Interview Questions › AI Product

An AI agent that books trips end to end

MakeMyTrip wants an AI agent that plans and books a whole trip (flights, hotel, cabs) from one request. Design it, and explain how you would stop it making costly mistakes.

Context

Bookings involve real money and cancellation fees. Prices change minute to minute.

Clarifying questions to ask first

• Which trip types first?
• Does the agent pay automatically or ask for confirmation?
• How does it handle price changes?

How to approach it

1. Start from the user problem, not the model: is AI the right tool here?
2. Describe the experience and where the model fits in it
3. Define what "good output" means and how you would evaluate it before and after launch
4. Name the failure modes (wrong answers, bias, privacy, cost) and how you contain them
5. Close with a launch plan and success metrics

Framework: User and problem -> Is AI the right tool? -> Experience design and human-in-the-loop -> Quality bar and evaluation -> Risks, cost and latency -> Staged launch and metrics

Sample answer

• Agent plans, human confirms one itinerary with total price
• Hard checks on dates, names and refund rules before payment
• Narrow scope first (domestic weekend trips)

1. Simulated booking tasks with expected itineraries
2. Booking error rate (wrong date, name, city) as a launch gate
3. Support contacts and cancellations per agent booking

Start with domestic weekend trips: the agent drafts a complete itinerary, the user confirms once with the full price, and rule-based checks run before payment. Launch only when booking error rate is below the human-booking baseline.

What interviewers look for

• Trips booked via agent
• Booking error rate
• Cancellations and support contacts