X · by NO1ennn
A RAG loop where Jev decides what is real
Hybrid search, one Jev scoring call and a claim check, with agents around them.
NO1ennn
@N01ennn
this is pure f*cking treasure A Stanford AI research group finally drew the perfect RAG system: retrieval, Jev and agents in one loop, and it fixes the 3 things that break every RAG app: > the LLM reads 20 passages when only 3 matter > it answers questions your docs can't answer > it trusts whatever text it retrieves here's how it runs: > a lead agent sends the query > hybrid search pulls the top 20 candidates, dense + keyword > ONE Jev request scores all 20 + 2 gates: answerable? injection? > only passages above 0.6 reach the writer agent > a second Jev call checks every claim against its source > grounded answer, with citations and when the docs don't have it: > answerable fails, the writer never runs > a researcher agent rewrites the query and retries once > still nothing? "not in the docs". zero tokens spent on a guess retrieval casts the net. Jev decides what's real. agents do the work save this before you build your next RAG
Oct 1, 2026 · 409 likesOpen on X
NO1ennn describes a Stanford research group's RAG design. Hybrid search pulls the top 20 passages, one Jev request scores all 20 and runs two gates, answerable and injection, and only passages above 0.6 reach the writer. A second Jev call checks every claim against its source. If the docs cannot answer, the writer never runs and the question is retried once.
Open the source
