Skip to content

Interview question · Identity, OAuth & Access Control

An AI agent acts on behalf of a user. Whose identity does it use, which scopes, and how is access revoked?

A service account is the easy answer and the wrong one. The interviewer wants both identities visible in every call, scoped to the task, and revocable by the user.

hardNewPreparation tags: Anthropic, OpenAI, MicrosoftUpdated Nov 2026

A service account is the easy answer and the wrong one. The interviewer wants both identities visible in every call, scoped to the task, and revocable by the user.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

signing in unlocks more free answers per topic

What if · the follow-ups in this answer

The answer works through 6 follow-ups like an interviewer would

An email agent acts for a user and needs to read their mailbox and create calendar events, and the team proposes giving it a service account with access to all mailboxes.

  1. Why not a broad service account?
  2. What authority should the agent have instead?
  3. How does the agent get that token?
  4. What should be logged?
  5. How is access revoked?
  6. What identity design would you implement?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Sign in free to open it.

UP NEXT ON YOUR JOURNEY
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.