Testing and run history

Try your draft before learners meet it, check it against tests, then read what happened in any run.

Try it

Test → Try it runs the unpublished draft, so you don't need to publish to test.

• Who pays. Every message is a real run on the key under Options → Who pays. It needs the Run agents permission and must allow your steps' models. A stopped run still bills the model calls it started.
• Memory. Options → Memory chooses Continue a conversation (recommended), Independent messages or Send history from this browser.
• Test as. Options → Test as sends a person's identifier, such as student-042, as your app would.
• Reference data. Material sent with each message, such as a rubric. Steps read it as {{context.name}}. Try it as in a course activity fills in an activity's How the AI helps, so you see the replies its learners get.
• Attachments. + attaches photos and PDFs when every step that gets the message can read them.

Each reply shows its cost, steps and time. Show on canvas replays the run.

Edit a message you sent and click Save & send: it becomes a new version from that point, with its own replies, and ‹ n/m › moves between versions. New chat clears them; runs stay in Run history.

Run history

A run is one execution of an agent. Test → Run history lists runs newest first. Filter by Where runs came from, such as Chat page, Course or Dashboard test, and by How runs ended. You can also filter by result data, for example needs_human: true. Export downloads the latest 200 as CSV or JSONL.

A run's trace

A run shows its reply, duration, model calls, tokens and cost. Run trace lists the steps in order. A step's Input is what it acted on; its Output shows the result (Pretty or Raw JSON) with the Provider calls. A VETTING step lists each round's verdict and the Reviewer's reason.

Tests

To check a change against what learners might say before you publish, keep tests and run them: see Agent tests.

Insights

Test → Insights shows what people ask the published agent over 7, 30 or 90 days, without your tests, and flags answers that need a look: Failed, Not answered, Needs a person and Review didn't pass. Topics groups recent questions, with What the sources seem to miss. For the middle two, have your Reply step return "status": "not_found" or "needs_human": true in Result data for your app.

Memory

Memory is what an agent keeps about a person between conversations, up to 200 facts each, from a Memory step or Remember the user in an Agent step. A person is the user your app sends, or a chat page's visitor. Test → Memory lists who the agent remembers and what.

Warning

Deleting a fact, or using Forget everything about a person, is permanent.