LangChain's 46-minute talk with the Jev team on where decisions belong
In a demo an agent tries to delete a customer, Jev flags the call as risky and the tool never runs; the talk also covers routing easy prompts to a fast model and keeping scoring criteria consistent.
Teams still pay a heavy LLM to make calls a panel of humans would answer in 5 seconds LangChain sat down with the team behind Jev for 46 minutes on where those calls belong In the live demo an agent tries to delete a customer, Jev marks the call risky, and the tool never runs A second middleware sends the easy prompt to a fast model and keeps the big one for the hard task Their rule for scoring: describe every level well enough that a 1.5 means the same thing on every document you score And the cutoff stays yours to prove, because the confidence you get back is a statistic over the probability map, not a silver bullet My guide turns that into a research filter: 50 papers, a 0 to 3 relevance rubric, a review queue, and a check on the useful papers it archived Watch the session, then grab the starter and the prompts below
This post quotes another post: x.com/alphabatcher/status/2101725422517997896