Using Jev for typed routing at every agent decision point
The author argues a cheap-model detour costs 49% more than staying on the frontier model because context, not tokens, is what gets routed, so each decision point (which chunks to show, reuse or rebuild the cache, allow/ask/deny a command) is put to Jev as a typed question.
the cheap-model detour in your agent costs 49% more than staying on the frontier model, and its why u need JEV. Opus -> Sonnet -> Opus looks like savings on the price list. the small model loads the whole context, the big one reloads whatever changed, you pay for the transcript twice. routing priced per token is the bug. context is what gets routed. so the notes put one typed question to Jev at every decision point: > which chunks does this turn get to see > reuse the cached prefix or rebuild it > allow, ask or deny this command > which files does the subtask touch, and which provider may go near them the symptom table, the routing math, a checklist the notes skip, three skeletons you can paste today.
This post quotes another post: x.com/lintchadotcom/status/2102585604554801176