Student pricing is available for eligible university email holders. View plans

NextSprints
NextSprints Icon NextSprints Logo
Product Design

Master the art of designing products

Product Improvement

Identify scope for excellence

Product Success Metrics

Learn how to define success of product

Product Root Cause Analysis

Ace root cause problem solving

Product Trade-Off

Navigate trade-offs decisions like a pro

All Questions

Explore all questions

Meta (Facebook) PM Interview Course

Practice Meta-focused PM cases

Amazon PM Interview Course

Practice Amazon-focused PM cases

Apple PM Interview Course

Practice Apple-focused PM cases

Google PM Interview Course

Practice Google-focused PM cases

Microsoft PM Interview Course

Practice Microsoft-focused PM cases

All Courses

Explore all courses

1:1 PM Coaching

Practice in a one-to-one session

Resume Review

Narrate impactful stories via resume

Guides Pricing
nextsprints logo

Not a member?

By proceeding, you agree to our Terms of Use and confirm you have read our Privacy and Cookie Statement.

nextsprints logo

Register to continue.

Login with Google Login with LinkedIn

By proceeding, you agree to our Terms of Use and confirm you have read our Privacy and Cookie Statement .

Company focus

MercadoLibre
Product Design Hard Member-only

Design an AI shopping assistant in the Mercado Livre app for first-time online shoppers in Brazil.

Prepared by NextSprints

15 mins
Report an error
AI Product Sense User Segmentation Solution Design E-commerce Artificial Intelligence E-Commerce Product-Design Ai-Assistant Brazil
Product Management Product Design Question: AI shopping assistant for first-time online shoppers on Mercado Livre

Introduction

Brazil still adds millions of first-time online shoppers every year, many of them from classes C and D and from cities outside the São Paulo–Rio axis. For them, the hard part of buying on Mercado Livre is not finding a phone case. It is trusting a seller they can't see, choosing between Pix, boleto and "12x sem juros", entering a CPF and CEP correctly, and knowing what to do if the package never arrives. MercadoLibre already uses GenAI widely: a Seller Assistant used by sellers representing nearly half of GMV, and an AI shopping assistant in testing with part of buyers. I'll design that assistant specifically for first-time buyers, covering goals, segments, pain points, the solution, AI risks and metrics.

Tip

This is a hard question because it mixes UX and AI risk. I'd tell the interviewer up front that I'll spend real time on guardrails and evaluation, not just on the chat interface.

Step 1

Clarify Questions (3 minutes)

  • How do we define "first-time online shopper"?

  • Why it matters: Someone new to Mercado Livre but experienced on Shopee needs a different product.
  • Hypothetical answer: Users with no completed online purchase on any platform, based on onboarding answers and signals such as no saved cards and no purchase history in Mercado Pago.
  • Impact: The assistant must explain basics (delivery, payment, returns), not only recommend products.
  • What is the business goal: first purchase, or a second purchase?

  • Hypothetical answer: Conversion to a first purchase that goes well, followed by a second purchase within 60 days.
  • Impact: I'll avoid designs that push a risky first order just to hit conversion.
  • Can the assistant take actions, or only answer?

  • Hypothetical answer: It can build a cart, apply coupons and start checkout, but the user always confirms payment.
  • Impact: This is light agentic commerce with a human confirmation step.
  • Any constraints on sponsored products?

  • Hypothetical answer: Mercado Ads is a big revenue line, but the assistant's recommendations should be trusted.
  • Impact: I'll set clear rules for ads inside the assistant.

Propose the Goal

Help first-time Brazilian shoppers complete a first purchase on Mercado Livre that arrives as expected, so they come back for a second one.

Define the Scope

A conversational assistant ("Assistente Meli") inside the Mercado Livre app in Portuguese, with text and voice input, covering discovery, decision, checkout and post-purchase. Seller-facing tools and the web desktop experience are out of scope.

Tip

I'll pause here to confirm scope, then explain why this is worth building now.

Subscribe to access the full answer

Image of author NextSprints

NextSprints

Updated Oct 31, 2026