Discover the signals your competitors can't see

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

The skill enriches both cohorts with firmographics, technographics, hiring data, and funding, then compares the sets to surface the attributes that predict wins vs losses:

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

The discovered signals become a scoring function:

deepline workflows apply --payload '{"name":"icp-scoring","trigger":{"type":"webhook"},"steps":[/* enrich + score */]}'
# Configure the trigger and any approval gates via the dashboard at /workflows

Sample analysis: Cybersecurity ICP

A sample / illustrative fraud prevention company ran niche signal discovery on 84 closed-won and 85 closed-lost accounts. Here's what the data showed.

Positive-fit signals (predict closed-won)

Anti-fit signals (predict closed-lost)

The scoring model

Signals get weighted into a lead score:

From signals to outreach

Once you have the signals, Deepline finds the companies and contacts that match.

Step 1: Find companies with positive signals

deepline enrich --input tam-companies.csv --output scored.csv \
  --with 'cip_check=exa_search:{"query":"site:{{domain}} customer identification program"}' \
  --with 'sandbox=exa_search:{"query":"site:{{domain}} sandbox OR developer.{{domain}}"}' \
  --with 'tech=builtwith_domain_lookup:{"domain":"{{domain}}"}' \
  --with 'jobs=crustdata_job_listings:{"company_name":"{{company}}"}'

Step 2: Score and filter

deepline enrich --input scored.csv --output tier1.csv \
  --with 'score=run_javascript:calculateScore(cip_check, sandbox, tech, jobs)' \
  --with '{"alias":"keep","tool":"run_javascript","payload":{"code":"return Number(row.score) >= 60 ? row : null"}}'

Step 3: Find the buyers

deepline enrich --input tier1.csv --output contacts.csv \
  --with 'contacts=crustdata_people_search:{"company_domain":"{{domain}}","title_patterns":["Head of Fraud","VP Risk","BSA Officer","CCO","Head of KYC"]}'

Step 4: Enrich emails and reach out

deepline enrich --input contacts.csv --output outreach-ready.csv \
  --with 'email=bettercontact_enrich:{"first_name":"{{first_name}}","last_name":"{{last_name}}","company_domain":"{{domain}}"}'

deepline enrich --input outreach-ready.csv --output sent.csv \
  --with 'outreach=lemlist_add_to_campaign:{"campaign_id":"tier1-fraud-signals","email":"{{email}}","first_name":"{{first_name}}","company":"{{company}}","signal":"{{top_signal}}"}'

What gets enriched

Cost breakdown

From raw CRM export to scored outreach list for under $40.

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, deploy them as an always-on workflow:

deepline workflows apply --payload '{"name":"icp-scoring","trigger":{"type":"cron","schedule":"0 8 * * *"},"steps":[/* enrich + score + writeback */]}'
# Wire HubSpot as the source, Tier 1 routing (BetterContact + Lemlist push),
# and approval gates via the dashboard at /workflows.

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

Common questions

$ curl -s "https://code.deepline.com/api/v2/cli/install" | bash