In this third video from my Microsoft Agent Framework series, I continue building a real AI-powered system in ASP.NET Core.
So far, our AI agents work, but they have one major limitation: they forget everything after restart. In this part, we are going to fix that by adding persistent storage and saving conversations in a database using Entity Framework and PostgreSQL.
By the end of this video, you will see:
- how to integrate Entity Framework with your AI agent system;
- how to design entities for conversation storage;
- how to serialize AI messages (including polymorphic content);
- how to implement a DB-based conversation store;
- how to handle LLM message ordering issues.
If you're building real AI systems in .NET - this series is for you.









![Defluffer - reduce token usage 📉 by 45% using this one simple trick! [Earthday challenge]](https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fiekbgepcutl4jse0sfs0.png)


