We built an AI-powered LinkedIn Chrome extension — live, from a voice memo, using multi-agent orchestration.
A Chrome extension that crawls your LinkedIn feed using Qwen 3.5 via OpenRouter to classify connections and build actionable dossiers for specific networking goals.
Find donors and allies for a friend's nonprofit focused on AI for human good.
Surface investors and angels for Multpod, an AI event management startup.
Event organizers, conference ops, and community leads for Multpod.
Location-aware lists for Palo Alto, East Bay, and SF meetups.
Installed Anthropic's CLI, then added oh-my-claudecode for multi-agent superpowers.
OMC's Socratic interview turned a rambling voice note into a tight spec with goals, constraints, and edge cases.
Three agents reached consensus on the implementation plan before a single line of code was written.
Designer, executor, and verifier agents built the full extension end-to-end.
Extension loaded, side panel opened, LinkedIn feed crawled, posts classified. It works.
Prompt → code → debug → repeat. Hours of back-and-forth fixing what the AI missed.
Interview → plan → architect → build → verify. Ambiguity dies before code starts. One shot, working extension.
97% of tokens were cache reads — Claude Code reuses context aggressively. Actual LLM generation: 111K tokens. Cost breakdown: cache reads $19, output $8, cache writes $6.
The deep-interview turns your rambling into a real specification. Just answer honestly.
10 minutes of /ralplan saves hours of debugging. Let agents argue about architecture first.
Designer, executor, reviewer, verifier — each does one thing well. That's the whole trick.
Qwen 3.5 at 35B handled classification perfectly. Right model, right cost, right results.
Voice memo → working Chrome extension. In one live session. This is software now.