Build a RAG assistant that answers from data in Azure SQL, with security and monitoring.
A support team wants answers drawn from product manuals and order data stored in Azure SQL.
The detailed steps, checklists and trainer review open in the SOTT student portal for enrolled students.
E-commerce: Checkout that stays fast at sale time. Slow queries made checkout time out during sales. Indexes, query tuning and read replicas for reports. Checkout stayed fast through the biggest sale.
Banking: No data lost in an outage. Nobody had tested restoring the core database. Automated backups, point-in-time restore and regular restore drills. A restore drill met the agreed recovery time.
Insurance: Faster answers from policy documents. Agents searched long PDFs to answer customer questions. A retrieval-augmented assistant answers with citations to the exact clause. Handling time fell and answers became consistent.
Yes. Once your trainer approves it, list it under Projects with the tools you used, one line on the problem it solves and a link to your repository and demo video.
About 18 hours of hands-on work, and it fits best after week 12 of the Azure SQL AI Developer (DP-800) course.
Enrolled students get every task with steps, "done when" checks, the submission form and a trainer review in the SOTT student portal.