Use Case

Discover the signals your competitors can't see

Analyze closed-won vs closed-lost accounts to find the niche ICP signals that actually predict revenue. Turn founder intuition into a data-driven scoring model.

Why generic ICP filters fail

Your ICP doc says "Series B SaaS, 100-500 employees." So does everyone else's. There is no differentiation in the signals you score on.

The question that matters: what is actually different between your closed-won accounts and your closed-lost accounts? Not what you think. What the data shows.

How to discover your niche signals

Step 1: Export two lists

Pull from Salesforce or HubSpot:

  • closed-won.csv (50 accounts that closed)
  • closed-lost.csv (50 accounts that did not)

Step 2: Run the niche signal discovery skill

Tell Claude Code
I have two CSVs: closed-won.csv (50 accounts) and closed-lost.csv (50 accounts). Enrich both with firmographics, technographics, hiring data, and funding. Then compare the two sets and tell me the 5 attributes that most strongly predict whether an account will close. Build a scoring function from those signals.

Claude Code reads the Deepline niche signal discovery skill and runs:

deepline enrich --input closed-won.csv --output won-enriched.csv \
  --with 'company=crustdata_companydb_autocomplete:{"field":"company_name","query":"{{Company}}"}' \
  --with 'tech=builtwith_domain_lookup:{"domain":"{{Domain}}"}' \
  --with 'jobs=crustdata_job_listings:{"company_name":"{{Company}}"}'

deepline enrich --input closed-lost.csv --output lost-enriched.csv \
  --with 'company=crustdata_companydb_autocomplete:{"field":"company_name","query":"{{Company}}"}' \
  --with 'tech=builtwith_domain_lookup:{"domain":"{{Domain}}"}' \
  --with 'jobs=crustdata_job_listings:{"company_name":"{{Company}}"}'

Step 3: Review the signals

Claude analyzes both cohorts and surfaces the 3-5 attributes that statistically separate winners from losers.

Step 4: Deploy as a scoring model

Tell Claude Code
Deploy these signals as a scoring model that runs on new leads.

The discovered signals become a scoring function:

deepline workflows deploy icp-scoring --trigger webhook --spec scoring-model.yaml

What niche signals look like

Real examples from Deepline customer runs:

SignalWon accountsLost accounts
VP of RevOps hired in last 6 monthsYesNo
Tech stackSnowflake + dbtLegacy BI
Open engineering roles5+Flat or shrinking
Careers page language"data quality""dashboards"

Your competitors cannot see these signals. They are running the same generic filters everyone else uses.

What gets enriched

Data typeSources
FirmographicsApollo, People Data Labs
TechnographicsBuiltWith, TheirStack
Hiring signalsCrustdata job postings
FundingCrunchbase via Crustdata
Web researchExa semantic search

Cost breakdown

StageCreditsCost
Enrich 100 accounts50-80~$5-8
AI comparison + scoring model10~$1
Total60-90~$6-9

Compare to a RevOps consultant at $5K-15K.

Who uses this

  • Founders who want to stop guessing which accounts to prioritize
  • RevOps leads building scoring models that predict revenue
  • AEs who want to know which accounts are worth their time

Deploy ongoing scoring

Once you have the signals:

Tell Claude Code
Score every new HubSpot contact against these 5 signals. Run daily.

New leads get scored automatically. Signals stay tied to real outcomes, not assumptions.

Common questions

Frequently Asked Questions

1How many accounts do I need?+

50 of each is enough to find patterns. 100+ gives stronger signal.

2What if my won/lost sets are imbalanced?+

Deepline normalizes for sample size. 30 won and 70 lost still works.

3Can I re-run this quarterly?+

Yes. Your ICP evolves as you close more deals. Re-running keeps signals fresh.

Find the signals hiding in your data

Export your won and lost accounts. Deepline does the rest.