· 7 min read
Knowing when to stop: Agentic loops and "system one model" evaluators
Part 1/2 - An agent is only as good as its exit conditions. Most failures are not bad first steps, but loops that never stop. This post makes a simple case: breaking conditions should be first-class evals, checked at every iteration. A new class of models, which TypeSafe AI calls System One models, makes that economically realistic for the first time.
