Jev unlocked a new way to stop AI agents from spinning.
Built a semantic circuit breaker that uses Jev to detect when an agent is stuck on a wrong assumption, cutting a run from 19.9K to 5.1K tokens.
The original post
Jev unlocked a new way to stop AI agents from spinning.
Agents do not always repeat the same action. Sometimes they try different things based on the same wrong assumption.
I built a semantic circuit breaker around that.
In one stuck run:
12 model calls -> 4
19.9K tokens -> 5.1K
What the author linked
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under agents & workflows. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the agents & workflows page.
Related Jev cases
Had jev, claude haiku 4.5, and gemini 3.5 flash-lite play
Games
found the perfect use case for @typesafeai Jev: instant
Agents
Breaking: Browser Use + Jev = Ultrafast Findings flights
AgentsBrowser agents
Jev case: in 40 seconds it broke down 724 live ads from 37
WebsitesAgents
Keep browsing: all 1173 Jev cases · more from @ashutoshftw · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post