Operations

Operate AXL

Getting an agent working and keeping it working are different jobs. This section is the second one: what to look at when a run behaves oddly, how to tell whether quality is drifting, and where to start when something has plainly broken.

If you need to…Read
See what a deployment is doing right nowUse the diagnostics console
Follow what happened during a runObserve runs
Check or cancel work that outlives a requestTrack asynchronous tasks
Know whether the agent is actually any goodEvaluate agent quality
Work out why something is failingTroubleshoot a deployment

The two questions to instrument early

What a run actually did is answered by observability - traces, tool audit entries, provider calls, and cost, all correlated by run identifier. Set this up before you need it, because the run you most want to inspect is always one that already finished.

Whether it is getting worse is answered by evaluations. A prompt change that improves three examples and quietly breaks twenty is invisible without a dataset, and online evaluation samples real production runs so you find drift without waiting for someone to complain.

Architecture and concurrency invariants live under rather than here.

Next

On this page