emails: 807
- Calls: 112
- Meetings: 128
- Notes: 50

Coaching observations
1. Bookings are 75% of quota, leaving 50,000 to reach target.
2. DS3 holds 552,705 of 1,260,390 in active pipeline; DS1 and DS2 together hold 638,381 (284,621 + 353,760), so a substantial portion remains in earlier stages.
3. Timing is the most frequently recorded loss reason (13 of 27). The DS2-to-won rate is 7.2% on the full 111-deal cohort, including 76 still open.
multithreading-gap0.75
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 $0.0101 · 67s · in 32,296 / out 7,526 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
The files do not include deal amount, stage, or open/closed status. The list below flags qualifying deals in `deal_contacts.csv`, assuming they are open. Active contacts are non-former and engaged on or after 2026-07-26 (60 days before 2026-09-24). Stage-specific persona priority cannot be determined without stage data.

- Deal-EC3025 — Amount/stage: not provided. Active contacts: 1. Personas present: champion. Missing: economic buyer, HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-6827DB (Chief People Officer, economic buyer).
- Deal-92D97D — Amount/stage: not provided. Active contacts: 1. Personas present: HR admin. Missing: economic buyer, champion, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: none.
- Deal-50D386 — Amount/stage: not provided. Active contacts: 2. Personas present: champion, HR admin. Missing: economic buyer, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-A1C4B3 (Chief People Officer, economic buyer).
- Deal-D0D6B5 — Amount/stage: not provided. Active contacts: 3. Personas present: champion. Missing: economic buyer, HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-1FA4DB (Chief People Officer, economic buyer).
- Deal-5BFE3B — Amount/stage: not provided. Active contacts: 2. Personas present: champion. Missing: economic buyer, HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: none.
- Deal-36C33F — Amount/stage: not provided. Active contacts: 1. Personas present: IT security. Missing: economic buyer, champion, HR admin, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-1DB73E (Chief People Officer, economic buyer).
- Deal-885F45 — Amount/stage: not provided. Active contacts: 2. Personas present: economic buyer, champion. Missing: HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-B3F25D (IT Security Lead, IT security).
- Deal-FCBE5B — Amount/stage: not provided. Active contacts: 1. Personas present: champion. Missing: economic buyer, HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: none.
- Deal-5408B0 — Amount/stage: not provided. Active contacts: 2. Personas present: champion, HR admin. Missing: economic buyer, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-07FA76 (Chief People Officer, economic buyer).
- Deal-C6D97A — Amount/stage: not provided. Active contacts: 3. Personas present: champion. Missing: economic buyer, HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: none.
- Deal-F9A08A — Amount/stage: not provided. Active contacts: 1. Personas present: champion. Missing: economic buyer, HR admin, IT security, finance. Most valuable persona to add given stage: cannot determine; stage not provided. Unengaged contact on file: CT-697541 (Chief People Officer, economic buyer).

Arithmetic: Deal-D0D6B5 and Deal-C6D97A have 3 active contacts but only 1 persona, so they qualify as single-persona deals. All other flagged deals have fewer than 3 active contacts.
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 $0.0079 · 55s · in 48,769 / out 4,885 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
First five minutes: Alex Franklin led with a customer proof point in 8/10 calls (80%); the other two opened with an agenda or straight pricing. In the repeated proof-point opening, Alex cited a retailer’s turnover reduction after automating milestone awards.

Three most common objections and responses:
- Budget (4 calls): In three budget-objection calls, Alex countered with turnover-savings rationale. Quote: “Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off.” (TT-001)
- Timing (3 calls): Alex proposed a limited pilot to build internal data ahead of next-quarter planning. Quote: “Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?” (TT-002)
- Spreadsheet / gift-card status quo (3 calls): Alex argued that automation and analytics become more valuable as recognition scales. Quote: “Spreadsheets work until they scale — the difference is automation: milestones fire without HR lifting a finger, and you get analytics on who is being recognized.” (TT-004)

Concrete next step agreed: 7/10 calls = 70%. Counted calls where the prospect agreed to a specific working session; the other three did not produce an agreed next step.

Competitors prospects raised: Awardco (Deal-547B2B) and Kudos (Deal-EDC141). Workhuman was mentioned by Alex, not raised by a prospect.

Coaching notes:
1. The same proof-point opening recurs in 8/10 calls; tailor the opening to the prospect’s stated priorities where available.
2. When a prospect cannot commit, clarify the decision process and agree on a low-friction follow-up rather than ending without a next step.
reporting-analytics 5 tests
q3-weighted-forecastPASS 1.00
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 $0.0295 · 187s · in 118,791 / out 20,663 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
## Q3 2026 forecast

Only deals closing 2026-07-01 through 2026-09-30 are included.

- **COMMIT:** 7 deals; total amount **44,729**
- **BEST_CASE:** 24 deals; total amount **203,565**
- **PIPELINE:** 22 deals; contributes **0**
- **Weighted forecast:** **44,729 + (203,565 × 35%) = 44,729 + 71,247.75 = 115,976.75**

### Excluded: outside the quarter

**32 deals; total amount 227,575.** Excluded because their close dates fall after 2026-09-30:

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

### Top 5 BEST_CASE deals inside the quarter

1. Deal-2D7423 — 38,935
2. Deal-25F752 — 24,000
3. Deal-E53952 — 19,656
4. Deal-5EED42 — 16,250
5. Deal-FA32A0 — 11,116

## Data quality

Owner is blank for nearly all deals, limiting accountability and owner-level checks. `why_buys_chars` is 0 for most records, so buyer rationale appears largely absent. COMMIT appears at early stages, including DS1 and DS2, which may indicate stage/category inconsistencies. The extract includes an amount with a decimal (2,480.4), unlike the other listed amounts.
aha-moment-2x20.67
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 $0.0098 · 38s · in 70,709 / out 3,695 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
| First-month signals | Companies | Retained at 24 months | Retention rate |
|---|---:|---:|---:|
| Both (m1_users ≥ 5 and m1_redemptions ≥ 1) | 43 | 29 | 29 ÷ 43 = **67.4%** |
| Givers-only | 45 | 24 | 24 ÷ 45 = **53.3%** |
| Redemption-only | 23 | 9 | 9 ÷ 23 = **39.1%** |
| Neither | 81 | 33 | 33 ÷ 81 = **40.7%** |

**Excluded:** 0 companies. All 192 companies have a current_status value; non-active statuses count as not retained.

**Largest lift for a single signal:** Givers-only, compared with neither: 53.3% − 40.7% = **+12.6 percentage points**. Redemption-only versus neither: 39.1% − 40.7% = **−1.6 points**.

**What this shows:** In this cohort, the both-signals group had higher 24-month retention than each other group: 67.4% versus 53.3%, 39.1%, and 40.7%.

**What it does not prove:** This is an observed association, not evidence that the signals cause retention. The extract does not establish why groups differ or control for other factors.
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 $0.0116 · 75s · in 63,357 / out 8,437 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
As of 2026-09-05, using the subscription statuses provided and counting only `active` subscriptions for billing ARR:

- CRM company ARR: **$603,581.76** (sum of 39 company records)
- Billing ARR: **$604,739.28** (sum of 37 active subscriptions’ MRR × 12)
- Variance (billing − CRM): **+$1,157.52**

Variance decomposition:

- Status mismatch: **−$13,158.48** — CRM ARR remains on accounts whose subscriptions are marked `cancelled`.
- Rounding: **$0.00** — the provided data doesn’t establish rounding as the cause of any difference.
- Missing records: **+$11,952.00** — billing-only $28,449.24 less CRM-only $16,497.24.
- Other: **+$2,364.00** — unexplained active-account differences: +$2,400.00, −$16.00, and −$20.00.
- Check: **−$13,158.48 + $0.00 + $11,952.00 + $2,364.00 = +$1,157.52**

Mismatched accounts (variance = billing − CRM):

| Company alias | Billing ARR | CRM ARR | Variance | Bucket | Suggested owner |
|---|---:|---:|---:|---|---|
| C-0C8323BF | $0.00 | $4,905.24 | −$4,905.24 | Status mismatch | CRM Ops; verify CRM ARR against cancelled subscription |
| C-0DC4FB8C | $0.00 | $8,253.24 | −$8,253.24 | Status mismatch | CRM Ops; verify CRM ARR against cancelled subscription |
| C-0D5BBE3A | $0.00 | $16,497.24 | −$16,497.24 | Missing record | CRM Ops; verify missing billing subscription or CRM ARR |
| C-21629AA4 | $28,449.24 | $0.00 | +$28,449.24 | Missing record | CRM Ops; verify missing CRM company record |
| C-0D66DF9E | $23,184.00 | $23,200.00 | −$16.00 | Other | RevOps; reconcile ARR values |
| C-14D70CE0 | $18,180.00 | $18,200.00 | −$20.00 | Other | RevOps; reconcile ARR values |
| C-0F7269D7 | $26,796.00 | $24,396.00 | +$2,400.00 | Other | RevOps; reconcile ARR values |

No individual owner names were provided, so suggested owners are functional roles.

Agreement-date violations (term is not 12 months and `cf_agreement_end_date` is blank):

- `SUB-0002` — `C-1794A52C`, 24 months
- `SUB-0019` — `C-22170CA1`, 36 months
kvm-month-over-monthPASS 1.00
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 $0.0136 · 67s · in 44,063 / out 9,124 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
Equal-weighted company averages across the 30 aliases. Absolute changes are percentage points (pp) for engagement rates and giving rate; relative change = (August − July) ÷ July.

| KVM | 2026-08 | 2026-07 | Absolute change | Relative change | Direction |
|---|---:|---:|---:|---:|---|
| Giving rate | 60.2713% | 60.2297% | +0.0417 pp | +0.07% | Up |
| Redemptions per user | 1.73016 | 1.72998 | +0.00018 | +0.01% | Up |
| 1:1 meetings engagement | 44.7177% | 44.6887% | +0.0290 pp | +0.06% | Up |
| Pulse check engagement | 50.8610% | 60.0587% | −9.1977 pp | −15.31% | Down |

Largest relative move: pulse check engagement. The `enterprise` size_band drove the decline: its average fell from 54.998% to 27.428% (−27.57 pp). The supplied data supports size_band as the driver; all records have `plan_tier` `tier_three`. Enterprise aliases: C-0B2895EF, C-0B2213A9, C-0D6CC8E3, C-0D0B047C, C-0D3278C7, C-0FCCD2DF, C-0F6C0F34, C-8C2E8F00, C-0B827671, C-0BA71F12.
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 $0.0343 · 151s · in 218,414 / out 7,460 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
Redemptions — through August 2026

Last completed month: August 2026

- Redemptions: 48
- Spend: $3,536.00
- Unique redeemers: 46
- Redemptions per redeemer: 48 ÷ 46 = 1.04
- Provider mix by spend:
  - TangoCard: 14.14%
  - Tremendous: 32.38%
  - custom: 29.89%
  - Snappy: 23.59%
  - Total: 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 $0.0121 · 69s · in 42,277 / out 8,870 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
Eligibility applied from the 2026-09-05 snapshot: health score <60, eligible amount >$0, and renewal within 120 days (through 2027-01-03). Eight accounts qualify.

| Account | Amount at stake | Play that fits | Supporting signal |
|---|---:|---|---|
| C-0F6C0F34 | $49,707 | Executive touch | Champion inactive. Usage is growing and 308/395 seats are used (78.0%), so usage revival is not the clearest signal. |
| C-0B827671 | $25,365 | Usage revival | Usage declining; 113/202 seats used (55.9%). |
| C-0B360C78 | $35,748 | No specific play supported by the provided signals | Usage growing, 246/327 seats used (75.2%), champion active. Health score is 57, but there’s no stated cause or recovery signal to distinguish a play. |
| C-0B0F1BAB | $5,494 | Executive touch | Champion inactive. Usage is flat; 238/363 seats used (65.6%). |
| C-0CA21961 | $16,829 | Usage revival | Only 84/325 seats used (25.8%); usage is flat. |
| C-0E9C27D1 | $41,235 | No specific play supported by the provided signals | Renewal is 19 days away; champion is active and 134/157 seats are used (85.4%). Usage is flat, but the data doesn’t identify a cause or a recovery play. |
| C-0CEF69FD | $32,621 | Executive touch | Champion inactive. Usage is growing; 97/136 seats used (71.3%). |
| C-0D3278C7 | $17,602 | Usage revival | Usage declining and only 126/380 seats are used (33.2%). |

Total at stake: $49,707 + $25,365 + $35,748 + $5,494 + $16,829 + $41,235 + $32,621 + $17,602 = **$224,601**.

**Commercial concession:** None is specifically supported by the supplied signals. The rules establish eligibility and an amount at stake, but provide no pricing objection, discount history, or other commercial signal to justify a concession. The same rules don’t define play-selection criteria, so the plays above are signal-based recommendations, not documented eligibility rules.

**At-risk but not eligible:**

- C-0BC71BDD — $0 eligible amount; renewal is 52 days away.
- C-0BA71F12 — $6,824 eligible amount, but renewal is 218 days away.
- C-0F6694C3 — $0 eligible amount; renewal is 197 days away.
- C-0BE96399 — $0 eligible amount; renewal is 54 days away.
- C-0F876796 — $19,958 eligible amount, but renewal is 154 days away.
- C-0FCCD2DF — $0 eligible amount; renewal is 230 days away.
- C-10A56B0F — $0 eligible amount; renewal is 98 days away.
expansion-kitPASS 1.00
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 $0.0091 · 51s · in 51,060 / out 4,199 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
Seat coverage: 150 licensed seats / 400 headcount = 37.5%; 250 headcount are beyond current licensed seats.

Usage health:
- Monthly active users rose from 88 in March to 126 in August: +38, or 43.2%.
- August activity was 126 / 150 = 84% of licensed seats, leaving 150 − 126 = 24 licensed seats unused.

Headroom at the current per-seat rate:
- Current rate: $9,000 ARR / 150 seats = $60 per seat per year.
- 250 additional seats to reach headcount; theoretical incremental ARR: 250 × $60 = $15,000/year. This assumes all headcount could be covered at the current rate.
- The 24 unused licensed seats are already within current ARR; they are not additional ARR headroom.

Reply and buying authority: Maria S., People Operations Coordinator, replied on September 2 and said she is not the purchasing decision-maker. She identified Dana R., VP People, as responsible for budget and seat expansion, and offered to introduce her.

Right buyer in provided contacts: Dana R., VP People (last engaged May 18, 2026).

Reply email (under 150 words):

Hi Maria,

Thanks for sharing this—and glad to hear the team is enjoying Bonusly. One useful data point: monthly active users increased from 88 in March to 126 in August.

Since you mentioned Dana handles budget and seat expansion and has been asking about usage, would you be comfortable introducing us? I can share the usage figures and discuss whether additional seats make sense for the team. No pressure if now isn’t the right time.

Best,
Cole
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 $0.0086 · 42s · in 56,069 / out 3,754 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
C-0D284E42 — mid-onboarding prep

Completed
- Slack integration: connected 2026-08-12.
- Allowance: set 2026-08-13.
- Admins: 2 added.
- First recognition: 2026-08-15 14:22.
- HRIS integration: not shown as connected.
- First redemption: not shown.

Early engagement
- Active givers rose from 3 on 2026-08-11 to 15 on 2026-09-04: +12, or +400% ((15−3)÷3).
- The 25 daily observations average 8.56 active givers. The last 7-day average was 13, versus 4.29 for the first 7 days.
- The series is not strictly increasing: active givers fell on some days, including 13 to 11 between 2026-08-30 and 2026-08-31.

Cover on the call
1. Confirm whether HRIS integration is needed and, if so, what remains to connect it.
2. Check whether any redemptions have occurred; the provided field is blank. If not, identify and address any blocker.
3. Review the rise in active givers and agree on the next engagement milestone; the data does not show total eligible users or a target, so adoption rate cannot be calculated.
renewal-risk-conflicting-dates0.75
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 $0.0190 · 122s · in 73,315 / out 14,026 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 — as of 2026-09-24

Scope: renewals dated 2026-09-25 through 2026-12-23, inclusive. For multi-year contracts, I use Chargebee’s date because you specified that ChurnZero’s multi-year renewal dates are known to be wrong. The three multi-year accounts with Chargebee dates before 2026-09-25 are outside this window; their date conflicts are listed below.

Risk method: High = seat utilization below 40% and declining usage; Medium = utilization below 60% or declining usage; Low = neither. “At risk” below means High or Medium. Usage trend is active users in June → July → August 2026; change compares August with June. Seat utilization = seats used ÷ seats.

| Company alias | CSM | ARR | Date used | Seat utilization | 3-month usage trend | Risk and evidence |
|---|---|---:|---|---:|---|---|
| C-0BBE3E60 | Dana Mercer | $30,993 | 2026-09-26 (Chargebee) | 74/114 = 64.9% | 39 → 35 → 33 (−6; −15.4%) | Medium — usage fell by 6 while utilization is 64.9%. |
| C-0F5D2323 | Cole Ingram | $90,647 | 2026-09-29 (Chargebee) | 111/390 = 28.5% | 20 → 21 → 18 (−2; −10.0%) | High — utilization is 28.5% and usage fell by 2. |
| C-0EC6999D | Elena Sinclair | $79,419 | 2026-10-03 (dates agree) | 31/112 = 27.7% | 17 → 16 → 15 (−2; −11.8%) | High — utilization is 27.7% and usage fell by 2. |
| C-0B20DB64 | Dana Mercer | $21,770 | 2026-10-07 (dates agree) | 214/378 = 56.6% | 294 → 298 → 294 (0; 0.0%) | Medium — seat utilization is below 60%. |
| C-0BBC4E7A | Cole Ingram | $56,374 | 2026-10-10 (dates agree) | 228/337 = 67.7% | 142 → 141 → 139 (−3; −2.1%) | Medium — usage fell by 3 over the three months. |
| C-0FD551AB | Elena Sinclair | $48,815 | 2026-10-14 (dates agree) | 210/376 = 55.9% | 123 → 122 → 126 (+3; +2.4%) | Medium — seat utilization is below 60%. |
| C-0F9F8F13 | Dana Mercer | $46,230 | 2026-10-18 (dates agree) | 199/352 = 56.5% | 185 → 185 → 182 (−3; −1.6%) | Medium — utilization is below 60% and usage declined. |
| C-0BC34584 | Cole Ingram | $16,740 | 2026-10-22 (dates agree) | 327/494 = 66.2% | 104 → 104 → 106 (+2; +1.9%) | Low — utilization is at least 60% and usage increased. |
| C-0B7A7546 | Elena Sinclair | $35,062 | 2026-10-25 (dates agree) | 182/205 = 88.8% | 64 → 65 → 63 (−1; −1.6%) | Medium — usage fell by 1 over the three months. |
| C-0B369871 | Dana Mercer | $85,128 | 2026-10-29 (dates agree) | 317/422 = 75.1% | 326 → 330 → 333 (+7; +2.1%) | Low — utilization is at least 60% and usage increased. |
| C-0B144C78 | Cole Ingram | $30,899 | 2026-11-02 (dates agree) | 169/224 = 75.4% | 101 → 101 → 106 (+5; +5.0%) | Low — utilization is at least 60% and usage increased. |
| C-0FC4DBB8 | Elena Sinclair | $94,732 | 2026-11-05 (dates agree) | 356/464 = 76.7% | 189 → 191 → 193 (+4; +2.1%) | Low — utilization is at least 60% and usage increased. |
| C-0D5BBE3A | Dana Mercer | $39,740 | 2026-11-09 (dates agree) | 85/102 = 83.3% | 88 → 90 → 91 (+3; +3.4%) | Low — utilization is at least 60% and usage increased. |
| C-0FB9D5AF | Cole Ingram | $63,158 | 2026-11-13 (dates agree) | 144/199 = 72.4% | 173 → 173 → 176 (+3; +1.7%) | Low — utilization is at least 60% and usage increased. |
| C-0B344485 | Elena Sinclair | $64,384 | 2026-11-16 (dates agree) | 224/287 = 78.0% | 238 → 240 → 244 (+6; +2.5%) | Low — utilization is at least 60% and usage increased. |
| C-0CB2C1B4 | Dana Mercer | $40,628 | 2026-11-20 (dates agree) | 386/473 = 81.6% | 47 → 48 → 49 (+2; +4.3%) | Low — utilization is at least 60% and usage increased. |
| C-22170CA1 | Cole Ingram | $45,646 | 2026-11-24 (dates agree) | 251/294 = 85.4% | 143 → 148 → 146 (+3; +2.1%) | Low — utilization is at least 60% and August usage remains above June. |

Date disagreements — all are multi-year contracts, so Chargebee is the selected source; each Chargebee date is before the 90-day window:

- C-0B7D2C30: ChurnZero 2026-09-10 vs Chargebee 2026-09-15; use Chargebee.
- C-0BCDB8C2: ChurnZero 2027-09-18 vs Chargebee 2026-09-18; use Chargebee.
- C-0D2AB865: ChurnZero 2026-09-10 vs Chargebee 2026-09-22; use Chargebee.
- C-0BBE3E60: ChurnZero 2027-09-26 vs Chargebee 2026-09-26; use Chargebee.
- C-0F5D2323: ChurnZero 2026-09-10 vs Chargebee 2026-09-29; use Chargebee.

Summary: 17 accounts renew within the window. Total ARR renewing: $890,365. High risk: $170,066; Medium risk: $239,244; Low risk: $481,055. ARR at risk = High + Medium = $170,066 + $239,244 = $409,310.

Company names beyond the provided account aliases were not supplied. Risk ratings are based only on the provided seat and usage data; no renewal outcomes or other risk signals were provided.
ticket-theme-synthesis0.80
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 $0.0106 · 74s · in 33,367 / out 7,559 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
**ARR exposure** below is the sum of each theme’s distinct affected accounts’ ARR, counted once per theme—not per ticket. It is an exposure proxy; ARR may overlap across themes. Shares use all 80 tickets as the denominator.

| Rank | Theme | Count / share | Distinct accounts | ARR affected | Two ticket IDs | Recommendation |
|---|---|---:|---|---:|---|---|
| 1 | HRIS provisioning failures — broad pattern | 12 / 15% (12 ÷ 80) | 3: C-0B2213A9, C-0F6C0F34, C-0DDFC9A7 | $114,000 ($36,000 + $30,000 + $48,000) | IC-460059, IC-460055 | Investigate provisioning and sync processing across affected HRIS integrations; add monitoring for skipped or uncreated accounts. |
| 2 | Redemption and gift-card failures — broad pattern | 18 / 22.5% (18 ÷ 80) | 7: C-0CEF69FD, C-0B827671, C-0FCCD2DF, C-0F876796, C-14264ABD, C-0D9CA315, C-0B0F1BAB | $68,800 ($8,900 + $10,700 + $9,600 + $8,700 + $11,000 + $9,600 + $10,300) | IC-460025, IC-460030 | Trace checkout-to-fulfillment failures and reconcile cases where points were deducted without a successful redemption. |
| 3 | Billing and invoice discrepancies — single-account concentration | 16 / 20% (16 ÷ 80) | 1: C-0E9C27D1 | $52,000 ($52,000) | IC-460071, IC-460069 | Review seat counts, tier pricing, and renewal calculations for this account; treat this as concentrated account exposure, not a broad pattern. |
| 4 | Recognition points not posting — broad pattern | 20 / 25% (20 ÷ 80) | 9: C-0D3278C7, C-0BF20542, C-0D0B047C, C-0BE96399, C-0D284E42, C-0D6CC8E3, C-21FEBCBB, C-0DD0626C, C-0B2895EF | $31,100 ($3,500 + $4,500 + $4,500 + $2,700 + $3,400 + $4,200 + $2,900 + $2,500 + $2,900) | IC-460004, IC-460016 | Investigate recognition-to-balance posting and team-wide delays; verify delivered recognitions reconcile to points credited. |
| 5 | Slack integration and command failures — broad pattern | 14 / 17.5% (14 ÷ 80) | 4: C-0B843542, C-10A56B0F, C-0BA71F12, C-8C2E8F00 | $18,900 ($4,400 + $5,400 + $3,900 + $5,200) | IC-460041, IC-460047 | Check Slack sync, authentication persistence, and slash-command errors as related integration reliability issues. |

The four multi-account themes are broad patterns. Billing is repeated but confined to C-0E9C27D1, so it is reported separately as a single-account concentration.
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 $0.0073 · 33s · in 23,679 / out 3,759 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
Using one point per matching field (industry, size band, use case, region), these three case-study customers tie at 3/4:

1. C-11C31562 — Industry: Manufacturing (different); size band: Mid-Market (match); use case: employee_recognition (match); region: NA-West (match). Arithmetic: 0 + 1 + 1 + 1 = 3/4.
2. C-64171065 — Industry: Technology (match); size band: Mid-Market (match); use case: employee_recognition (match); region: NA-East (different). Arithmetic: 1 + 1 + 1 + 0 = 3/4.
3. C-A13C193D — Industry: Technology (match); size band: Mid-Market (match); use case: retention (different); region: NA-West (match). Arithmetic: 1 + 1 + 0 + 1 = 3/4.

The provided fields do not distinguish among these tied matches.
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 $0.0151 · 85s · in 72,574 / out 11,753 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
Trailing six months: March–August 2026. I counted each contact with an SQO date as one SQO and summed its recorded pipeline amount. SQO-before-SQM rows are flagged below and remain included in these totals.

Paid performance

| Channel | Spend | SQMs | SQOs | Cost per SQM | Cost per SQO | SQM-to-SQO rate | Pipeline | Pipeline per $ |
|---|---:|---:|---:|---:|---:|---:|---:|---:|
| paid_search | $36,000 | 40 | 18 | $900 | $2,000 | 45.0% | $720,000 | $20.00 |
| linkedin_ads | $24,000 | 25 | 8 | $960 | $3,000 | 32.0% | $96,000 | $4.00 |
| paid_social | $18,000 | 0 | 0 | Undefined | Undefined | Undefined | $0 | $0.00 |
| webinars | $9,000 | 12 | 5 | $750 | $1,800 | 41.7% | $60,000 | $6.67 |
| Total paid | $87,000 | 77 | 31 | $1,129.87 | $2,806.45 | 40.3% | $876,000 | $10.07 |

Calculations:
- Spend: paid_search $6,000 × 6 = $36,000; linkedin_ads $4,000 × 6 = $24,000; paid_social $3,000 × 6 = $18,000; webinars $1,500 × 6 = $9,000.
- Cost per SQM = spend ÷ SQMs; cost per SQO = spend ÷ SQOs; SQM-to-SQO rate = SQOs ÷ SQMs; pipeline per dollar = pipeline ÷ spend.
- Total paid: $87,000 ÷ 77 = $1,129.87 per SQM; $87,000 ÷ 31 = $2,806.45 per SQO; 31 ÷ 77 = 40.3%; $876,000 ÷ $87,000 = $10.07 per dollar.
- paid_social spent $18,000 but has zero SQMs and SQOs, so cost per SQM and cost per SQO are undefined, not zero.

Organic and other non-paid

- organic_search: volume 30 SQMs; 10 SQOs; SQO rate 10 ÷ 30 = 33.3%; pipeline $90,000.
- referral, shown separately because it is listed as its own channel: volume 15 SQMs; 6 SQOs; SQO rate 6 ÷ 15 = 40.0%; pipeline $48,000.
- Combined organic_search + referral: 45 SQMs, 16 SQOs, rate 16 ÷ 45 = 35.6%, pipeline $138,000. No spend was supplied for these sources, so cost metrics and pipeline per dollar cannot be calculated.

Date-order flags

- CT-000044 (linkedin_ads): SQO date 2026-07-18 precedes SQM date 2026-07-23.
- CT-000041 (linkedin_ads): SQO date 2026-06-09 precedes SQM date 2026-06-14.

Recommendation: Reduce or pause paid_social pending attribution validation; it accounts for $18,000 of spend with no attributed SQMs in the supplied data. Consider shifting a limited test budget toward paid_search, which has the strongest observed pipeline per dollar ($20.00) and 18 SQOs. Preserve webinars for now, and investigate the two LinkedIn date-order exceptions before making a larger LinkedIn budget change.

Confidence: Low to moderate. paid_search has 18 SQOs, but webinars has 5, LinkedIn has 8 (including two date-order exceptions), and paid_social has none. These channel-level samples—and the six-month window—are limited; the figures support cautious testing, not a definitive long-term allocation.
competitor-battlecard-updatePASS 1.00
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 $0.0127 · 63s · in 40,076 / out 7,487 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
# Rivally battlecard

One-line positioning: Rivally offers points-based recognition with a lightweight engagement-survey add-on; reviewers praise its recognition feed but report limitations in analytics and admin tooling. [S02, S06, S16, S24]

Pricing (source and date):
- Latest listed price: Recognition Starter is $7 per user/month, with annual billing required, according to Rivally’s pricing page updated 2026-08-12. [S17]
- A prospect said Rivally quoted $7/user/month list and offered a 15% discount for a 3-year term on 2026-08-14. [S18] Applying that discount to the listed $7 gives $5.95/user/month ($7 × 0.85); that is arithmetic on a prospect-reported offer, not a confirmed generally available price. [S17, S18]
- Conflict: earlier pricing-page sources listed $5/user/month in January and still showed $5 for Recognition Starter in April; a June call note reported a $6.50/user/month quote to a 500-seat prospect. [S03, S08, S13] The newer August pricing-page source lists $7, so use $7 as the latest listed price; the deal-specific quotes do not establish a different current list price. [S13, S17]

Where they win:
- Ease of setup and Slack: a mid-market reviewer said setup took under a week and Slack worked out of the box. [S04]
- EU needs: a prospect mention says Rivally pitched EU data residency; a reviewer praised support for distributed EU teams and multiple languages; Rivally later announced EU data residency generally available. [S05, S12, S15]
- Recognition experience and support: reviewers praised its points-based/engaging recognition feed and one review praised support response time under four hours. [S02, S16, S22]

Where we win:
- Analytics depth is the clearest supplied win signal: an 800-seat prospect chose Bonusly over Rivally, citing analytics depth. [S25]
- Rivally’s analytics and admin limitations appear in reviewer feedback: limited analytics, basic dashboards, lagging admin tooling, and no bulk recognition editing. [S02, S07, S16, S24] These are reviewer reports, not independently verified product facts.

Objections and responses:
- “We need EU data residency or multilingual support.” Acknowledge that Rivally announced EU data residency generally available and has a reviewer signal praising multilingual support for distributed EU teams. [S12, S15] Confirm the buyer’s specific requirements; the supplied data does not establish Bonusly’s comparable capabilities.
- “Rivally has Slack integration.” That is consistent with a reviewer report that Slack worked out of the box; the existing card’s claim that Rivally lacks Slack integration is contradicted by this source. [S04]
- “Rivally’s analytics are enough for us.” Reviewers have reported limited analytics and basic dashboards, while one 800-seat prospect selected Bonusly citing analytics depth. [S02, S07, S25] Ask the buyer to validate the reports and export workflows they require; do not assume the review reports apply to their configuration.
- “Rivally is cheaper.” The latest supplied pricing-page source lists $7/user/month with annual billing; a prospect-reported 15% discount for a 3-year term would calculate to $5.95/user/month if applied to that list price. [S17, S18] Compare term, discount, and included scope rather than treating the prospect-reported offer as universal pricing.

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

Our 12-month win/loss record against Rivally:
- The supplied deals table contains 20 Rivally deals from 2025-09 through 2026-08: 13 wins and 7 losses. Win rate = 13 ÷ 20 = 65%; loss rate = 7 ÷ 20 = 35%. [deals_with_competitor.csv; no snippet IDs were provided for this table]
- Wins: Deal-A9FD43, Deal-7AA785, Deal-44C524, Deal-0D0CD6, Deal-D5B790, Deal-5C636E, Deal-67BE14, Deal-1B6969, Deal-F03E7B, Deal-072E31, Deal-F65C8F, Deal-E46EAB, Deal-1D2392. [deals_with_competitor.csv; no snippet IDs were provided for this table]
- Losses: Deal-7767F5, Deal-5645A5, Deal-C6FFAA, Deal-D263E0, Deal-935746, Deal-9066A6, Deal-72A02F. [deals_with_competitor.csv; no snippet IDs were provided for this table]
- The supplied deal table does not include reasons for these outcomes, except for the separate 800-seat prospect mention that cited analytics depth when choosing Bonusly. [deals_with_competitor.csv; S25]

Existing-card claims needing attention:
- “Rivally lacks a Slack integration” is contradicted by the reviewer report that Slack worked out of the box. [S04]
- “Rivally was acquired by WorkHuman in 2025” is unverified in the supplied snippets; no acquisition source was provided.
- “Points-based recognition for mid-market” is only partly supported: points-based recognition is mentioned in a reviewer report, and one reviewer describes a mid-market setup experience; the supplied data does not establish mid-market as Rivally’s overall positioning. [S02, S04]
- “Strong in EU enterprise with multi-language support” has reviewer support for EU teams and multiple languages, plus company-announced EU data residency; it is not independently established as a general enterprise strength. [S12, S15]
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 $0.0158 · 76s · in 70,724 / out 6,403 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
Rates use total step-level sends as the denominator: open = opened/sent; reply = replied/sent; meeting = meetings/sent. Totals are summed across steps, not unique contacts.

- New Logo Nurture — 1,386 sent; open 490/1,386 = 35.35%; reply 90/1,386 = 6.49%; meeting 27/1,386 = 1.95%. Weakest: step 3 (18/428 = 4.21% reply). Change: replace step 3 with a fresh value angle.
- Expansion Nurture — 875 sent; open 565/875 = 64.57%*; reply 59/875 = 6.74%; meeting 12/875 = 1.37%. Weakest: step 3 (12/275 = 4.36% reply). Change: replace step 3 with a new message rather than another follow-up.
- Cold Outbound - HR Leaders — 1,785 sent; open 545/1,785 = 30.53%; reply 8/1,785 = 0.45%; meeting 0/1,785 = 0%. Weakest: step 3 (1/590 = 0.17% reply). Change: rewrite step 1 around a specific HR-relevant value proposition and ask.
- Cold Outbound - People Ops — 1,163 sent; open 340/1,163 = 29.23%; reply 29/1,163 = 2.49%; meeting 6/1,163 = 0.52%. Weakest: step 3 (6/377 = 1.59% reply). Change: replace step 3 with a new angle.

*Tracking error: Expansion Nurture step 2 reports 340 opened from 300 sent (40 above sent); its 113.33% open rate is invalid.

Overlap: audiences.csv shows cross-sequence duplicate assignments, including CT-000301 and CT-000624 in New Logo Nurture and Expansion Nurture; and CT-000849, CT-001217, CT-001255, CT-001105, CT-001103, CT-000884, CT-001345, CT-001258, CT-001227, CT-001097, CT-001311, CT-001285, CT-000908, CT-001153, CT-001101, CT-001236, CT-001159, and CT-000890 in both Cold Outbound sequences.

Below 2%: Cold Outbound - HR Leaders is under 2% at every step; opens but replies fall from 5/600 to 1/590, suggesting a post-open relevance/message/CTA problem, not a proven cause. Cold Outbound - People Ops step 3 is 1.59%, consistent with diminishing returns late in sequence.

Fix Cold Outbound - HR Leaders first: lowest overall reply rate and zero meetings.
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 $0.0130 · 43s · in 51,998 / out 4,646 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
Q3-2026 has elapsed 66/92 days = 71.7% of the quarter. For count and pipeline targets, expected-to-date is target × 66/92; delta is actual − target. For closed-lost MIA rate, delta is actual rate − target, so positive is unfavorable.

| Metric | QTD actual | Target | Delta | Pace |
|---|---:|---:|---:|---|
| SQMs | 230 | 300 | −70 | Ahead: 230 vs. 215.2 expected to date |
| SQOs | 84 | 120 | −36 | Behind: 84 vs. 86.1 expected to date |
| DS2s | 40 | 75 | −35 | Behind: 40 vs. 53.8 expected to date |
| Closed-lost MIA rate | 5/25 = 20% | ≤10% | +10 percentage points | Behind target |
| Same-quarter closes | 10 | 20 | −10 | Behind: 10 vs. 14.3 expected to date |
| Active pipeline coverage | $3,000,000 / $4,000,000 = 75% | $4,000,000 | −$1,000,000 | Ahead: $3,000,000 vs. $2,869,565 expected to date |

Arithmetic: 66/92 = 71.7%; expected-to-date counts are 300×66/92 = 215.2 SQMs, 120×66/92 = 86.1 SQOs, 75×66/92 = 53.8 DS2s, and 20×66/92 = 14.3 same-quarter closes. MIA rate = 5/25 = 20%; 20%−10% = +10 percentage points. Pipeline coverage = $3,000,000/$4,000,000 = 75%; pipeline delta = $3,000,000−$4,000,000 = −$1,000,000; expected-to-date pipeline = $4,000,000×66/92 = $2,869,565.

Week-over-week movement cannot be determined from the provided data: it contains QTD totals but no prior-week snapshot or weekly changes. Current QTD, SQMs and active pipeline are ahead of prorated pace; SQOs, DS2s, and same-quarter closes are behind, while the closed-lost MIA rate is 10 percentage points above its target.
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 $0.0045 · 22s · in 11,634 / out 1,760 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 forecast: $115,976.75 = $44,729 COMMIT + 35% × $203,565 BEST_CASE ($71,247.75); PIPELINE = $0.  
32 deals totaling $227,575 close after Sep 30, including COMMIT Deal-D348E1 ($13,770, Oct 15); several October DS2/DS3 dates remain within four weeks of quarter-end.  
Treat the forecast as unverified: owners are blank on 85/86 deals, and why-buys are missing on 71/86, including all 7 in-quarter COMMIT deals, leaving no rep/quota rollup or documented rationale for the $44,729 COMMIT.
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 $0.0041 · 15s · in 10,612 / out 1,065 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
Subject: Following up on 150-seat pricing

Hi,

I’m following up on the recap I emailed on August 5 with pricing for 150 seats after our July 28 demo. Would you be open to reviewing the pricing together?

Best,  
Alex
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 $0.0103 · 28s · in 79,440 / out 1,749 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
Marketing: The team delivered 46 SQMs against a weekly target of 52, a gap of 6 (52 − 46 = 6). The webinar channel contributed 18 SQMs, while paid search held at $150 per SQM.

Sales: The team converted 14 SQOs, set 9 DS2 meetings, created $310,000 in new pipeline, and recorded 3 same-quarter closes this week.

CS: The team saved 2 renewals, and NPS moved to 61. There are 3 open red-flag accounts heading into next week.

PLG: PLG added 412 signups, with activation at 31%. 38 companies reached the aha moment of 10 recognition gives.
partner-digest-sectionPASS 1.00
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 $0.0039 · 15s · in 10,621 / out 768 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. Two sourced DS1 deals: Deal-DDAAF2 ($180,000) + Deal-2CF33E ($95,000) = $275,000. Co-webinar locked for 09-15.

HRCloud Partners — Active. One sourced deal, Deal-F1CDA5 ($140,000), moved to DS2 after the security review closed.

CultureBridge — Active. Two sourced early-stage deals: Deal-096E1D ($60,000) + Deal-067213 ($75,000) = $135,000.

WorkWell Group — Active. No sourced deals this period (0 deals, $0). Q4 joint-playbook restart discussed; planning call booked for 09-09.

Recogniq — Quiet; no activity reported.

KudosWave — Quiet; no activity reported.

PeopleFirst Advisors — Quiet; no activity reported.

TotalPerk — Quiet; no activity reported.

Partner-sourced pipeline: 5 deals; $550,000 total ($275,000 + $140,000 + $135,000).
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 $0.0039 · 12s · in 10,654 / out 723 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
Q1. Yes. Customer data is encrypted at rest using AES-256. [P1]

Q2. Yes. Data in transit is encrypted with TLS 1.2 or higher. [P1]

Q3. Yes. Bonusly maintains a SOC 2 Type II report, renewed annually. Prospects can obtain it under NDA. [P2]

Q4. Customer data is retained for 90 days after the contract ends, then deleted from production systems. [P3]

Q5. The current subprocessor list is published at trust.bonusly.com. Customers receive 30 days’ notice before a new subprocessor is added. [P4]

Q6. Yes. SAML 2.0 single sign-on is available on the Enterprise plan. [P5]

Q7. Production databases are backed up daily. Backups are encrypted and retained for 35 days. [P6]

Q8. Unanswerable from the provided excerpts; they do not state whether Bonusly holds ISO 27001 certification. The ISO 27001 certificate or certification statement would answer this. [P1–P8]

Q9. Unanswerable from the provided excerpts; they do not specify a contractual uptime SLA percentage. The applicable uptime SLA or contract would answer this. [P1–P8]

Q10. Unanswerable from the provided excerpts; they do not state whether Bonusly will sign a HIPAA Business Associate Agreement. Bonusly’s HIPAA/BAA policy or contract terms would answer this. [P1–P8]
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 $0.0351 · 113s · in 254,322 / out 14,337 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
1. ALWAYS-trigger overlap / duplication

- WARNING · MERGE — `comms-drafter` and `email-drafter`: both trigger on writing, drafting, reviewing, rewriting, and replying to customer-facing communications. Their descriptions overlap on phrases including “write me an email,” “draft a follow-up,” and “what should I say.” Proposal: merge the email-specific workflow into one authoritative communication skill.
- WARNING · REVIEW — `pipeline-intelligence-report` and `weekly-pipeline-report`: both trigger on pipeline reports/updates and “what does pipeline look like” requests. Proposal: narrow their trigger boundaries so a full scored pipeline report and a weekly performance update route distinctly.
- WARNING · REVIEW — `analysis-validator`, `signalforge-claim-compressor`, and `signalforge-feedback`: all claim mandatory coverage of SignalForge analysis/report outputs. Their stated execution order separates the steps, but their broad ALWAYS triggers overlap. Proposal: define the shared scope and explicit handoff boundaries.

2. Circular delegation

- WARNING · REVIEW — `deal-strategy-coach` ↔ `email-drafter`: `deal-strategy-coach` directs manager-to-prospect emails to `email-drafter`; `email-drafter` routes strategy and coaching requests back to `deal-strategy-coach`. Proposal: define a one-way handoff rule for mixed strategy-and-drafting requests.

3. Dangling delegation targets

Relative to the supplied files and manifest, these referenced skill targets have no matching file/manifest row:

- WARNING · REVIEW — `bonusly-brand`, `prospect-research-multithreading`, `signalforge-reports`, `skill-orchestrator`.
- WARNING · REVIEW — `bonusly-data-questions`, `bonusly-product-questions`, `bonusly-business-reporting-questions`, `bonusly-rewards-questions`, `bonusly-ppp-questions`, `bonusly-feature-flag-questions`, `bonusly-deal-desk-questions`, `bonusly-datadog-questions`.

Proposal: confirm these targets exist outside the supplied set or update the references.

4. Version conflict

- WARNING · UPDATE_BODY — `analysis-validator` declares v3.6, but its validation-trail template identifies the validator as v3.2. Proposal: make the trail version consistent with v3.6; v3.6 is the version to retain.

5. Descriptions over 1,024 characters

- INFO · REVIEW — 0. Arithmetic: 14 manifest descriptions checked; 0 have `description_chars > 1,024`.

6. Hardcoded page IDs, dates, or person names

- WARNING · UPDATE_BODY — `analysis-validator`: dates include April 26, 2026 and May 9, 2026. Named people include Amani Phipps, Manish, Alaina Loori, Shealagh Coughlin, Bryce Harmon, Hugo Lindqvist, Dana Mercer, Alex Franklin, Cole Ingram, Gavin Porter, Colleen Perry, Ellie Barton, Ashley Reyer, Megan Franz, Elena Sinclair, Youssef Elkhateeb, Amanda Czenkus, Ben Castelli, John Thomas, and Yasmin Wahid. Proposal: make roster and date-dependent content live or clearly mark it as historical.
- WARNING · UPDATE_BODY — `closed-lost-analysis`: hardcoded dates include May 2026, May 4–12, and 4/13. Proposal: mark dated examples and sample findings as historical rather than current guidance.
- WARNING · UPDATE_BODY — `deal-strategy-coach`: Confluence page ID `2257879045`; person names `Perseus` and `Farid`; pricing is labeled 2026. Proposal: verify the fixed reference data and page target remain current.
- WARNING · UPDATE_BODY — `model-selection`: hardcoded registry check date `2026-05-19`. Proposal: keep the registry check date current.
- WARNING · UPDATE_BODY — `partner-digest`: page/folder IDs `2286616609`, `2286321666`, `2265382925`, `2236940297`, `2237825028`, `2239365136`, and `2238283777`; dates include May 16, 2026, May 19, 2026, and June 2, 2026; person names include Amani Phipps, Kelli, Jen Lee, Hani, Bryce, and Sara. Proposal: validate IDs and refresh dated examples and named contact references.
- WARNING · UPDATE_BODY — `pipeline-intelligence-report`: hardcoded dates include May 2026 and March 28, 2023; named people include Bryce Harmon, Dana Mercer, Cole Ingram, Alex Franklin, and Gavin Porter. Proposal: verify the roster and date-sensitive system claims at runtime.
- WARNING · UPDATE_BODY — `sales-forecast`: parent page ID `2232582148`; hardcoded dates include April 27, 2026 and July 9, 2026; person names include Alaina and Elena. Proposal: verify the page target and keep examples/person references current.
- WARNING · UPDATE_BODY — `signalforge-feedback`: page IDs `2295136266`, `2234417154`, and `2247295002`. Proposal: verify these Confluence targets remain valid.
- WARNING · UPDATE_BODY — `stale-pipeline-report`: dates include June 10, 2026, 5/15, 5/7, and 5/19. Proposal: label dated examples as examples or use runtime dates.
- WARNING · UPDATE_BODY — `weekly-pipeline-report`: hardcoded periods include Q2 2026 and Q1 2026; named person: Ben Lavin. Proposal: make reporting periods and owner references runtime-driven where appropriate.

7. Manifest drift

- INFO · REVIEW — No drift in either direction. Arithmetic: 14 supplied skill files − 14 manifest rows = 0 files without rows; 14 manifest rows − 14 supplied files = 0 rows without files.
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 $0.0063 · 26s · in 23,186 / out 2,243 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
## Reward-worker queue incident runbook

1. **Acknowledge alert and take incident command** — **Bryce Harmon** (M01)  
   **Action:** Acknowledged the PagerDuty alert for queue depth over 10k and took IC.  
   **Success verification:** The thread records the acknowledgment and IC handoff; no separate verification is reported.  
   **Rollback:** Not applicable; no system state change is documented.

2. **Check queue depth** — **Farid Osman** (M02)  
   **Command:** `bundle exec rake sidekiq:queue_depth`  
   **Result:** 48,213 pending jobs; normal is under 500.  
   **Rollback:** Not applicable; diagnostic command only.

3. **Inspect dead set** — **Farid Osman** (M03)  
   **Action:** Reported 112 dead-set jobs, all `Redis::TimeoutError` from around 13:58. The inspection command is not recorded.  
   **Success verification:** The reported finding is the only verification given.  
   **Rollback:** Not applicable; no state change is documented.

4. **Pause enqueue** — **Farid Osman** (M04)  
   **Command:** `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`  
   **Success verification:** No direct flag-state verification is recorded; needs confirmation.  
   **Rollback:** `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'` (explicitly supplied in the thread).

5. **Clear the dead set** — **Elena Sinclair** (M05)  
   **Action:** Reported clearing the dead set in the console. Exact command/action details are not recorded; needs confirmation.  
   **Success verification:** Not recorded; needs confirmation.  
   **Rollback:** Not recorded; needs confirmation.

6. **Scale workers up** — **Bryce Harmon** (M06)  
   **Command:** `kubectl scale deployment/reward-worker --replicas=6` (reported as changing from 3).  
   **Success verification:** No direct replica-count verification is recorded; needs confirmation. Later queue improvements are reported in M07–M08 but are not direct verification of the replica count.  
   **Rollback:** `kubectl scale deployment/reward-worker --replicas=3` (explicitly supplied in the thread).

7. **Check queue progress** — **Farid Osman** (M07)  
   **Action:** Reported queue depth at 9,400 and falling approximately 1,200/min. Measurement command is not recorded.  
   **Rollback:** Not applicable; no state change is documented.

8. **Verify queue and error rate** — **Cole Ingram** (M08)  
   **Command:** `bundle exec rake sidekiq:queue_depth`  
   **Success verification:** Command returned 0; Datadog error rate was reported back to baseline.  
   **Rollback:** Not applicable; diagnostic verification only.

9. **Re-enable enqueue** — **Bryce Harmon** (M09)  
   **Command:** `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`  
   **Success verification:** 40 new jobs processed cleanly in the next 3 minutes.  
   **Rollback:** Not documented; needs confirmation.

10. **Scale workers back down and resolve** — **Bryce Harmon** (M10)  
    **Command:** `kubectl scale deployment/reward-worker --replicas=3`  
    **Success verification:** Queue reported stable at 0; incident marked resolved.  
    **Rollback:** Not documented; needs confirmation.
datadog-incident-timeline0.80
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 $0.0070 · 33s · in 46,136 / out 3,527 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
First error — 2026-09-03 14:01:12 UTC: `reward-service` logged `Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s`.

Cascade, in timestamp order:
- 14:01:20, 14:01:30, 14:01:40 — `reward-service` reports retries exhausted for `RewardGiveJob`. At 14:01:40, `sidekiq` logs that `RewardGiveJob` failed with the Redis timeout and will retry in 60 seconds.
- 14:01:46–14:01:57 — `sidekiq_jobs.csv` records six `RewardGiveJob` failures: J-00005 (14:01:46), J-00001 (14:01:51), J-00003 (14:01:54), J-00006 (14:01:55), J-00002 (14:01:56), J-00004 (14:01:57).
- 14:02:28 — `sidekiq` logs another `RewardGiveJob` retry. At 14:02:30 it warns that reward queue depth is above 10,000.
- 14:02:36–14:05:50 — job records show additional Redis-timeout failures: `RecognitionDigestJob` J-00013 (14:02:36), `RewardGiveJob` J-00007 and J-00011 (14:02:51), J-00008 (14:02:56), J-00010 (14:02:57), J-00009 (14:02:58), then `RecognitionDigestJob` J-00014 (14:03:15), J-00015 (14:04:55), and J-00016 (14:05:50). Sidekiq logs further `RewardGiveJob` retries at 14:03:31, 14:04:22, 14:05:26, and 14:06:47.
- 14:03:05 onward — `api-gateway` logs 502 upstream timeouts calling `reward-service`; `web-app` then logs failed Give form submissions, first at 14:03:30. Both services log further errors through 14:06:52.
- 14:22:10 — `reward-service` logs that Redis connectivity is restored and job processing resumes. At 14:24:45, `sidekiq` reports reward queue depth below 500.

Service and jobs involved: the first error is in `reward-service`; the worker errors are logged by `sidekiq`. The named jobs are `RewardGiveJob` and `RecognitionDigestJob`. The later request failures involve `api-gateway` and `web-app`.

Datadog query to confirm the first error:
`service:reward-service "Redis::TimeoutError" "redis-primary:6379"`
Set the time range to 2026-09-03 14:01:00–14:01:30 UTC. If `level` is indexed as a log attribute, add `@level:ERROR`.

What the logs do not show: why Redis timed out, Redis-side health or network evidence, the exact number of affected user requests or jobs beyond the listed records, whether any reward operations were lost or duplicated, or what caused recovery. The sequence is consistent with the timeout preceding the retries, queue growth, and request errors, but the slice alone does not establish the underlying Redis cause.
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 $0.0043 · 18s · in 11,147 / out 1,383 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
| Flag | State | What it controls per code | Targeting / company count |
|---|---|---|---|
| `recognition_streaks_v2` | On | Records a streak when a recognition is given. | `segment:beta_companies` — 42 |
| `points_budget_guardrails` | On | Enforces the company’s points budget when points are given. | `all_companies` — 220 |
| `slack_dm_nudges` | On | Sends a Slack DM nudge to a user. | `segment:region_na` — 87 |
| `redeem_flow_redesign` | Off | Selects the redeem experience: enabled renders `RedeemV2Component`; otherwise it renders `RedeemV1Component`. | `targeted_list` — 12 |
| `analytics_dashboard_v3` | On | Uses the V3 analytics dashboard. | `segment:tier_three` — 65 |
| `ms_teams_app_v2` | Off | Installs `TeamsAppV2`. | `targeted_list` — 9 |
| `legacy_give_modal` | Off | No code reference in the excerpt. | `segment:legacy_plan` — 14 |
| `survey_boosters_q3` | On | No code reference in the excerpt. | `segment:legacy_plan` — 7 |
| `paused_offboard_cleanup` | Off | No code reference in the excerpt. | Targeting rule is blank; company count is 0, so it has no targets in this export. |

The export gives targeting rules and counts, but not company names or identities.
nda-triagePASS 1.00
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 $0.0038 · 10s · in 10,533 / out 510 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: Standard mutual confidentiality; “Term: two (2) years from the Effective Date; obligations survive for three (3) years after termination,” with stated carve-outs and Delaware governing law.
- NDA-2 — YELLOW: Counsel review for the embedded non-solicit: “During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement.”
- NDA-3 — RED: Full legal review for the broad three-year non-compete—“Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser's business”—plus one-way confidentiality, no stated carve-outs, and exclusive Irish jurisdiction.