⊚
ICP fit + buying-signal scorer
RevOpsTakes an enriched account (firmographics + scraped web/compliance signals) and returns an Expected-Fit score 0-100, a tier (A/B/C/Disqualify), the evidence-cited compliance buying-signals it found, and a one-line routing verdict with a tailored angle — the LLM judgment layer on top of enrichment so reps only chase best-fit accounts and know who to say no to.
The routing recipe
Job typeComplex reasoningPolicyBalanced
routes to
NVIDIA Nemotron 3 Ultra 550B-A55B nvidia
nvidia:nvidia/nemotron-3-ultra-550b-a55b
90.8
match score
96.5
task fit
100
cost
59.5
speed
Why this model from benchmarks & capabilities
- "Complex reasoning" leans hardest on reasoning; NVIDIA Nemotron 3 Ultra 550B-A55B scores 100/100 there — top-1 of 40 chat models.
- Strength on this class of work shows up on GPQA Diamond, MMLU-Pro, BIG-Bench Hard, where NVIDIA models are competitive.
- Cost: runs on NVIDIA free credits / self-hostable NIM — effectively $0 marginal. Speed: ~70 tok/s (estimated).
- Chosen over NVIDIA Nemotron 3 Super 120B-A12B for higher task-fit (96.5 vs 90.7) & more context.
| Capability the job needs | Weight | NVIDIA Nemotron 3 Ultra 550B-A55B | Catalog rank |
|---|---|---|---|
| reasoning | 1.00 | #1 of 40 | |
| math | 0.60 | #3 of 40 | |
| knowledge | 0.50 | #4 of 40 |
Relevant benchmarksGPQA Diamond MMLU-Pro BIG-Bench Hard LiveBench (reasoning)
EconomicsCost: runs on NVIDIA free credits / self-hostable NIM — effectively $0 marginal.
Speed: ~70 tok/s (estimated). vs runner-upChosen over NVIDIA Nemotron 3 Super 120B-A12B for higher task-fit (96.5 vs 90.7) & more context. (NVIDIA Nemotron 3 Super 120B-A12B, score 89.5)
Speed: ~70 tok/s (estimated). vs runner-upChosen over NVIDIA Nemotron 3 Super 120B-A12B for higher task-fit (96.5 vs 90.7) & more context. (NVIDIA Nemotron 3 Super 120B-A12B, score 89.5)
Example result
Sample input ▾
Enriched account → Venddly | 140 employees | HealthTech SaaS | sells to hospital systems | Signals: (a) job posting 'GRC Manager — own SOC 2 Type II + HIPAA' opened 9 days ago; (b) no trust center found, no GRC tooling detected on site; (c) G2 review (last month) mentions 'security questionnaires are slowing our enterprise deals'; (d) recent funding: Series B $22M, 4 months ago
{
"fit_score": 91,
"tier": "A (>=75)",
"top_signals": [
{"signal": "Active compliance hire", "evidence": "'GRC Manager — own SOC 2 Type II + HIPAA' posted 9d ago", "weight": "high"},
{"signal": "Deal-blocking questionnaires", "evidence": "G2 review (last month): 'security questionnaires are slowing our enterprise deals'", "weight": "high"},
{"signal": "Trust-center gap", "evidence": "No trust center / GRC tooling detected on site", "weight": "medium"},
{"signal": "Funded + upmarket HIPAA motion", "evidence": "Series B $22M (4mo ago); sells to hospital systems (HIPAA-bound buyers)", "weight": "medium"}
],
"disqualifiers": [],
"score_swing": "If the GRC role were already filled 6+ months ago with tooling live, drop ~20 pts (they may have a solution) — verify on the trust page before outreach.",
"routing_verdict": "Route to AE now — textbook HIPAA+SOC2 ICP with a fresh GRC hire and active questionnaire pain. Lead with 'kill the security-questionnaire bottleneck' + stand up a trust center before their next enterprise deal."
}
Test it on your own data
do not list the signal.\n- disqualify if <30 employees with no signal, or vertical is outside icp (e.g. pure consumer/e-commerce with no compliance pressure), or already a customer/competitor.\n- be decisive. no hedging, no 'it depends'. if data is thin, say what single data point would change the tier.\n\noutput strict json only:\n{\"fit_score\": <0-100>, \"tier\": \"a (>=75) | b (50-74) | c (25-49) | disqualify (<25)\", \"top_signals\": [{\"signal\": \"\", \"evidence\": \"\", \"weight\": \"high|medium|low\"}], \"disqualifiers\": [], \"score_swing\": \"the one data point that would most move this score\", \"routing_verdict\": \"one line: route-to/hold + the angle to lead with\"}","task":"reasoning","optimize":"balanced"}'>