platform-guideline checked
Responsible AI for Agent Design
Documents responsible AI principles for agents, including transparency, making capabilities and limitations clear, safety filters, accountability, privacy, security, and informed user decisions.
Pattern Decisions This Source Supports
| Pattern | Supported decision | Required contract | Claim note |
|---|---|---|---|
| AI agent acts without approval | Flag this anti-pattern when an AI agent or automation executes a high-impact side effect without showing and requiring approval for the exact action and payload first. | The agent distinguishes read-only steps, draft steps, reversible local changes, and external side-effect steps before execution. | Supports transparency, safety, accountability, informed decisions, security, and privacy requirements for agent design. |
| AI limitation onboarding | Choose AI limitation onboarding when the user needs first-use or changed-capability orientation about AI benefits, limits, data scope, uncertainty, feedback, human responsibility, and fallback. | The onboarding explains what the AI can help with and what it is not able to do before the first risky use. | Supports transparency, capability and limitation disclosure, safety filters, accountability, and informed user decisions. |
Evidence Role
This source is treated as platform-guideline evidence. Use it to validate the decision rules above, not as a visual style reference.
Publisher: Microsoft Learn. Last checked: .