# Runs

The execution log: every test result, with a detail view that shows exactly which assertion failed.

**Path:** Trust Lab → Runs (fourth icon)

Runs is the execution log — every time scenarios were tested, the result appears here.

## Summary cards

<RunSummaryCards />

| Card | Description |
| :--- | :--- |
| **Passed** | Total runs where all scenarios passed |
| **Failed** | Total runs with assertion failures or errors |
| **Total** | All runs on the current page |
| **Pending/Running** | Runs still in progress |

## Run list

Each row represents a single suite or scenario execution:

| Column | Description |
| :--- | :--- |
| **Suite / Scenario** | What was tested |
| **Outcome** | Passed or Failed |
| **Pass Rate** | e.g., "3/3 passed" |
| **Trigger** | How it was initiated — MANUAL or SCHEDULED |
| **Started** | Exact timestamp |

Use the **Suite**, **Scenario**, and **Outcome** filters to isolate specific failures or track a scenario's history over time.

## Drilling into a failed run

<FailedEval />

Click any row to open the run detail. You'll see each turn with the agent's actual response alongside the eval criteria. Failed evals are highlighted in red, showing exactly which assertion didn't pass and what the agent said instead.

:::note[Debugging flaky runs]
When a run fails intermittently, open multiple run records for the same scenario side-by-side and compare agent responses to identify what's changing.
:::