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.
Understand how Redpanda captures end-to-end execution transcripts on an immutable distributed log for agent governance and observability.
Monitor agent execution, analyze conversation history, track token usage, and debug issues using Inspector, Transcripts, and agent data topics.
Open a transcript in ADP, read the conversation turn by turn, and investigate errors, costs, and performance.
Diagnose and fix common issues with AI agents including deployment failures, runtime behavior problems, and tool execution errors.
Emit OpenTelemetry traces from your BYOA (Bring Your Own Agent) so the Agentic Data Plane can attribute calls, costs, and tool invocations to your agent. Covers the minimum required span contract, common optional attributes, and how it differs from a Redpanda-managed agent.
