Build my ICP from my closed-won deals

<context>
I want to build a precise ICP definition from my actual
closed-won customers — not from assumptions or filters,
but from the patterns that appear consistently in the
deals I've already won.

My closed-won customers:
1. [Company name or domain]
2. [Company name or domain]
3. [Company name or domain]
4. [Company name or domain]
5. [Company name or domain]
[Add as many as you have — minimum 5 for reliable patterns]

What I sell: [one sentence describing your product and
the problem it solves]
My target buyer: [e.g. VP of Sales, Head of RevOps, CFO]
</context>

<task>
1. FIRMOGRAPHIC ANALYSIS — Use Lusha to pull the verified
   profile for each closed-won customer:
   - Industry and sub-vertical
   - Employee count at time of close
   - Revenue range
   - Funding stage and total raised
   - HQ geography
   - Company type: public / private / PE-backed

2. SIGNAL ANALYSIS — For each customer, check what signals
   were firing at the account in the 90 days before the
   deal closed:
   - Hiring surges in the target function
   - Executive moves in the buying role
   - Funding events
   - Intent signals on relevant topics
   - Tech stack changes

3. PATTERN IDENTIFICATION — Across all customers, find
   the attributes that appear most consistently:
   - Which firmographic combinations appear in 70%+
     of wins?
   - Which signals appeared before most deals closed?
   - Which tech stack signals correlate with conversion?
   - What does the typical deal look like at the moment
     it entered the pipeline?

4. ICP DEFINITION — Return a structured ICP built from
   the patterns found:
   - Firmographic profile: the specific ranges and
     categories that appear most in your wins
   - Signal triggers: the events that most commonly
     preceded a close
   - Tech stack indicators: technologies that correlate
     with fit
   - Exclusion criteria: attributes that appear in
     low-fit or lost deals if identifiable
   - Confidence level for each criterion based on how
     consistently it appears across your wins

5. SCORING FRAMEWORK — Return a simple scoring model
   based on the ICP found:
   - Which criteria are must-haves vs nice-to-haves?
   - How to score a new prospect against this ICP
     in under 2 minutes
</task>

A precise ICP definition built from your actual closed-won data — firmographic patterns, signal triggers, tech stack indicators, and a scoring model you can use immediately.

Your ICP definition

Customers analyzed: 8  ·  Patterns identified: 6 high-confidence, 3 directional  ·  Confidence threshold: 70%+

Firmographic profile

Signal triggers

Signals that appeared in the 90 days before most deals closed:

Tech stack indicators

Exclusion criteria

Scoring model

Use this to score any new prospect in under 2 minutes:

Score interpretation:

• 7–9 — Strong ICP match. Prioritize immediately.
• 4–6 — Partial match. Qualify further before investing time.
• 0–3 — Weak match. Deprioritize unless a compensating signal exists.
• Fail on must-have — Exclude regardless of score.

Example outputs in this play are illustrative — they reflect the structure, fields, and format of real Lusha connector output, but were not pulled from a live session. Run the prompt with your own closed-won customers and connectors to see live results.