Major project
Retail, E-commerce & Consumer Goods
Retail capstone: production multilingual shopping assistant
Solve a real retail or e-commerce problem end to end, such as a multilingual shopping assistant, with monitoring and a security review.
The brief
Indian shoppers ask questions in many languages. Build and deploy a multilingual shopping assistant (or another retail AI product you scope with your mentor) with cost controls, monitoring and a security review. Good looks like: a deployed product, measured quality in each language, a security review, and a demo for a panel.
What you will build
- Scope the problem and success measures with your mentor
- Build the assistant with catalogue grounding
- Support English, Hindi and one more language
- Review security against the OWASP Top 10 for LLM applications
- Deploy with monitoring and cost limits
- Present the results to a panel
Free, open data to build it with
- Shopping Queries Dataset (ESCI) ↗ Amazon Science (GitHub)
- OWASP Top 10 for LLM applications ↗ OWASP
Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.