An AI agent does more than write its final answer. It chooses a tool, reads the result, decides whether to continue, and sometimes has to admit that an action's outcome is unknown. TypeSafe released Jev in September 2026 as a model for typed decisions inside software, which makes those small…
Annons
Annons
An AI agent does more than write its final answer. It chooses a tool, reads the result, decides whether to continue, and sometimes has to admit that an action's outcome is unknown. TypeSafe released Jev in September 2026 as a model for typed decisions inside software, which makes those small transitions a practical design choice.Here is the agent we will build: a generative model plans and writes; Jev chooses among named next actions using the current state; Python checks hard rules, executes a local tool, and records what actually happened. The central question is where a fast decision belongs when the task still needs open-ended reasoning and real effects. The short answer is between observations and permitted transitions. Jev can judge the state, but its choice cannot itself refund an account or prove that a refund settled.Jev sits inside the state transition loop; the executor and observation record determine what actually changed.We will make one Jev call first, then connect it to a small support agent. Then we will compare Jev with two structured-output LLMs using our experiments on support and document-research tasks. The experiment is useful because it records both proposed actions and actual local effects.In this guideWhat Jev decidesGive the agent observable stateBuild the guarded loopRun support and research tasksCompare three supervisorsRead probabilities and disagreementsDecide where Jev belongsOne distinction will keep the rest of the build honest. A tool returning HTTP 202 says a request was accepted for processing. It does not say the requested business outcome happened. That gap is exactly where a supervisor needs evidence, and where code must resist an unsafe retry. Read more
