ClientMine: how it is built
A weekly board of companies ready to buy, built by AI agents and approved by a person.
clientmine.aiClientMine, opens in a new tabClientMine is a web app that tells a firm, every week, which companies are ready to buy. It checks two things together: signals of buying readiness, like hiring abroad, new funding or SEC filings, and fit, meaning the right type of company with a clear decision maker. Each company comes with a tailored approach, and a person approves the board before the firm sees it. Its first paying client is an immigration law firm.
Tools. Claude Code agents, Python scraping, Firecrawl, SEC EDGAR API, PredictLeads API, Supabase, Next.js, Vercel.
Run a weekly scan. Watch which steps are AI agents and which are plain code.Sample
- Find companies with a buying triggerAIScout agent
- Read each company’s website onceCodeCode
- Check the gates, score the fitAIScorer agent
- Research the best, up to 6 a weekAIEnricher agent
- Write an approach for eachAIEnricher agent
- Final score and tierCodeCode, no AI
- You approve the boardYouA person
- Publish to the firm’s boardCodeCode
- Recheck last week’s companiesAIMonitor agent, alongside
This week’s scan hasn’t run yet.
Last week’s board is still live for the firm. Press Run it to watch the agents build the next one.
Larkspur Biotech
Raised a Series B in Germany
Head of People. Email found.
First moveCongratulate her on the raise. Ask how the German team will move over.
Tidewell Analytics
Opening a U.S. office
COO. Email found.
First moveAsk who handles visas for the U.S. launch team.
Oakmere Foods
Local bakery, no hiring
Too smallBrightline Freight
Hiring 12 engineers abroad
VP Engineering. On LinkedIn.
First moveAsk about timing for the 12 hires abroad.
Quillon Software
New VP of People
Marrow & Pine
A law firm itself
Wrong industryHalcyon Labs
Expanding to Texas
Vessel Robotics
No named leader to reach
No way in
Hot ListNew this week
Acting now
Worth building
How it is built, for the technical reader.
One product, end to end: what I did, how it is put together, what it costs to run well, and where it falls short.
Tools. Claude Code agents, Python scraping, Firecrawl, SEC EDGAR API, PredictLeads API, Supabase, Next.js, Vercel, React, Tavily, Apollo.
- My part
- I designed and built the product: the weekly scan, the agents’ written procedures, the database and the web app the firm uses. My partner sells it and runs the client relationship.
- The design
- AI agents do the reading and judging. Plain Python runs everything else: the order of steps, the gates, the final score and the save. Each agent writes its results to a file, and a checker rejects any file that breaks the agreed shape before the next step reads it.
- One trade-off
- Deep research costs the most, so it is spent last and on at most 6 companies a week. Cheap checks drop poor fits first. The firm gets fewer companies, each researched properly, instead of a long list nobody can call.
- How it is tested
- About 170 automated test files cover the plain-code steps, the file checks, the gates and the database write. The approval gate is enforced in code: the write refuses to run without an approval tied to that exact board.
- Limits
- The weekly scan still runs with me supervising. Outside data services can fail or hit a usage limit mid-scan. When a step fails, nothing is published and last week’s board stays up.
- Status
- In paid use since July 2026 by an immigration law firm, with a new board each week.
More work.
- SuperBloom: weekly LinkedIn drafts that start from her own answers
- The New York Sun: unknown subscription sources cut from over 90% to about 7%
- instantAIpage: a page AI search can find and quote accurately
- Chamber chatbot: a chatbot that answers from its own material and hands harder questions to staff
- VAST Cleaning: every request becomes a priced proposal, approved twice
- Client websites: websites their owners keep building