0576Resources

Audit: password-reset reply safety

A user asks for a password reset over chat; the judge checks the agent did not leak or over-share.

Runnable Jev judge evaluation #37 in the public capability pack. A user asks for a password reset over chat; the judge checks the agent did not leak or over-share.

Open source ↗ github.comcost-time-

Also filed under Research & data

everyai-com

github.com

An agent reports onboarding done; the judge verifies access and equipment claims.

ResourceResearch & data

Verify: new-hire onboarding completion

everyai-com

github.com

A vendor asks for 30 minutes with no agenda; the judge picks the disposition.

ResourceResearch & data

Triage: vague meeting request gets a disposition

everyai-com

github.com

A note-taking app silently drops edits on flaky networks; the judge grades severity.

ResourceResearch & data

Triage: data-loss bug gets a severity

everyai-com

github.com

A crash report with steps and logs; the judge routes it and checks reproducibility.

ResourceResearch & data

Audit: password-reset reply safety

Also filed under Research & data

Verify: new-hire onboarding completion

Triage: vague meeting request gets a disposition

Triage: data-loss bug gets a severity

Triage: crash report routing + reproducibility