What it does
Screen agent tool calls and returned content with Jev, then review the judgments in shadow mode before enabling enforcement.
Agent tooling
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
Screen agent tool calls and returned content with Jev, then review the judgments in shadow mode before enabling enforcement.
Let this tool warn you about your AI assistant's actions before allowing it to block them. Read the warnings and check for mistakes while the assistant keeps working. Jev, the outside AI service it uses, rates the risk of each action. If you switch services, test the warnings again: a high risk score from one may mean something different from another.