Scenario
You’re building a company intelligence API (like Extruct), and you have one customer — a procurement automation company that uses your API to score potential suppliers. You want to find more companies like them.Starting Prompt
Claude loads the context-building skill and starts gathering information about your product and ICP.
I’ll help you build a campaign starting from this win case. First, let me capture some context.
- What’s your product’s core value proposition?
- Who typically sends these emails (name/role)?
- What tone do you prefer for outreach?
- Any words or phrases you never want to use?
The context file includes your win case, product info, voice rules, and ICP profile derived from the successful customer.
Claude uses the hypothesis-building skill to identify why this customer is a good fit and what pain points your product solves for them.
Based on this win case, I see a few hypothesis angles:
- Procurement data gap — companies scoring vendors need company intelligence that’s not in their CRM
- Build vs buy for APIs — teams building features that need company data
- Legacy data quality — companies frustrated with stale or incomplete vendor databases
claude-code-gtm/
└── context/
├── extruct_context.md
└── procurement-automation/
└── hypothesis_set.md
# Lookalike search from seed company
curl -X GET "https://api.extruct.ai/v1/companies/customer-example.com/similar?limit=100" \
-H "Authorization: Bearer $EXTRUCT_API_TOKEN"
# Query 1: Procurement workflow automation
curl -X GET "https://api.extruct.ai/v1/companies/search" \
-H "Authorization: Bearer $EXTRUCT_API_TOKEN" \
-d '{
"q": "procurement automation software that helps companies evaluate and score suppliers",
"limit": 100
}'
# Query 2: Vendor management platforms
curl -X GET "https://api.extruct.ai/v1/companies/search" \
-d '{
"q": "vendor management and supplier qualification platforms",
"limit": 100
}'
# Create table
curl -X POST "https://api.extruct.ai/v1/tables" \
-d '{
"name": "Procurement Automation - Seed Campaign",
"kind": "company"
}'
# Upload domains in batches
curl -X POST "https://api.extruct.ai/v1/tables/tbl_abc123/rows" \
-d '{
"rows": [
{"data": {"input": "domain1.com"}},
{"data": {"input": "domain2.com"}}
]
}'
Created table
tbl_abc123 with 267 companies. View at: https://app.extruct.ai/tables/tbl_abc123
I’ll design enrichment columns to validate hypothesis fit:
Column 1: Vendor Evaluation Workflow
Type: select
Options: Manual process, Basic tools, Automated platform, No formal process
Why: Confirms procurement sophistication Column 2: Data Integration Signals
Type: text
Prompt: Check if mentions API integrations, data enrichment, or third-party data in their product description Why: Shows if they’re already comfortable with API-based solutions Column 3: Recent Procurement News
Type: text
Prompt: Find recent news or announcements from about procurement, vendor management, or supplier qualification features Why: Timing signal for outreach
Type: select
Options: Manual process, Basic tools, Automated platform, No formal process
Why: Confirms procurement sophistication Column 2: Data Integration Signals
Type: text
Prompt: Check if mentions API integrations, data enrichment, or third-party data in their product description Why: Shows if they’re already comfortable with API-based solutions Column 3: Recent Procurement News
Type: text
Prompt: Find recent news or announcements from about procurement, vendor management, or supplier qualification features Why: Timing signal for outreach
# Add enrichment columns
curl -X POST "https://api.extruct.ai/v1/tables/tbl_abc123/columns" \
-d '{
"kind": "agent",
"name": "Vendor Evaluation Workflow",
"key": "vendor_workflow",
"value": {
"agent_type": "research_pro",
"prompt": "Research {input} and categorize their vendor evaluation process...",
"output_format": "select",
"labels": ["Manual process", "Basic tools", "Automated platform", "No formal process"]
}
}'
# Trigger enrichment
curl -X POST "https://api.extruct.ai/v1/tables/tbl_abc123/run"
Enriching 267 companies across 3 columns…
Estimated time: 8-10 minutes
Status: 89/267 complete…
Status: 178/267 complete…
Status: 267/267 complete ✓
## Segmented List: Procurement Automation Campaign
### Tier 1 — 31 companies (11.6%)
Strong hypothesis fit + rich enrichment data + clear hook
| Company | Domain | Hypothesis | Hook Signal |
|---------|--------|------------|-------------|
| VendorMatch | vendormatch.io | #1 Procurement data gap | CEO quoted on "lack of real-time vendor intelligence" |
| SupplyCore | supplycore.com | #1 Procurement data gap | Launched supplier scoring feature last month |
| ProcureIQ | procureiq.com | #2 Build vs buy | Job posting for "API Integration Engineer" |
### Tier 2 — 164 companies (61.4%)
Medium fit or data-rich without standout hook
### Tier 3 — 72 companies (27.0%)
Weak fit or insufficient data
# Email Prompt: Procurement Automation Campaign
## Voice Rules
- Sender: Danny from Extruct
- Tone: Builder-to-builder, analytical
- Language: B2 English, simple sentences
- Banned: agents, revolutionize, game-changing
## Structure
P1: Personalized opener referencing {{vendor_workflow}} or {{procurement_news}}
P2: Value prop + example query relevant to procurement use case
P3: Social proof from similar company
P4: Proof point (choose based on hypothesis)
## Hypothesis Mapping
- If vendor_workflow = "Automated platform" → use #1 Procurement data gap angle
- If mentions API in description → use #2 Build vs buy angle
...
Claude uses email-generation to create personalized emails for Tier 1 and templated emails for Tier 2.
Subject: Company intelligence for supplier scoring
Hi [First Name],
I saw your recent comments about the lack of real-time vendor intelligence
in procurement workflows. We've seen similar challenges with teams building
supplier scoring features.
Extruct is an API for company search and data. You can query companies by
description and get structured profiles. Example:
"Find B2B software vendors in supply chain with 50-200 employees founded
after 2015"
A procurement platform similar to VendorMatch uses this to auto-score vendors
their customers are evaluating.
Worth a look?
Danny
Extruct
PS. The API is free for search (unlimited), $59/mo for 1K enrichment credits.
For your 31 Tier 1 emails, Claude can use email-response-simulation to simulate how the recipient might read the email.
# Upload to Instantly via API
curl -X POST "https://api.instantly.ai/api/v1/lead/add" \
-d '{
"api_key": "$INSTANTLY_API_KEY",
"campaign_id": "camp_xyz",
"email": "[email protected]",
"first_name": "...",
"variables": {...}
}'
Final Artifacts
Campaign Results
After running the campaign for 2 weeks:- Tier 1: 31 sent, 8 replies (25.8% reply rate), 4 positive
- Tier 2: 164 sent, 12 replies (7.3% reply rate), 3 positive
- Top hypothesis: #1 Procurement data gap (9 of 11 positive replies)