platform-guideline 1 linked patterns checked
Audit logs for Copilot and AI applications
Documents audit records for Copilot and AI application user interactions, admin activities, accessed resources, user, time, location, retention, AIAppInteraction records, and response-generation context.
Read with a purpose
What this source can teach
Use this source to understand a platform convention and the setting it was designed for.
- Start with the original. Open the source and find the guidance or example relevant to your task.
- Trace the connection. Use the claim notes below to see how this site applies the source to specific patterns.
- Check the setting. Compare the source's platform, people, and constraints with your own decision.
Pattern Decisions This Source Supports
| Pattern | Supported decision | Required contract | Claim note |
|---|---|---|---|
| AI output audit trail | Choose AI output audit trail when the task is to inspect or prove how a specific AI-generated output was produced, changed, approved, copied, applied, exported, or retained. | Users can open the trail from the generated output, applied object, activity record, or investigation result without losing the answer identity. | Supports AI application interaction audit records, accessed resources, users, timestamps, location, retention, and admin activity context. |
Comparisons supported by this source
- AI output audit trail vs activity log vs source grounding display vs confidence uncertainty display vs editable AI output vs regenerate retry vs agent progress trace vs human approval gate
Supports AI interaction audit records, accessed resources, user, time, location, and retention.
Evidence Role
This source is treated as platform-guideline evidence. Its value comes from the specific claims and setting described above.
Publisher: Microsoft Learn. Last checked: .