@ashutoshftw built a semantic circuit breaker so agents that try different actions from the same wrong assumption still get stopped. In one stuck run they report 12 model calls down to 4 and 19.9K tokens down to 5.1K.

Ashutosh Mathore (@ashutoshftw) published this on 2026-09-18. @ashutoshftw built a semantic circuit breaker so agents that try different actions from the same wrong assumption still get stopped. In one stuck run they report 12 model calls down to 4 and 19.9K tokens down to 5.1K. 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. How Jev or TypeSafe is used, in the post's own words: “Jev unlocked a new way to stop AI agents from spinning.” The post does not name a separate audience. It is for people reading what @ashutoshftw shows here (it links to ashutoshvjti.github.io; it includes media).