After this course you can build database solutions on SQL Server, Azure SQL and SQL databases in Microsoft Fabric that use AI directly. You generate and maintain embeddings, set up vector and hybrid search and pass query results to a language model through RAG. You also cover data protection with encryption and Row-Level Security, analysing slow queries and deploying with SQL Database Projects. The course suits you if you already write T-SQL and develop databases and now want to connect AI applications cleanly to your data.
What you’ll take away.
- Design tables, JSON columns and programmability objects, and query them with advanced T-SQL
- Protect data with encryption, Dynamic Data Masking and Row-Level Security
- Version, test and deploy database changes with SQL Database Projects
- Generate embeddings and implement full-text, vector and hybrid search
- Pass query results to a language model with RAG and process the response
Your training in detail
- Who is it for?
- Database developers, data engineers and DBAs who want to implement AI features directly on Microsoft SQL platforms and give applications a dependable data layer.
- Prerequisites
- You write T-SQL confidently and have developed databases on SQL Server or Azure SQL. Basic knowledge of CI/CD with GitHub and of terms such as embedding and vector is helpful.
- Format & planning
- Standard length: 4 training days. A different length can be arranged for companies.
Agenda: from understanding to application
Our independently developed agenda proposal. Focus areas, lab environment and scope are agreed before booking.
Designing database objects: tables, specialised tables, JSON, constraints and partitioning
Advanced T-SQL: CTEs, window functions, JSON and regex functions, graph queries
AI-assisted development with GitHub Copilot, instruction files and MCP endpoints
Security and performance: encryption, masking, RLS, execution plans and Query Store
CI/CD with SQL Database Projects and REST or GraphQL access through Data API builder
Connecting external models, chunking text and keeping embeddings up to date
Intelligent search and RAG: vector and hybrid search, RRF and model calls from T-SQL
You build a hybrid search for a product catalogue: generate embeddings for the descriptions, create a vector index, merge full-text and vector hits with RRF and pass the top results to a language model as JSON.
Exams, licences & credentials
The course prepares you for exam DP-800 for the Microsoft Certified: SQL AI Developer Associate certification. The exam and its fee are only included if the offer explicitly confirms this. The certificate is issued by Microsoft. This is not an official Microsoft course unless the offer states otherwise.
Vendor references & review date
Sources checked on 2026-11-10. These sources describe the technology or external exam requirements. They do not imply a partnership with NextNowa.
Your learning content
These objectives describe the training topic. The specific syllabus, dates and trainer are agreed before booking; the written offer is binding.
Frequently asked questions
Which platforms does the course cover?
SQL Server, Azure SQL and SQL databases in Microsoft Fabric. These are the three platforms Microsoft names for exam DP-800.
Do I train my own AI models in the course?
No. You connect existing models, generate embeddings and use them for search and RAG directly from the database.
How long is exam DP-800?
Microsoft states 120 minutes. According to Microsoft, you need a score of at least 700 to pass.
Does DP-800 Developing AI-Enabled Database Solutions: AI features in SQL databases include a certificate?
The course prepares you for exam DP-800 for the Microsoft Certified: SQL AI Developer Associate certification. The exam and its fee are only included if the offer explicitly confirms this. The certificate is issued by Microsoft. This is not an official Microsoft course unless the offer states otherwise.