Design an agentic product search experience
PremiumLLM systemHard
- LLM agents
- Tool calling
- Clarifying questions
Quick answer
This LLM system interview question asks you to design an agentic product search experience. Aim for a design that uses language models to serve users well, then explain retrieval, prompting, serving, evaluation and trade-offs. Interviewers want to see how you control quality, cost and latency, and how you evaluate the results.
The problem
Design an agentic product search experience: a shopping assistant in an online store that takes requests like “waterproof hiking boots under $120, wide fit”, calls read-only catalog tools and shows real products. The hard parts are asking clarifying questions only when needed, never breaking a hard constraint, and grounding every result.
The user refines over several turns (“lighter ones”, “only ones that arrive by Friday”). The agent keeps a running list of hard constraints and soft preferences, searches, checks the results and answers with product cards built from catalog data.
What must an agentic product search experience do?
- Hard constraints vs preferences: Hard constraints (budget, size, in stock, delivery date, excluded brands) must hold for every product shown; preferences (colour, “lightweight”) only change the order.
- Clarify only when it matters: Ask at most one clarifying question per turn, and only when the answer would change the results; otherwise show results and offer refinements.
How well must it do it?
- Bounded tool use: At most 6 tool calls and 10 seconds per user message; then answer with what is known.
- Latency: First words within 2 seconds and product cards within 5 seconds at p95.
What scale should you design for?
Use these numbers in your estimates.
The scale numbers unlock with this questionUnlock
Key concepts
- LLM agents
- Tool calling
- Clarifying questions
- Constraint extraction
- Grounded answers
- Prompt caching
How you’ll practise
- Problem framing
- Data and retrieval
- Prompting and orchestration
- Evaluation and safety
- Serving, cost and latency
- Wrap-up
Lala, personalized to you, gives a hint when you ask and reviews your design when you are ready.
What do interviewers look for?
In any LLM system design round.
- Defines the user task and what a good answer is
- Explains how relevant context reaches the model
- Plans evaluation before and after launch
- Controls cost and latency with caching and routing
- Covers safety, privacy and abuse
- Handles failures and fallbacks gracefully
Questions people ask about this interview question
- Which design type is this question?
- It is an LLM system question. You design an agentic product search experience and explain your choices the way you would in an interview.
- Is this question asked at entry level?
- It is marked Hard. It suits engineers preparing for senior interviews, where you are expected to drive the discussion and go deep on trade-offs.
- What should I cover first?
- Start with the user task, what a good answer looks like and how it will be measured. Agree on scope with the interviewer before you design anything.
- Can I practise it for free?
- It is a premium question. Sign up and unlock it once for 10 credits; it then stays unlocked. When you finish, Lala, your personalized AI mentor, can review your design for 30 credits.
Related questions
Updated · Written by the SevyDevy team