first-customer-finder
First Customer Finder
Turn a startup URL or product description into a short, evidence-backed list of plausible first customers. Use public signals, preserve privacy, and distinguish a prospect from a confirmed buyer.
Read references/research-framework.md before researching or scoring prospects and references/report-artifact.md before creating the final report. For saved history, feedback, or a repeat search, also read references/feedback-and-history.md.
Use English by default; follow an explicit language request. Keep the chat handoff short and put the useful detail in the report. Research requires available web search/browser tools; the bundled Python helpers only validate, export, and manage local files. If live browsing is unavailable, report that limitation instead of inventing leads.
Workflow
1. Understand the product
- Inspect the supplied URL, repository, landing-page copy, or product description.
- Identify the product, outcome, buyer, user, price or buying motion, geography, and strongest use case.
- Define one primary ICP, one adjacent ICP, pain triggers, positive signals, and disqualifiers.
- Infer missing context when safe and label the inference. Ask one concise question only when ambiguity would materially change the search.
- Use one stable product-specific workspace folder. If its history exists, inspect the saved preferences and excluded prospects before searching. Never load another product's history just because it is nearby. State briefly where history will be saved; respect requests for no saved history.