◆ The honest test

Same candidates. Two minds.
One real outcome.

A generic LLM ranks the best CV against the job. Huntchy ranks who this client accepts. Paste a real role you know the ending to — see who called it right. If they tie, you learn it cheaply. If Huntchy matches the real client choice and the LLM doesn't, that's the moat, shown.

Candidate A
Candidate B
Candidate C · optional
What you know about THIS client — the layer-2 fuel

The part an LLM never has. What does this client actually accept or reject, beyond the job description?

Running both minds against the same candidates
The same candidates, judged two ways — LLM vs Huntchy
Generic LLM — ranks the CV
Reads the job + the CVs. Best engineer on the page.
◆ Huntchy — ranks what this client accepts
Weighs revealed preference, rate that closes, two-sided fit — above raw CV strength.
◆ What actually happened
Generic LLM picked
Huntchy picked
Both picks sit next to the real outcome. You're the judge — did the layer earn its keep, or was the CV enough?