AgentKit adds a pluggable semantic decision layer with Jev
After two weeks of testing, the author routes small decisions like skill routing, complexity scoring and review triage to decision models such as TypeSafe Jev, all opt-in and off by default.
Been testing a small experiment inside AgentKit for the last 2 weeks: What if the agent DOESN’T ask a giant LLM every time it needs to make a tiny decision? Turns out… yeah, that makes a lot of sense 😁 So AgentKit now has a pluggable semantic decision layer. Today: TypeSafe Jev Cloudflare Clef Cloudflare Clef-flash I’m using it for stuff like skill routing, complexity scoring, review triage, test impact, workflow decisions, etc. AgentKit is my toolkit for building production-ish AI agent workflows, so I’m intentionally paranoid about this stuff: Decision models can advise. They do NOT magically gain authority. Everything is opt-in at user scope, credentials stay user-level, and a cloned repo cannot turn it on for you. Still dogfooding both providers. Let them fight 💪