AI Release Readiness
2 AI systems · evidence-based release recommendations · updated 2026-10-10 10:07 UTC
openai/gpt-oss-20b · prompt v2 · latest run 2026-10-10 01:24 UTC
- R10 — accepted: Personal or confidential customer data is exposed in answers
10Risks
9Mitigated
0Open
0Evidence gap
1Accepted
openai/gpt-oss-20b · prompt v3 · latest run 2026-10-10 09:01 UTC
- H01 is open and rated critical: Agent calls the wrong tool, or skips a tool it needed
- H02 is open and rated critical: Wrong arguments — dates, leave type or request ids (e.g. "next Monday" booked on the wrong day)
- H09 is open and rated high: Quality silently degrades after a prompt, model or tool change
10Risks
7Mitigated
3Open
0Evidence gap
0Accepted
Recommendations only — each release needs a named approver's sign-off in its system card.