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

======================================================================
CRM AUDIT REPORT — Amani GTM Analysis
======================================================================

1. SOURCE DATA SCOPE
--------------------------------------------------
  Companies:      34 rows
  Contacts:       52 rows
  Enrichment:     25 domains (ZoomInfo export)
  Deals:          NO deals table provided (owner, stage, amount,
                  close date, why-buys all absent).
  GTM constraint: 10 fixes ranked by operational severity
                  because pipeline amount cannot be calculated.

2. FIELD COMPLETENESS PERCENTAGES
--------------------------------------------------
  Companies:
    domain              : 34/34 (100%)
    industry            : 34/34 (100%)
    employee_count      : 25/34 (74%)
    hq_country          : 28/34 (82%)
  Contacts:
    email               : 52/52 (100%)
    title               : 40/52 (77%)
    persona             : 37/52 (71%)
  Note: 4 contacts have an 'email' value, but the value is syntactically
        invalid (missing domain, just '@'). Email completeness remains
        100% because the field is non-empty; validity is reported in §4.

3. DUPLICATE COMPANY CLUSTERS
--------------------------------------------------
  Duplicate domains:
  domain = acme-corp.com
    C-0A092931  industry='Technology'  emp=500  hq=US
    C-0A092932  industry='tech'  emp=510  hq=USA
    SURVIVOR: C-0A092931 (most complete row in cluster)
  domain = globex.io
    C-0A092933  industry='SaaS'  emp=200  hq=US
    C-0A092934  industry='Technology'  emp=200  hq=US
    SURVIVOR: C-0A092933 (most complete row in cluster)

  Shared free-form industry name variants (not a true duplicate,
  but they make reporting/forecasting noisy):
    'manufacturing' -> ['C-2D1F1B', 'C-31ED2A', 'C-2D7423']
    'technology' -> ['C-66D1FC', 'C-EC3025', 'C-44EA29', 'C-92D97D', 'C-D04904', 'C-77A95A', 'C-AA8DDA', 'C-B25F40', 'C-60C75F', 'C-425E2A', 'C-BA969B', 'C-332637', 'C-93C8BF', 'C-C9BB20', 'C-0A092931', 'C-0A092932', 'C-0A092934']
    'retail' -> ['C-C6FE92', 'C-950043', 'C-D73B89', 'C-D0662E', 'C-B97B4E']
    'finance' -> ['C-96039F', 'C-E51FB7']
    'healthcare' -> ['C-B23205', 'C-63A874', 'C-2C60E5', 'C-7BBDFA', 'C-50D386', 'C-EE9FFB']

4. INVALID EMAILS (4 contacts)
--------------------------------------------------
  CT-0010  company=C-66D1FC
    email='user0@'  expected_domain='66d1fc.com'
  CT-0080  company=C-92D97D
    email='user0@'  expected_domain=''
  CT-0081  company=C-92D97D
    email='user1@'  expected_domain='92d97d.com'
  CT-0192  company=C-425E2A
    email='user2@'  expected_domain='425e2a.com'
  Format issues: addresses end in '@' with no domain portion.

5. EMAIL DOMAIN MISMATCHES (1 contact)
--------------------------------------------------
  CT-0011  company=C-66D1FC
    email=user1@other-domain.com
    expected_domain=66d1fc.com  actual_domain=other-domain.com

6. ENRICHMENT FILL (values to copy from zoominfo into CRM)
--------------------------------------------------
  C-EC3025: fill employee_count = 400  [source: enrichment]
  C-96039F: fill employee_count = 400  [source: enrichment]
  C-44EA29: fill employee_count = 400  [source: enrichment]
  C-D04904: fill employee_count = 400  [source: enrichment]
  C-B23205: fill employee_count = 400  [source: enrichment]
  C-60C75F: fill employee_count = 400  [source: enrichment]
  C-7BBDFA: fill employee_count = 400  [source: enrichment]
  C-50D386: fill employee_count = 400  [source: enrichment]

7. ENRICHMENT CONFLICTS (CRM and zoominfo disagree)
--------------------------------------------------
  C-66D1FC  domain=66d1fc.com
    field=industry
    crm='tech'  zi='Computer Software'
  C-66D1FC  domain=66d1fc.com
    field=hq_country
    crm='US'  zi='United States'
  C-950043  domain=950043.com
    field=hq_country
    crm='US'  zi='United States'
  C-EC3025  domain=ec3025.com
    field=industry
    crm='Technology'  zi='Computer Software'
  C-EC3025  domain=ec3025.com
    field=hq_country
    crm='USA'  zi='United States'
  C-96039F  domain=96039f.com
    field=hq_country
    crm='USA'  zi='United States'
  C-44EA29  domain=44ea29.com
    field=industry
    crm='tech'  zi='Computer Software'
  C-92D97D  domain=92d97d.com
    field=industry
    crm='Technology'  zi='Computer Software'
  C-D04904  domain=d04904.com
    field=industry
    crm='Technology'  zi='Computer Software'
  C-77A95A  domain=77a95a.com
    field=industry
    crm='Technology'  zi='Computer Software'
  C-77A95A  domain=77a95a.com
    field=hq_country
    crm='US'  zi='United States'
  C-AA8DDA  domain=aa8dda.com
    field=industry
    crm='Technology'  zi='Computer Software'
  C-B23205  domain=b23205.com
    field=hq_country
    crm='US'  zi='United States'
  C-E51FB7  domain=e51fb7.com
    field=hq_country
    crm='USA'  zi='United States'
  C-D0662E  domain=d0662e.com
    field=hq_country
    crm='US'  zi='United States'
  C-B25F40  domain=b25f40.com
    field=industry
    crm='Tech'  zi='Computer Software'
  C-B25F40  domain=b25f40.com
    field=employee_count
    crm='50'  zi='120'
  C-60C75F  domain=60c75f.com
    field=industry
    crm='tech'  zi='Computer Software'
  C-425E2A  domain=425e2a.com
    field=industry
    crm='Tech'  zi='Computer Software'
  C-425E2A  domain=425e2a.com
    field=hq_country
    crm='USA'  zi='United States'
  C-2D7423  domain=2d7423.com
    field=hq_country
    crm='USA'  zi='United States'

8. RECOMMENDED SOURCE PRIORITY RULES
--------------------------------------------------
  Industry:
    - CRM uses free-text ('tech', 'Tech ', 'Technology').
    - ZoomInfo uses canonical taxonomy ('Computer Software').
    - Rule: standardize to ZoomInfo taxonomy for all tech companies
      because it is searchable and dedupe-safe.
      Override ONLY if CRM segment is validated by a sales rep.

  Employee count / HQ country:
    - Treat enrichment as the authoritative source when fields are blank.
    - Treat enrichment as the authoritative source when both are non-blank
      but differ, because CRM values look stale ('US' vs 'United States' is
      a formatting mismatch, not a true semantic diff) and ZoomInfo is
      updated more frequently for firmographics.
    - Log the change in CRM notes for auditability.

  Contact emails:
    - CRM email is the record of obligation.
    - For invalid/mismatched emails, flag the contact for re-verification
      and DO NOT overwrite the CRM value without buyer confirmation.

9. TOP 10 FIXES (ranked by data-quality severity; pipeline amount unknown)
--------------------------------------------------
  Because no deals table was provided, fixes are ranked by:
  (1) number of duplicates/misaligned records, and
  (2) blocking revenue-impact (invalid contacts, null firmographics).

   1. DEDUP — acme-corp.com
       -> MERGE C-0A092931 + C-0A092932 into survivor C-0A092931
   2. DEDUP — globex.io
       -> MERGE C-0A092933 + C-0A092934 into survivor C-0A092933
   3. FIX invalid emails — 4 contacts
       -> Re-verify CT-0010, CT-0080, CT-0081, CT-0192; all lack a domain
   4. FIX email domain mismatch — 1 contact
       -> Re-verify CT-0011; email domain is other-domain.com, not 66d1fc.com
   5. STANDARDIZE industry taxonomy
       -> Replace 'tech'/'Tech '/'Technology' with one term (ZoomInfo: 'Computer Software') across 12 companies
   6. STANDARDIZE hq_country codes
       -> Normalize 'US', 'USA', 'United States' -> one value; enrich 6 blanks from ZoomInfo
   7. FILL missing employee_count
       -> Copy 8 null values from enrichment (all = 400)
   8. FILL missing hq_country
       -> Copy 6 null values from enrichment (all = United States or Canada)
   9. VALIDATE conflicting firmographics vs enrichment
       -> Resolve 20 conflicts; recommend enrichment wins; normalize 'US'/'United States' formatting into a consistent code
  10. FIX orphan contacts (C-2D1F1B, C-D73B89, C-44EA29) missing persona/persona
       -> Assign persona to 7 contacts in these companies where persona is blank; prioritize champion/economic buyer mapping

======================================================================
END OF REPORT
======================================================================

Report saved to /Users/amaniphipps/crm_audit_report.txt

**Per-transcript classification**

TG-001 / Deal-EC3025
Prospect quote: "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management."
Classification: Real product gap.
Product docs reference: "SCIM user provisioning ... are NOT currently listed as supported capabilities."
Deal/amount: Deal-EC3025. Amount: not provided in source data.

TG-002 / Deal-D0D6B5
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."
Classification: Real product gap.
Product docs reference: "ADP Workforce Now integrations are NOT currently listed as supported capabilities; HRIS: Workday, BambooHR, Gusto, Rippling (Pro and above)."
Deal/amount: Deal-D0D6B5. Amount: not provided in source data.

TG-003 / Deal-CFE7F4
Prospect quote: "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.
Product docs reference: Custom report builder is available on the Enterprise tier only. Rep confirmed upgrade path exist.
Deal/amount: Deal-CFE7F4. Amount: not provided in source data.

TG-004 / Deal-84DBA6
Prospect 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: Rollout/enablement issue.
Product docs reference: Slack integration is supported on all plans; not a missing capability.
Deal/amount: Deal-84DBA6. Amount: not provided in source data.

TG-005 / Deal-36C33F
Prospect quote: "Good to know. The web version should be fine for our office staff for now."
Classification: Not a prospect-raised gap. Mobile app absence was disclosed proactively by the rep; the prospect accepted the current state as temporary.
Product docs reference: No native mobile app listed in docs excerpt.
Deal/amount: Deal-36C33F. Amount: not provided in source data.

---

**Summary — Real product gaps only**

1. Deal-EC3025 — SCIM user provisioning absent (prospect: "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.")
2. Deal-D0D6B5 — ADP Workforce Now integration absent (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.")

show the model's full answer

**OPENER (FIRST FIVE MINUTES)**

8 of 10 calls lead with:
> "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."

The other 2 calls opened with:
> "I put together a short agenda — security review first, then pricing." (Deal-403845)

> "You asked for straight pricing last time, so let's start there." (Deal-1E2498)

---

**THREE MOST COMMON OBJECTIONS + HANDLING**

1. Budget locked (4 occurrences)
   Prospect: "Honestly, budget is locked until next fiscal year — I can't add a new line item right now."
   Alex: "Totally fair. Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off."

2. Revisit next quarter / open enrollment crunch (3 occurrences)
   Prospect: "This is good, but can we revisit it next quarter? Open enrollment starts in October and we're underwater."
   Alex: "Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?"

3. Spreadsheet and gift cards already in use (3 occurrences)
   Prospect: "We already do recognition with a spreadsheet and quarterly gift cards — why would we change?"
   Alex: "Spreadsheets work until they scale — the difference is automation: milestones fire without HR lifting a finger, and you get analytics on who is being recognized."

---

**CONCRETE NEXT STEP AGREED**

7 of 10 calls:
> "Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager."

No next step locked in 3 calls (Deal-403845, Deal-EDC141, Deal-84DBA6).
Rate: **70%**

---

**COMPETITORS PROSPECT-RAISED**

- Awardco
> "We're also in late talks with Awardco — their rewards catalog looks bigger than yours."

- Kudos
> "How are you different from Kudos? Our CEO used them at her last company."

(Workhuman was mentioned by Alex, not by a prospect.)

---

**COACHING NOTES**

1. The 400-person retailer success story is the dominant opener and the primary lever for defusing budget objections; default to it over agenda-led or pricing-first openings.
2. Accepting stall language ("I'll leave it with you," "I need to think about it," "I can't commit today") kills the close on otherwise qualified calls — always pivot to a specific calendar hold rather than letting the prospect set the close.

Last completed month: 2026-08

Redemption section
------------------
Redemption count: 378
Total spend: $27,846.00
Unique redeemers: 235
Redemptions per redeemer: 1.61

Provider mix (% of spend):
  custom:      39.0%
  Tremendous:  30.5%
  Snappy:      18.8%
  TangoCard:   11.6%
  [Sum: 100.0%]

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

Source: redemptions_ytd.csv (378 rows; no data beyond 2026-08 present).

Ticketing tier grouping with account-level details.

I parsed the 150 tickets by body text, condensed each repeated body into one row, counted distinct `account_alias` values for that body, summed ARR per unique ARR, and tallied ticket counts which equals distinct body text counts per exact text. Then I clustered related body texts into themes.

Takeaways:

- HRIS / Provisioning Failures dominate ARR exposure ($114,000 across 3 distinct accounts, 11 tickets)
- Redemption / Gift Card Failures carry the widest customer impact (7 distinct accounts, $68,800)
- Billing / Invoice Discrepancies is concentrated in 1 account ($52,000, 16 tickets) — single-account rally
- Points Not Posting is noisiest by ticket volume (20 tickets, 9 accounts, $31,100)
- Slack Integration Failures is smaller but recurring (4 accounts, $18,900)

Detailed Breakdown:

1. HRIS / Provisioning Failures
   - Tickets: 11 | Share: 7.3% | Distinct accounts: 3 | ARR affected: $114,000
   - Sample ticket IDs: IC-460059, IC-460062
   - Accounts: C-0B2213A9 ($36,000), C-0DDFC9A7 ($48,000), C-0F6C0F34 ($30,000)
   - One-line recommendation: Repair the silent-fail provisioning pipeline; the same 12-hire skip error across high-ARR accounts suggests a code-level bypass, not isolated data issues.

2. Redemption / Gift Card Failures
   - Tickets: 18 | Share: 12.0% | Distinct accounts: 7 | ARR affected: $68,800
   - Sample ticket IDs: IC-460025, IC-460031
   - Key accounts: C-0CEF69FD ($8,900), C-0B827671 ($10,700), C-0F876796 ($8,700), C-14264ABD ($11,000), C-0FCCD2DF ($9,600), C-0D9CA315 ($9,600), C-0B0F1BAB ($10,300)
   - One-line recommendation: Audit checkout redemption and vendor gift-card fulfillment end-to-end; when the same failure repeats across multiple mid-market accounts, the issue sits in the redemption fulfillment layer, not front-end UX.

3. Billing / Invoice Discrepancies
   - Tickets: 16 | Share: 10.7% | Distinct accounts: 1 | ARR affected: $52,000
   - Sample ticket IDs: IC-460071, IC-460079
   - Account: C-0E9C27D1 ($52,000)
   - One-line recommendation: Isolate C-0E9C27D1 in finance and review seat-count logic; 16 tickets from one account indicate an ongoing billing contract mismatch, not a platform bug.

4. Points Not Posting (Crediting / Recognition Delivery)
   - Tickets: 20 | Share: 13.3% | Distinct accounts: 9 | ARR affected: $31,100
   - Sample ticket IDs: IC-460001, IC-460004
   - Accounts: C-0D3278C7 ($3,500), C-0BF20542 ($4,500), C-0D0B047C ($4,500), C-0B843542 ($4,400), C-10A56B0F ($5,400), C-0BE96399 ($2,700), C-0D284E42 ($3,400), C-0DD0626C ($2,500), C-0B2895EF ($2,900)
   - One-line recommendation: Check the points-event backlog after recognition delivery; repeated "sent but never arrived" reports across low-to-mid ARR accounts suggests a queue-time or eventual-consistency issue in the credit writer.

5. Slack Integration Failures
   - Tickets: 14 | Share: 9.3% | Distinct accounts: 4 | ARR affected: $18,900
   - Sample ticket IDs: IC-460047, IC-460046
   - Accounts: C-0B843542 ($4,400), C-0BA71F12 ($3,900), C-10A56B0F ($5,400), C-8C2E8F00 ($5,200)
   - One-line recommendation: Investigate the Slack OAuth/token refresh flow; the “sync toggle resets” and “re-auth doesn’t stick” symptoms are pointing to an authorization persistence bug, not user error.

If you want, I can send you a machine-readable JSON version.

**Weekly Marketing Goals Update — Q3-2026**
Quarter elapsed: 66 of 92 days (71.7%)

| metric | qtd_actual | target | delta | pace |
|---|---|---|---|---|
| sqms | 230 | 300 | -70 | ahead |
| sqos | 84 | 120 | -36 | behind |
| ds2s | 40 | 75 | -35 | behind |
| closed_lost_mia_rate | 20.0% | 10.0% | +10.0pp | behind |
| same_quarter_closes | 10 | 20 | -10 | behind |
| active_pipeline | $3,000,000 | $4,000,000 | -$1,000,000 | ahead |

Arithmetic
- closed_lost_mia_rate = 5 ÷ 25 = 0.20 (20.0%).
- Pace baseline = 66 ÷ 92 = 71.7% of quarter elapsed.
- Higher-better metrics pace determined by (QTD actual ÷ target) vs 71.7%:
  - SQMs: 230 ÷ 300 = 76.7% → ahead
  - SQOs: 84 ÷ 120 = 70.0% → behind
  - DS2s: 40 ÷ 75 = 53.3% → behind
  - same_quarter_closes: 10 ÷ 20 = 50.0% → behind
  - active_pipeline: $3M ÷ $4M = 75.0% → ahead
- Lower-better closed_lost_mia_rate: actual 20.0% > target 10.0% → behind.

---

The provided source files contain only QTD aggregates; no weekly-sequence or prior-week baselines are present, so week-over-week movement cannot be identified. From the QTD position, SQMs and active pipeline are running ahead of the 71.7% elapsed pace, while SQOs, DS2s, and same-quarter closes are all trailing. The closed-lost MIA rate is exactly double its 10% target (20.0%, or 5 of 25 closed-lost deals), which by definition removes those deals from the same-quarter close pool and is the most data-backed bottleneck at this snapshot.

vendor response

Q1 — Yes. Customer data is encrypted at rest using AES-256. [P1]

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

Q3 — Yes. Bonusly maintains a SOC 2 Type II report, renewed annually, and it is available to prospects under NDA. [P2]

Q4 — Customer data is retained for the duration of the contract plus 90 days, after which it is 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. Document needed: ISO 27001 certification documentation or compliance attestation.

Q9 — Unanswerable from the provided excerpts. Document needed: service level agreement or contractual uptime commitment documentation.

Q10 — Unanswerable from the provided excerpts. Document needed: HIPAA Business Associate Agreement policy or HIPAA compliance documentation.

NDA-1: GREEN — Mutual confidentiality paired with standard carve-outs (publicly available, prior knowledge, third-party receipt, independent development, legally required disclosure), Delaware governing law, and no anti-red-flag clauses such as non-solicit, non-compete, or exclusivity.

NDA-2: YELLOW — Embeds an employee non-solicitation and no-hire clause ("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") that is atypical for an evaluation NDA and should be reviewed by counsel for enforceability and scope before execution.

NDA-3: RED — Contains an aggressive non-compete with no service-area or business limitation ("For a period of three (3) years following the Effective Date, Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser's business") and states no confidentiality carve-outs whatsoever, creating significant overbreadth and enforceability concerns that require full legal review.