Interview Questions › AI Product

AI cooking assistant for a recipe app

Swiggy wants an AI assistant that suggests what to cook from what you have at home and adds missing items to an Instamart cart. Design it.

Context

Users vary from students to families. Some have dietary restrictions or allergies.

Clarifying questions to ask first

• Who is the main user?
• How does the assistant know what is at home?
• How are allergies captured?

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

• Simple input (photo or quick list)
• Hard constraint filters for allergies, not left to the model
• One-tap add missing items

1. Eval set of pantries and restrictions with expected safe outputs
2. Measure suggestion-to-cart and cart-to-order
3. Track allergy violations as a zero-tolerance metric

Start with a photo-or-list input for students and young families, enforce allergies with rules outside the model, and measure missing-item cart conversion with allergy violations at zero.

What interviewers look for

• Recipes cooked
• Instamart conversion
• Allergy-safe suggestions