> ## Documentation Index
> Fetch the complete documentation index at: https://developers.agentx.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Topics

> What your agents are actually being asked, clustered

<Frame caption="Find out what people are talking about.">
  <img src="https://mintcdn.com/agentx-ffe8d995/PbzTdPvYY2JtPkrQ/images/topics.png?fit=max&auto=format&n=PbzTdPvYY2JtPkrQ&q=85&s=9650bf6dbe5885a1bc9caf95c523c713" alt="PLACEHOLDER: entity-relationship style diagram. Left: Agent emits Traces (with child Spans and Tool calls), Traces group into Sessions. Middle: Patterns and Online Evaluators read Traces/Sessions and raise Signals. Right: Datasets (Questions + criteria) drive Evaluation Runs producing Results with ratings. Bottom: Prompts and Tool Schemas registries receive evidence from Signals and Results." width="2012" height="1146" data-path="images/topics.png" />
</Frame>

Monitor tells you when your agent fails; **Topics** tells you what people actually ask it. When enabled, an LLM classifier assigns each monitored trace a short topic label, clustered and shown as Overview's topic map and the dashboard's own **Topics** tab - the fastest way to see that 40% of traffic is about one thing your prompt barely covers. It's off by default (every classification is an LLM call against your key): turn it on in Platform Settings → **Monitoring Defaults** → Topics, a single project-level toggle. Classification is per trace, not per session, since a topic describes an individual request.