Learn how you can use VS Code Agents, GitHub Copilot, and the MSSQL extension to build apps with Semantic Search with Carlos Robles.

✅ Chapters:
0:00 Intro
1:01 Scenario overview, plan mode
4:08 New Agents experience in VS Code
5:08 App is running, how did it use openspec
7:57 openspec propose
11:00 openspec apply
13:00 investigate and update an issue with vector search
14:51 MSSQL extension, dev containers
16:00 Schema designer with GitHub Copilot integration
17:15 recap


 ✅ Resources:
✔️Resources: 
Check out the MSSQL extension for VS Code: https://github.com/microsoft/vscode-mssql
 
📌 Let's connect:
Twitter - Anna Hoffman, https://twitter.com/AnalyticAnna
Twitter - AzureSQL, https://aka.ms/azuresqltw
 
🔴 Watch even more Data Exposed episodes: https://aka.ms/dataexposedyt
 
🔔 Subscribe to our channels for even more SQL tips:
Microsoft Azure SQL: https://aka.ms/msazuresqlyt
Microsoft SQL Server: https://aka.ms/mssqlserveryt
Microsoft Developer:  https://aka.ms/microsoftdeveloperyt
 
#AzureSQL #SQL #LearnSQL

Microsoft Developer

A walkthrough of building a semantic search app using VS Code's agentic experience, GitHub Copilot, and SQL Server 2025. The demo features a Next.js 'call for papers' app that uses SQL Server vector data types and vector distance for semantic search, with Prisma as the ORM for type safety. The workflow uses OpenSpec for spec-driven development inside VS Code's agent mode, allowing structured feature planning, proposal generation, and code application. The MSSQL extension is used to inspect the database schema, view embeddings, and verify data. A live bug fix is demonstrated where the agent modifies a SQL query to filter out past events, showing how GitHub Copilot agent mode integrates directly with SQL development.

Use VS Code Agents, GitHub Copilot, and the MSSQL extension to build AI apps | Data Exposed