Product design question

How would you design Project Mariner (web-browsing agent) to safely book things on a user's behalf?

Practice this question out loud. An AI interviewer asks it, follows up like a real interviewer would, and scores your answer. Type or speak.

Start a mock interview on this question · Mock interview from a job description

What this question tests

Product design for a high-stakes autonomous agent taking real-world actions (payments, bookings) on a user's behalf.

How to approach it

  1. Clarify the scope: a web-browsing agent completing tasks like booking a flight or purchasing an item using the user's own accounts and payment methods.
  2. Design explicit consent checkpoints: the agent must show a clear summary of the exact action (price, dates, cancellation terms) and get explicit confirmation before any payment or irreversible booking action.
  3. Set autonomy boundaries by action type: low-risk browsing and comparison steps can run freely, while payment or irreversible actions always require a final human approval.
  4. Add transparency during execution: a live, human-readable log of what the agent is doing, so the user can intervene if it goes off track.
  5. Add safety rails against manipulation: since the agent interacts with arbitrary websites, it must resist deceptive page content designed to trick it into unwanted actions.
  6. Define success as task completion rate with zero unauthorized charges or bookings, tracked as the primary trust metric above raw speed or convenience.

What a strong answer includes

Common mistakes

Likely follow-up questions

More product design questions

More questions from Google DeepMind

Learn the skill behind it

Chapters of the AI PM course that teach what this question tests.

Preparing for a specific role?

Book summaries for this kind of question

Browse all 4,000+ questions in the bank