Turn closed-won data into
a 100-point ICP rubric.

RoleYou are building the ICP scoring rubric for my B2B SaaS company by analyzing closed-won vs closed-lost deal patterns. Output a 100-point scoring rubric across 4 categories (firmographic 45 / technographic 30 / behavioral 25 / negative −15), the closed-won vs closed-lost evidence behind each criterion's point allocation, and a HubSpot deployment package with property definitions and workflow logic.

My BrandBrand: [your B2B SaaS brand name]
Target ACV range: [e.g. "$15K - $50K mid-market deals"]
Average sales cycle: [in days, affects behavioral signal lookback]
Known disqualifiers (from sales): [disqualifiers your sales team has flagged, e.g. "agencies (we serve in-house only), companies under 20 employees, students, competitor employees"]

Task1. Pull all closed-won deals from HubSpot in the last 12 months. For each deal, capture: deal amount, company industry, company employee count, company ARR, company HQ country, technographic data if present (HubSpot Insights, Clearbit, etc.), associated contact job title and seniority, source (Original Source), days from creation to close, number of contacts on the deal.

2. Pull all closed-lost deals from HubSpot in the same 12-month window. Capture the same attributes plus closed-lost reason if recorded.

3. Calculate baseline statistics:
   - Total closed-won count and average deal size
   - Total closed-lost count
   - Win rate by industry, employee count bucket, ARR bucket
   - Win rate by source (Google Ads, LinkedIn, organic, direct, referral)

4. For each potential criterion, compare closed-won concentration vs closed-lost concentration. A criterion is predictive if closed-won is significantly more concentrated in one value than closed-lost. Calculate the win-rate lift for each value within the criterion.

FIRMOGRAPHIC CATEGORY (45 points total)
Allocate the 45 points across 5-7 criteria from these candidates, weighted by predictive power:
- Industry/vertical (typical 9-13 points)
- Employee count bucket (typical 9-12 points)
- Company ARR/revenue (typical 7-11 points)
- Geography (typical 5-9 points)
- Business model (B2B vs B2C, SaaS vs services), typical 5-7 points
- Funding stage (Seed / Series A / Series B+), typical 5-7 points

TECHNOGRAPHIC CATEGORY (30 points total)
Allocate the 30 points across 3-5 criteria from these candidates:
- CRM platform (HubSpot/Salesforce typically score, others vary)
- Marketing automation tool
- Infrastructure provider (AWS/Azure/GCP if relevant)
- Specific complementary product in stack
- Cloud-native vs legacy, typical 3-5 points

BEHAVIORAL CATEGORY (25 points total)
Allocate the 25 points across 3-4 criteria from these candidates:
- Demo request submitted (typical 8-10 points)
- Pricing page visit (typical 5-8 points)
- Multi-touch engagement (3+ pages or 2+ sessions), typical 5-8 points
- Specific high-intent action (case study download, ROI calculator, etc.), typical 5-8 points

NEGATIVE CATEGORY (−15 points total)
Allocate the −15 points across 3-5 disqualifier criteria from these candidates:
- Competitor employee email domain (typical −5)
- Student/educational email, typical −5
- Agency (if not your ICP), typical −5
- Sub-threshold employee count (under 20 if your ICP is mid-market+), typical −5
- Excluded geography, typical −3

5. For each criterion, output:
   - Criterion name and value buckets (e.g. "Industry: SaaS / FinTech / Other")
   - Win-rate lift evidence (e.g. "SaaS deals: 32% win rate vs 14% baseline")
   - Point allocation per bucket
   - HubSpot property name (kebab-case, prefixed with "icp_")

Output format1. Headline: total deals analyzed (closed-won + closed-lost), confidence level (HIGH / MEDIUM / LOW based on data depth), single most predictive criterion identified.

2. Closed-won vs closed-lost comparison table: 6-10 rows of the most predictive attributes, with concentration in won deals, concentration in lost deals, and recommended point allocation.

3. The full 100-point rubric, organized by category. For each criterion: criterion name, value buckets, point allocation, HubSpot property name.

4. Score thresholds and what each means:
   - 0-30: Disqualified or unscored
   - 31-49: ICP-aligned but not qualified, nurture
   - 50-69: ICP-qualified, eligible for MQL
   - 70-100: High priority, route to sales immediately

5. HubSpot deployment package:
   - List of custom properties to create (with field types: dropdown / number / boolean)
   - Calculated property formula for total ICP score
   - Workflow logic for auto-scoring new contacts
   - Segmentation list definitions (ICP-qualified, High-priority)

6. Honest calibration:
   - If closed-won deals < 30, flag confidence as LOW. Recommend running a smaller behavioral pilot or waiting until volume builds.
   - If closed-lost data is missing closed-lost reasons, flag that the rubric is one-sided (won-data-only).
   - If the brand has had a recent pivot or pricing change, flag that 12-month historical data may not reflect the current ICP.

// Be evidence-based. Every point allocation must be justified by win-rate lift in the data, not assumed.
// Be honest about confidence. With < 30 closed-won deals, the rubric is directional, not authoritative.
// Don't over-fit. If a criterion shows lift but is highly correlated with another, only allocate points to the more fundamental one.
// The HubSpot deployment package is the most actionable output. Make it concrete enough to paste into HubSpot admin.