Use cases

Use AgentSight to debug and review real agent runs

Start with a slow run, an AI-generated change, a closed-source agent, or an extension you need to inspect.

Performance use case

Profile slow or expensive AI agent runs

Find where an AI agent run spent time and tokens by connecting model calls to commands, files, waits, and process activity.

Code review use case

Review an AI-generated change with the commands, tests, retries, file effects, and network activity that produced it.

Compatibility use case

Observe local AI agent commands and child processes without requiring an SDK, source change, proxy, or vendor-specific callback.

Extension audit use case

Run an agent extension under system-level tracing to inspect its subprocesses, file changes, remote calls, and resource cost.