> For the complete documentation index, see [llms.txt](https://docs.contextual.io/documentation-and-resources/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.contextual.io/documentation-and-resources/components-and-data/agents/agent-details.md). # Agent Details Agents are the operational embodiment of a flow, and the Agents user interface is the centralized place for defining, monitoring, and managing everything about an agent. The Agent Details screen includes the following tabs: **Definition —** The definition tab holds the configuration of the agent in terms of type (HTTP or Event), selected flow, agent image, scaling model, and scaling settings. Each of these is described in detail on the next page. [**Object Metrics**](/documentation-and-resources/tenants/monitoring/metrics.md#record-metrics-record--object-metrics) **—** View metrics for the agent configuration record, with current state and history views. **Operations —** The operations tab displays the current operational status of the instances of the agent. Each instance is shown in the grid view on this tab along with it's status and the date-time that it was started. [**Metrics**](/documentation-and-resources/tenants/monitoring/metrics.md#agent-metrics-agent--metrics) **—** Monitor agent runtime metrics, including CPU and memory usage. [**AI Gateway**](/documentation-and-resources/tenants/monitoring/metrics.md#agent-metrics-agent--metrics) **—** View provider usage for AI requests made by the agent. **Logs —** The logs tab displays both the session and individual message logs for the agent. These are logs of the messages output by log-tap nodes used within the flow, but also include system-level logging information and context to better assist in diagnosing issues with flows. **Audit Trail —** The audit trail tab holds the audit trail of changes made to the agent, when they were made, and who made them. **Versions —** The versions tab shows the list of agent versions. Each time that an Agent configuration is modified, a new version is created. You can see old versions here and examine the JSON for each of those versions. From the versions tab you can also rollback to a previous version of the agent. Each of these is described on the following pages in additional detail. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.contextual.io/documentation-and-resources/components-and-data/agents/agent-details.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.