Rivet's lesson: JEV doesn't reason—split severity classification into tiny yes/no prompts

yawnxyz · x · 2026-11-19

Hard-won tip from the Rivet team: JEV does not reason, by design. Their initial single prompt asking for an SEV1–4 severity verdict gave mediocre results; after reading the docs they split it into tiny binary asks (did production go down? are they blocked with no workaround? is something broken?) and mapped answers to severity with if-branches, which worked like a charm. The screenshot shows the decision process: checks run top to bottom until one matches, e.g. 82% confidence on "something in Rivet is broken" → SEV3.

Original post →

More from coding & agent

coding & agent channel →