Example reports

What AgentGate actually posts on your pull request

When the gate runs, it leaves a report like the ones below: the verdict, every metric with its error bars, what the statistics could and could not establish, and how much evidence it had to work with.

Each report here comes from a real run against the same 70-task suite — a healthy agent against one that was deliberately broken in a specific, realistic way. Nothing is hand-written. Notice that the gate reaches a different verdict for each kind of breakage; that difference is the whole point.

Start with the walkthrough Read the methodology
SAFETY_FAIL

Stop — safety failure

The agent did something it must never do. These skip the statistics entirely — no average is good enough to make up for a security failure.

UNDERPOWERED

Not enough evidence

The numbers moved, but not by enough to tell a real change from ordinary variation. This is the verdict a threshold rule can never give, and the one that prevents false alarms.

REGRESSION

Block the merge

The agent really did get worse, by more than the tolerance the policy declared. These block the merge.

PASS

Ship it

Non-inferiority was established — not merely 'we found no problem', but 'the suite was big enough to have found one and did not'.

How to read one

What you'll see inside