Agentic Data Plane

Monitor & Debug

See what your agents are doing and why. Monitor agent activity, read individual run transcripts, troubleshoot failures, and track speed, cost, and errors.

  • Use the Home Page

    Use the Agentic Data Plane Home page to see what needs attention, then check gateway traffic, spend, budget health, and top spenders.

  • How Observability Works

    Understand how Redpanda captures end-to-end execution transcripts on a distributed log for agent governance and observability.

  • Monitor Agent Activity

    Monitor agent execution, inspect available MCP tools, analyze conversation history, track token usage, and debug issues using Playground and Transcripts.

  • Visualize Your Agent Network

    See a live map of your agents, the models they call, and the MCP servers they use, with usage, cost, and health for a chosen time window.

  • Review the Audit Log

    Review authorization decisions in the UI or with rpk ai. Filter events and see who acted on which resource and whether the request was allowed.

  • See What Your Agent Did

    Open a transcript in Agentic Data Plane, read the conversation turn by turn, and investigate errors and performance.

  • Trace an Agent Run

    Read one row per agent run or AI Gateway call, expand it into spans, and find the call or policy decision behind a slow or failed run.

  • Troubleshoot Agents

    Diagnose and fix common issues with AI agents, including MCP server connection failures, gateway errors, runtime behavior problems, and tool execution errors.