Blog
Blog posts on .NET, AI, Azure, and more.
Set up GitHub Codespaces for a .NET 10 application
November 05, 2025 by Anuraj
dotnet csharp
In this blog post, we’ll explore how to setup GitHub Codespaces for a .NET 10 application. Microsoft will be releasing the latest version of .NET: .NET 10. This is the newest long term supported version of the Microsoft’s development platform. If you are unable or unsure about installing the latest .NET version on your local machine, developing using GitHub Codespaces is a great alternative. In this article, I will walk you through how to set up a GitHub Codespace for a .NET 10 application. We will cover the following:
Using MCP Tools for your AI Agent
November 04, 2025 by Anuraj
dotnet csharp AI mcp
In this blog post, we’ll explore how to use MCP Tools for your AI agent using Microsoft Agent Framework and MCP Client SDK. I will be using almost same code as my earlier post. Instead of the custom tool, I will be using the Playwright MCP server and expose the tools from the MCP to the AI Agent.
Build your first AI Agent using Microsoft Agent Framework
October 30, 2025 by Anuraj
dotnet csharp AI
In this blog post, we’ll explore how to build your first AI agent using Microsoft Agent Framework. Microsoft Agent Framework is an open-source development kit for building AI agents and multi-agent workflows for .NET and Python. It brings together and extends ideas from Semantic Kernel and AutoGen projects, combining their strengths while adding new capabilities. Built by the same teams, it is the unified foundation for building AI agents going forward.
10 Practical C# Tips for Clean and Reliable Code
October 09, 2025 by Anuraj
dotnet csharp
In this blog post, we’ll explore top 10 Practical C# Tips for Clean and Reliable Code.
Passing images to LLMs in C# with Microsoft.Extensions.AI
September 22, 2025 by Anuraj
dotnet csharp AI
In this blog post, we’ll explore how to send images to LLMs for analysis in C# with Microsoft.Extensions.AI. Recently while working on chat application, I realize I couldn’t find any samples where we will be sending images to multi model LLMs to analyze the image. So I explored a little bit. Initially I used to convert the image to base64 and send it along with the prompt, but it didn’t worked as expected because of the token window constraints. Then I explored a little bit more and found this.
Copyright © 2025 Anuraj. Blog content licensed under the Creative Commons CC BY 2.5 | Unless otherwise stated or granted, code samples licensed under the MIT license. This is a personal blog. The opinions expressed here represent my own and not those of my employer. Powered by Jekyll. Hosted with ❤ by GitHub