AI system · 2026
Lead research agent
Finds and qualifies sales leads, with evidence for every claim. Drafts the outreach. Sends nothing.
- Role
- Design, build, deploy
- Stack
- Next.js, Supabase, Claude Agent SDK, Apify, Firecrawl
- Status
- Archived
Overview
A list of companies is cheap. The research before the first email is the expensive part, and so is sending something wrong under your own name.
Decisions
There's no send tool.
The agent can't send anything because it was never given a way to. Each stage also runs sealed off from the machine it's on.
The bar stays where it is.
When there aren't enough good leads, it searches wider. It doesn't lower the criteria, and if it's still short, it stops and asks.
Spending waits for approval.
Paid searches only start after the founder confirms the criteria. Every stage has a cap on steps and spend.
Architecture
- Person
- Model
- Tool
- Check
- Result
Step 1, Human: Founder sets the goal
Founder
Step 2, AI: Criteria written
Agent
Step 3, Human: Founder confirms
Founder
Step 4, Step: Find companies
Apify
Step 5, Step: Read each site
Firecrawl
Step 6, AI: Qualify with evidence
Sonnet 5
Step 7, Logic: Enough leads?
Check
Then: step 4 (short? widen the search); step 8 (yes).
Step 8, AI: Draft outreach
Sonnet 5
Step 9, Output: Saved, not sent
In the app
Results
12 / 10
qualified leads against target
48
drafts, none sent
72
actions, all logged
From one full run.
Known limits
Nothing checks timing.
Only 3 of the 12 leads had a real reason to reach out now.
Nothing reviews the criteria.
Every later stage depends on what that step writes.