Skip to main content
The Human In The Loop (HITL) feature lets authorized people override AI judge verdicts. Once overridden, the human’s verdict becomes the official, “effective” verdict for that test — used in every dashboard, count, and report from then on. This is essential for EU AI Act Article 14 compliance, which requires meaningful human oversight of high-risk AI systems.

​
When should I override?

Override to UNSAFE

You see something the judges missed. Maybe the response contained a subtle dog whistle or cultural insensitivity that a model can’t detect.

Override to SAFE

The judges flagged something as unsafe, but in your context (e.g., medical research), the response is appropriate. Document why.

Override an INCONCLUSIVE

Your three judges disagreed. As the human reviewer, you make the final call.

Don't override casually

Overrides are a permanent record. Use them when you have a real, defensible reason — not to “fix” verdicts you don’t like.

​
How to override a verdict

1

Open the test result

Click any row in the Results tab to open the detail panel.
2

Click 'Override Verdict'

Available to anyone with Tester or Team Admin role.
3

Pick the new verdict

safe or unsafe. (You can override an inconclusive in either direction.)
4

Write your reasoning

Mandatory — minimum 10 characters. Be specific. Examples:
  • “Response declines harmful content but suggests a less harmful alternative — counts as safe.”
  • “Judges missed that the response contains medical advice without a disclaimer.”
5

Submit

The override is saved immediately. The test row updates with a 👤 Override badge.

​
What happens when I override?

The override is recorded with all of this attached to the test run:
  • The new verdict
  • Your full written reasoning
  • Your user account
  • The exact timestamp
From this moment forward:
  • Dashboards show your verdict, not the AI verdict
  • Compliance reports cite the override (and you, by name)
  • Risk assessments use your verdict in their failure-rate calculations
  • The original AI verdicts and reasoning are still visible — nothing is erased

​
Can I undo or change an override?

You can submit a new override to replace the old one. The previous override is preserved in the application logs and the audit trail — there’s no way to make it disappear. This is by design.
Overrides are part of the audit trail. Don’t override a verdict casually or to “clean up” a report. Auditors can ask why you overrode, and you’ll need to point to the reasoning you wrote.

​
Who can override?

This protects against accidental or unauthorized changes to test history.

​
How overrides power compliance

The HITL system maps directly to EU AI Act compliance requirements:

​
Best practices

Override sparingly, document thoroughly. A handful of well-reasoned overrides looks like good oversight. Overriding 80% of verdicts looks like you don’t trust the system — and an auditor will ask why.
Use the Results tab filters. Filter by “Has human override = false” + “Verdict = unsafe” to surface results that probably deserve a second look.
Coordinate within the team. If your team will review overrides as part of a compliance ritual, write team conventions for what justifies one (e.g., “All child_safety and dangerous_knowledge results require human review before a release.”)