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

Model's actual answer

show the model's full answer

DEALS (owner, stage, amount, close date, why-buys)
- Deals extract is not provided, so I cannot:
  - report completeness % per deal field
  - compute “pipeline amount at stake”
  - produce the “10 fixes with the most pipeline amount at stake”
  Needed file: deals.csv (at minimum: deal_alias (or key), owner, stage, amount, close_date, why_buys, company_alias).

COMPANIES (34 rows)
1) Completeness % per required field (arithmetic shown)
- industry: 34/34 = 1.0000 = 100.00%
- employee_count: 25/34 = 0.735294... = 73.53%
- hq_country: 28/34 = 0.823529... = 82.35%

2) Duplicate company clusters (shared domain) + survivor
Note: no company “name” field exists here, so I can only cluster by shared domain (not name variants).

- Cluster: domain = acme-corp.com
  - Members: C-0A092931, C-0A092932
  - Survivor (chosen by most-complete tie-break, then lexicographic): C-0A092931
  - Differences to resolve:
    - industry: C-0A092931 = Technology; C-0A092932 = tech
    - employee_count: C-0A092931 = 500; C-0A092932 = 510
    - hq_country: C-0A092931 = US; C-0A092932 = USA

- Cluster: domain = globex.io
  - Members: C-0A092933, C-0A092934
  - Survivor (chosen by most-complete tie-break, then lexicographic): C-0A092933
  - Differences to resolve:
    - industry: C-0A092933 = SaaS; C-0A092934 = Technology
    - (employee_count and hq_country are the same: 200, US)

3) Fill missing company fields ONLY where zoominfo_enrichment.csv has a matching domain row
- employee_count is missing for 9 companies; 8 of those have a ZoomInfo match with a non-empty zi_employee_count and can be filled:
  - C-EC3025 (ec3025.com): employee_count = (blank in CRM) → 400 (ZoomInfo)
  - C-96039F (96039f.com): employee_count = (blank) → 400
  - C-44EA29 (44ea29.com): employee_count = (blank) → 400
  - C-D04904 (d04904.com): employee_count = (blank) → 400
  - C-B23205 (b23205.com): employee_count = (blank) → 400
  - C-60C75F (60c75f.com): employee_count = (blank) → 400
  - C-7BBDFA (7bbdfa.com): employee_count = (blank) → 400
  - C-50D386 (50d386.com): employee_count = (blank) → 400
- employee_count missing but cannot be filled from enrichment (no matching enrichment row):
  - C-93C8BF (93c8bf.com): employee_count is blank; no ZoomInfo row provided for 93c8bf.com

- hq_country missing for 6 companies; none can be filled from enrichment based on the provided export:
  - C-2D1F1B (2d1f1b.com): CRM blank; ZoomInfo zi_hq_country is also blank
  - C-D73B89 (d73b89.com): CRM blank; ZoomInfo blank
  - C-44EA29 (44ea29.com): CRM blank; ZoomInfo blank
  - C-D04904 (d04904.com): CRM blank; ZoomInfo blank
  - C-2C60E5 (2c60e5.com): CRM blank; ZoomInfo blank
  - C-EE9FFB (ee9ffb.com): CRM blank; no ZoomInfo row provided for ee9ffb.com

4) Where CRM and enrichment DISAGREE: list both + recommend a source
Recommendation logic (no new facts): use ZoomInfo for standardized values (industry taxonomy + country normalization) and keep any internal segmentation separately (don’t overload “industry” with “tech/Technology”).

Industry conflicts (CRM vs ZoomInfo)
- C-66D1FC (66d1fc.com): industry CRM=tech; ZoomInfo=Computer Software → recommend ZoomInfo for industry
- C-EC3025 (ec3025.com): industry CRM=Technology; ZoomInfo=Computer Software → recommend ZoomInfo
- C-44EA29 (44ea29.com): industry CRM=tech; ZoomInfo=Computer Software → recommend ZoomInfo
- C-92D97D (92d97d.com): industry CRM=Technology; ZoomInfo=Computer Software → recommend ZoomInfo
- C-D04904 (d04904.com): industry CRM=Technology; ZoomInfo=Computer Software → recommend ZoomInfo
- C-77A95A (77a95a.com): industry CRM=Technology; ZoomInfo=Computer Software → recommend ZoomInfo
- C-AA8DDA (aa8dda.com): industry CRM=Technology; ZoomInfo=Computer Software → recommend ZoomInfo
- C-B25F40 (b25f40.com): industry CRM=Technology; ZoomInfo=Computer Software → recommend ZoomInfo
- C-60C75F (60c75f.com): industry CRM=tech; ZoomInfo=Computer Software → recommend ZoomInfo
- C-425E2A (425e2a.com): industry CRM=Tech ; ZoomInfo=Computer Software → recommend ZoomInfo

HQ country conflicts (CRM vs ZoomInfo; mostly normalization)
- C-66D1FC (66d1fc.com): hq_country CRM=US; ZoomInfo=United States → recommend ZoomInfo (or normalize CRM to “United States”)
- C-950043 (950043.com): hq_country CRM=US; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-EC3025 (ec3025.com): hq_country CRM=USA; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-96039F (96039f.com): hq_country CRM=USA; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-77A95A (77a95a.com): hq_country CRM=US; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-B23205 (b23205.com): hq_country CRM=US; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-E51FB7 (e51fb7.com): hq_country CRM=USA; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-D0662E (d0662e.com): hq_country CRM=US; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-425E2A (425e2a.com): hq_country CRM=USA; ZoomInfo=United States → recommend ZoomInfo/normalize
- C-2D7423 (2d7423.com): hq_country CRM=USA; ZoomInfo=United States → recommend ZoomInfo/normalize

Companies with no enrichment match in the provided export (cannot enrich from provided data)
- C-BA969B (ba969b.com)
- C-332637 (332637.com)
- C-93C8BF (93c8bf.com)
- C-EE9FFB (ee9ffb.com)
- C-C9BB20 (c9bb20.com)
- C-0A092931 (acme-corp.com)
- C-0A092932 (acme-corp.com)
- C-0A092933 (globex.io)
- C-0A092934 (globex.io)

CONTACTS (52 rows)
1) Completeness % per required field (arithmetic shown)
- email (non-empty): 52/52 = 1.0000 = 100.00%
- title: 39/52 = 0.7500 = 75.00%
- persona: 37/52 = 0.711538... = 71.15%

2) Invalid emails (format)
(Also: “email non-empty” is 100%, but valid-format is lower.)
- Valid-format email rate: 48/52 = 0.923076... = 92.31%
- Invalid emails:
  - CT-0010 (C-66D1FC): email = user0@
  - CT-0080 (C-92D97D): email = user0@
  - CT-0081 (C-92D97D): email = user1@
  - CT-0192 (C-425E2A): email = user2@

3) Domain mismatches (email domain != contact domain), among valid-format emails
- CT-0011 (C-66D1FC): email = user1@other-domain.com; domain = 66d1fc.com

PROPOSED FIXES (what to change in CRM ops / validation)
- Deals: cannot audit or rank by pipeline until deals.csv is provided. Add hard-required fields for owner, stage, amount, close date, why-buys at the stage(s) you consider commit-qualified.
- Companies:
  1) Backfill employee_count from ZoomInfo ONLY for the 8 matched companies listed above; leave C-93C8BF blank unless a matching enrichment row is provided.
  2) Normalize hq_country to a single standard (e.g., use ZoomInfo “United States” vs CRM “US/USA”) to eliminate reporting fragmentation.
  3) Standardize industry: if you adopt ZoomInfo, migrate CRM “tech/Technology/Tech ” into a separate internal segment field (so you don’t lose seller segmentation).
  4) Deduplicate by domain:
     - Merge C-0A092932 → C-0A092931 (acme-corp.com)
     - Merge C-0A092934 → C-0A092933 (globex.io)
- Contacts:
  5) Enforce email-format validation (blocks user0@ patterns).
  6) Enforce/flag email-domain alignment to company domain; route exceptions to review (CT-0011).
  7) Make title + persona required for roles used in opportunity qualification (or at least require persona when linked to active opportunities).

TOP 10 FIXES BY PIPELINE AMOUNT AT STAKE
- Cannot compute: deal amounts and deal-to-company/contact linkage are not provided (no deals.csv). Provide the deals extract and I will rank the fixes by summed amount (with arithmetic shown) and cite deal aliases exactly as given.

SUMMARY — real product gaps (prospect voice only)
1) Deal-EC3025 — Amount: NOT PROVIDED in the data
   Prospect quote: “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.”
   Why it’s a real gap per docs: Product docs state “SCIM user provisioning … [is] NOT currently listed as supported capabilities.”

2) Deal-D0D6B5 — Amount: NOT PROVIDED in the data
   Prospect quote: “Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us.”
   Why it’s a real gap per docs: Product docs state “ADP Workforce Now integrations are NOT currently listed as supported capabilities.”

Arithmetic (counts)
- Real gaps = 2 (= 1 SCIM + 1 ADP)
- Other prospect-raised candidates evaluated = 2 (plan gate 1 + rollout/enablement 1)
- Total prospect-raised candidates evaluated = 4 (= 2 real gaps + 1 plan gate + 1 rollout/enablement)

CANDIDATES (each prospect line + classification + deal + amount)
- TG-001 / Deal-EC3025 / Amount: NOT PROVIDED
  Quote: “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.”
  Classification (using docs): REAL GAP (SCIM not listed as supported)

- TG-002 / Deal-D0D6B5 / Amount: NOT PROVIDED
  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.”
  Classification (using docs): REAL GAP (ADP Workforce Now not listed as supported)

- TG-003 / Deal-CFE7F4 / Amount: NOT PROVIDED
  Quote: “I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?”
  Classification (using docs): PLAN GATE (custom report builder is Enterprise-only)

- TG-004 / Deal-84DBA6 / Amount: NOT PROVIDED
  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.”
  Classification (using docs): ROLLOUT/ENABLEMENT ISSUE (Slack integration exists on all plans; issue is training/adoption)

Excluded (not prospect voice)
- TG-005 rep language about “we don't have a native mobile app…” was not counted because it’s not a prospect line.

What they lead with in the first five minutes (10 calls total)

1) Case-study / ROI opener (8 of 10 calls)
- Arithmetic: 8 ÷ 10 = 0.8 = 80%
- Quote: “Quick one to kick off: a 400-person retailer we work with cut regretted turnover 18% in two quarters after automating milestone awards, and I wanted to walk you through exactly how they did it.”

2) “Agenda first” framing (1 of 10 calls)
- Arithmetic: 1 ÷ 10 = 0.1 = 10%
- Quote: “I put together a short agenda — security review first, then pricing.”

3) “Start with pricing” framing (1 of 10 calls)
- Arithmetic: 1 ÷ 10 = 0.1 = 10%
- Quote: “You asked for straight pricing last time, so let's start there.”


How they handle the three most common objections (by frequency across the 10 calls)

1) Budget locked / can’t add a line item (4 of 10 calls)
- Arithmetic: 4 ÷ 10 = 0.4 = 40%
- Handling (rep quote): “Totally fair. Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off.”

2) Timing push / “revisit next quarter” (3 of 10 calls)
- Arithmetic: 3 ÷ 10 = 0.3 = 30%
- Handling (rep quote): “Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?”

3) Status quo / “we already do recognition with a spreadsheet + gift cards” (3 of 10 calls)
- Arithmetic: 3 ÷ 10 = 0.3 = 30%
- Handling (rep 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.”


How often a concrete next step is agreed (rate)

- Count with an explicit agreed next step: 7 calls (TT-001, TT-002, TT-003, TT-005, TT-006, TT-008, TT-009)
- Total calls: 10
- Arithmetic: 7 ÷ 10 = 0.7 = 70%
- Quote: “Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager.”


Every competitor a prospect raised (prospect-said only)

- Awardco
  - Quote: “We're also in late talks with Awardco — their rewards catalog looks bigger than yours.”
- Kudos
  - Quote: “How are you different from Kudos? Our CEO used them at her last company.”

Note: Workhuman is mentioned by the rep, but no prospect line raises Workhuman in these transcripts.


Two coaching notes

1) The first-5-minutes opener is highly repetitive (80% identical opener). Keep the case study, but add 1–2 alternative openers (e.g., security-first or pricing-first) matched to what the prospect asked for to reduce “script” feel.

2) When “committee/no urgency” shows up, the rep response doesn’t capture a dated next step in the provided lines; add a consistent close that converts “committee” into a scheduled working session with named attendees and a calendar time (the same way the Thursday 2pm close works when it lands).

Last completed month: 2026-08

Redemptions (through 2026-08)
- Redemption count: 378
  - Check (by provider counts): 90 (TangoCard) + 192 (Tremendous) + 37 (custom) + 59 (Snappy) = 378
- Spend (USD): 27,846.00
  - Check (by provider spend): 3,230.00 (TangoCard) + 8,505.00 (Tremendous) + 10,873.00 (custom) + 5,238.00 (Snappy)
    - 3,230.00 + 8,505.00 = 11,735.00
    - 11,735.00 + 10,873.00 = 22,608.00
    - 22,608.00 + 5,238.00 = 27,846.00
- Unique redeemers (distinct user_key): 233
- Redemptions per redeemer: 378 / 233 = 1.6223

Provider mix (% of spend; sums to 100.00%)
- custom: 10,873.00 / 27,846.00 = 39.05%
- Tremendous: 8,505.00 / 27,846.00 = 30.54%
- Snappy: 5,238.00 / 27,846.00 = 18.81%
- TangoCard: 3,230.00 / 27,846.00 = 11.60%
- Total: 39.05% + 30.54% + 18.81% + 11.60% = 100.00%

Top 5 countries by redemptions (count)
1) US: 244
2) CA: 24
3) AU: 21
4) GB: 17
5) NL: 17

Total tickets: 80

BROAD PATTERNS (multi-account), ranked by ARR affected (unique accounts)

1) HRIS provisioning/sync not creating accounts
- Count: 12
- Share: 12/80 = 0.15 = 15.0%
- Distinct accounts (3): C-0B2213A9, C-0DDFC9A7, C-0F6C0F34
- ARR affected: 36,000 + 48,000 + 30,000 = 114,000
- Example ticket_ids: IC-460059, IC-460057
- Recommendation: Add HRIS sync reconciliation + alerting (explicit “skipped hires” list with actionable error reasons) so missed provisions are detected and recoverable.

2) Redemption/checkout & gift card fulfillment failures
- Count: 18
- Share: 18/80 = 0.225 = 22.5%
- Distinct accounts (7): C-0B0F1BAB, C-0B827671, C-0CEF69FD, C-0D9CA315, C-0F876796, C-0FCCD2DF, C-14264ABD
- ARR affected: 10,300 + 10,700 + 8,900 + 9,600 + 8,700 + 9,600 + 11,000 = 68,800
- Example ticket_ids: IC-460025, IC-460034
- Recommendation: Implement end-to-end redemption idempotency + clear failure states (checkout spin, points deduction, gift card delivery) with monitoring on each step.

3) Recognition points ledger: points missing / not posting / balance not updated
- Count: 20
- Share: 20/80 = 0.25 = 25.0%
- Distinct accounts (9): C-0B2895EF, C-0BE96399, C-0BF20542, C-0D0B047C, C-0D284E42, C-0D3278C7, C-0D6CC8E3, C-0DD0626C, C-21FEBCBB
- ARR affected: 2,900 + 2,700 + 4,500 + 4,500 + 3,400 + 3,500 + 4,200 + 2,500 + 2,900 = 31,100
- Example ticket_ids: IC-460004, IC-460007
- Recommendation: Add a points-posting “ledger status” + automated reconciliation for delivered recognitions vs posted balances to prevent silent drop/delay.

4) Slack integration failures (posting, auth, slash command)
- Count: 14
- Share: 14/80 = 0.175 = 17.5%
- Distinct accounts (4): C-0B843542, C-0BA71F12, C-10A56B0F, C-8C2E8F00
- ARR affected: 4,400 + 3,900 + 5,400 + 5,200 = 18,900
- Example ticket_ids: IC-460041, IC-460042
- Recommendation: Add integration health checks + harden auth/token persistence (stop re-auth “not sticking” / toggle reset) and instrument slash-command errors.

SINGLE-ACCOUNT NOISE (one account), ranked by ARR affected

5) Billing accuracy: seat-count / invoice discrepancy / renewal tier pricing (single-account concentration)
- Count: 16
- Share: 16/80 = 0.20 = 20.0%
- Distinct accounts (1): C-0E9C27D1
- ARR affected: 52,000 = 52,000
- Example ticket_ids: IC-460071, IC-460079
- Recommendation: Do a targeted billing audit for C-0E9C27D1 (seat count + tier price + renewal charge logic) and add pre-invoice validation to prevent repeat discrepancies.

Active quarter: Q3-2026 (days elapsed: 66/92 = 66 ÷ 92 = 0.717391)

SQMs
- QTD actual: 230
- Target: 300
- Delta (actual - target): 230 - 300 = -70
- Pace: ahead (expected-to-date = 300 * (66/92) = 300 * 0.717391 = 215.217391; actual 230 > 215.217391)

SQOs
- QTD actual: 84
- Target: 120
- Delta (actual - target): 84 - 120 = -36
- Pace: behind (expected-to-date = 120 * (66/92) = 120 * 0.717391 = 86.086957; actual 84 < 86.086957)

DS2s
- QTD actual: 40
- Target: 75
- Delta (actual - target): 40 - 75 = -35
- Pace: behind (expected-to-date = 75 * (66/92) = 75 * 0.717391 = 53.804348; actual 40 < 53.804348)

Closed-lost MIA rate
- QTD actual: closed_lost_mia / closed_lost_total = 5 / 25 = 0.200000
- Target: 0.1
- Delta (actual - target): 0.200000 - 0.100000 = +0.100000
- Pace: behind (lower_better; 0.200000 > 0.100000)

Same-quarter close count
- QTD actual: 10
- Target: 20
- Delta (actual - target): 10 - 20 = -10
- Pace: behind (expected-to-date = 20 * (66/92) = 20 * 0.717391 = 14.347826; actual 10 < 14.347826)

Active pipeline coverage against target
- QTD actual: $3,000,000
- Target: $4,000,000
- Delta (actual - target): $3,000,000 - $4,000,000 = -$1,000,000
- Coverage vs target: 3,000,000 / 4,000,000 = 0.750000 = 75.0%
- Pace: ahead (expected-to-date = 4,000,000 * (66/92) = 4,000,000 * 0.717391 = 2,869,565.217391; actual 3,000,000 > 2,869,565.217391)

What moved this week
Week-over-week movement cannot be determined from the provided data: marketing_qtd.csv contains only QTD totals and does not include a prior-week QTD snapshot or any dated weekly increments.

Q1 (Is customer data encrypted at rest? If so, how?)
Yes. All customer data is encrypted at rest using AES-256. [P1]

Q2 (Is data encrypted in transit?)
Yes. Data in transit is encrypted with TLS 1.2 or higher. [P1]

Q3 (Do you hold a SOC 2 report, and can we obtain a copy?)
Yes. Bonusly maintains a SOC 2 Type II report, renewed annually, and it is available to prospects under NDA. [P2]

Q4 (How long is customer data retained after contract termination?)
Customer data is retained for the duration of the contract plus 90 days, then deleted from production systems.
Arithmetic: retention end date = contract end date + 90 days. [P3]

Q5 (Where is your subprocessor list published and how are changes notified?)
The current subprocessor list is maintained at trust.bonusly.com. Customers receive 30 days notice before a new subprocessor is added. [P4]

Q6 (Do you support SAML single sign-on?)
Yes. SAML 2.0 single sign-on is available on the Enterprise plan. [P5]

Q7 (What is your production backup schedule and retention?)
Production databases are backed up daily. Backups are encrypted and retained for 35 days. [P6]

Q8 (Do you hold an ISO 27001 certification?)
Unanswerable based on the provided excerpts; ISO 27001 certification is not addressed in [P1], [P2], [P3], [P4], [P5], [P6], [P7], or [P8]. A current ISO 27001 certificate and/or an ISO 27001 statement in the trust portal would answer this. [P1] [P2] [P3] [P4] [P5] [P6] [P7] [P8]

Q9 (What is your contractual uptime SLA percentage?)
Unanswerable based on the provided excerpts; uptime SLA percentage is not addressed in [P1], [P2], [P3], [P4], [P5], [P6], [P7], or [P8]. The MSA/SLA (service level agreement) section of the contract would answer this. [P1] [P2] [P3] [P4] [P5] [P6] [P7] [P8]

Q10 (Will you sign a HIPAA Business Associate Agreement?)
Unanswerable based on the provided excerpts; HIPAA BAA signing is not addressed in [P1], [P2], [P3], [P4], [P5], [P6], [P7], or [P8]. A HIPAA/BAA policy statement in the trust portal or the legal/compliance addendum/BAA template would answer this. [P1] [P2] [P3] [P4] [P5] [P6] [P7] [P8]

NDA-1 — GREEN (standard approval): “Carve-outs: information that (a) is or becomes publicly available through no breach, (b) was known prior to disclosure, (c) is received from a third party without duty of confidence, (d) is independently developed, or (e) must be disclosed by law or court order.” (standard carve-outs + mutual confidentiality; Delaware governing law is standard: “the laws of the State of Delaware, USA.”)

NDA-2 — YELLOW (counsel review): “Non-solicitation: ‘During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee…’” (embedded non-solicit; duration arithmetic: 18 months = 18/12 = 1.5 years post-term)

NDA-3 — RED (full legal review): “Non-compete: ‘For a period of three (3) years following the Effective Date, Recipient shall not… engage in or provide services to any business that competes with Discloser’s business.’” (non-compete + missing carve-outs: “No confidentiality carve-outs are stated in this Agreement.” + unusual governing law/jurisdiction: “laws of the Republic of Ireland… exclusive jurisdiction of its courts.”)