Skip to main content
When an AI agent cannot find the right tool on your server, the user hits a dead end and you never hear about it. Agent feedback closes that loop. AgentCat gives the agent a way to say what it needed or what went wrong, so you can see the gaps in your server and how often agents hit them. This feature is on by default, with no configuration needed. AgentCat adds a get_more_tools tool to your server, which agents call to report what they looked for and did not find.

What you see

agent feedback event in session replay
Agent feedback shows up in three places: Sessions list — The Issues column counts feedback notes next to errors. This gives you a quick sense of how often agents are hitting gaps. Session Replay — Feedback events appear in the timeline with a warning badge. Click one to see what the agent needed and the context behind the request. This is where you find the detail that you need to decide what to build next. Alerts — The Agent feedback alert posts each note to Slack or email as it arrives, with a link back to the session.

The option in each language

Each SDK has one option for this feature, named for the style of its language. We recommend that you keep it on, because the notes show you which tools to build next: