Test sets
Manage the test sets that validate the agent's behaviour before you publish.
Test sets
The Test sets page is where you build the scenarios that check whether the agent behaves the way you expect. Each set defines inputs, expected outputs, and whether the run should succeed or fail.
Reach it through the Test sets icon in the editor's side navigation.
The list of sets
The table shows every test set on the agent:
| Column | What it is |
|---|---|
| Name | The scenario's name ("Happy path", "Invalid input with no configuration") |
| Expected to succeed | Yes (green) — the agent should finish without escalating · No (red) — the agent should escalate or reject the input |
| Inputs | How many input arguments the set configures |
| Expected outputs | How many output arguments it expects |
| Last run | How long ago it last ran ("2 days ago"), or — if it never has |
Click any row to open that set's editing panel.
Running every set
To run them all at once:
- Click Run (the play icon) in the editor's top bar.
- Choose Test sets in the menu.
- The Running the test sets panel opens with a confirmation:
Every test in this agent's test sets will run. This may consume tokens and take a few minutes.
- Click Run to confirm.
While they run, each set reports its status live:
| Status | What it means |
|---|---|
| Waiting | Queued, not started yet |
| Running | In progress |
| Passed | Finished, and the result matched what was expected |
| Did not pass | Finished, but the result differed from what was expected |
| Failed | Something went wrong during the run |
Click a result card for that run's details, trace and logs.
Removing a set
Click the bin icon on the set's row. A confirmation appears:
Remove this test set? This cannot be undone.
Confirm with Remove.