Skip to main content
Agents is in private beta, so things may change. If you hit a problem, tell us via Support & feedback.
Auto-improve is a second AI that studies the first. It reads back through your Agent’s runs, finds what’s going wrong, and suggests changes to its instructions. Go to Agents → open an Agent → ImproveAuto-improve. The page has two tabs: Configure and Runs.
An Auto-improve analysis in progress, showing the runs it reviewed and the new issues it diagnosed

How do I run an analysis?

Open the Runs tab, tell it what to look at if you want, and click Run analysis.
Focus example
Leave the box empty and it looks at everything. When it finishes, it tells you how many runs it read, how many problems it found, how many fixes it made, and what it cost.

How do I tell it what “good” looks like?

Open the Configure tab and answer three questions: Skip that last one and Auto-improve will report your own policies as bugs.

Can it run on a schedule?

Yes. On the Configure tab, turn the schedule on, set when, and pick a timezone.

Can it fix things on its own?

Yes. Under Behavior, switch it from only raising problems to fixing them automatically. Leave it on raising problems until you’ve read a few analyses and trust what it suggests.

How do I stop it spending too much?

Three caps sit under Behavior on the Configure tab: Every analysis reads some runs, so Traces per run is required: enter a whole number from 1 to 50. Leave Credits or Duration empty for no cap. Auto-improve costs credits, but it isn’t a run, so it shows up under Spend by source on Analytics rather than in the run charts.

Where do its findings go?

To the Issues page. The Runs tab shows the analyses it’s done. Issues shows what they found.

Additional FAQ

Your Agent’s runs, including the thumbs up and thumbs down your team left on them. See Run history. Reviewing runs makes its analyses better.
Only if you let it. BuildMoreIssue access has three settings: None, Read, and Read and write. See Issues.
Not unless you apply a fix, or you turned on automatic fixes. Applying one is immediate: it publishes a new version and goes live on the next run, with no draft to check first. Every fix is in your version history, so you can roll it back. See Issues.
Often enough that there are new runs to learn from. For a busy Agent, once a week is a good place to start.