My new course “Aligning Generative AI with Business Cases” is LIVE on top training platform Pluralsight !   In this course, you’ll learn how to identify, develop, and evaluate suitable use cases for GenAI in your business:   First, you’ll explore how to evaluate and leverage GenAI for your business.   Next, you’ll discover the tools and concepts involved when developing GenAI solutions.   Finally, you’ll learn how to create an agentic AI solution that provides grounded, contextual, and relevant answers in natural language using the latest Microsoft and Open AI technologies.     When you’re finished with this course, you’ll have the skills and knowledge to help you identify, develop, and evaluate suitable use cases for GenAI in your business. ~ Demo Rich This no-fluff course is demo and code heavy.  It's aimed at an intermediate level audience. With 4 modules running just under 60 minutes, the course rapidly accelerates your learning. It shows how to sol

Occasionally, I will hack around on a Raspberry Pi 4 with my son.  Recently, we had been creating a fun home motion detection home security system. We had been using Thonny as it shipped with the Pi installation and was running smoothly. The simple interface was good for my son. I installed Visual Studio Code.  It was unusable. The performance was terrible. The slightest click or cursor movement took ages. The PI has 8GB of RAM so should be fine. After a little digging, it turns out, you need to disable hardware acceleration. ~ Visual Studio Code To do this, press F1 in VS Code, type runtime:   Select: Preferences, Configure Runtime Arguments The file will load, you need to set this to the following: That’s it. Visual Studio Code is now useable in the Pi. In a future post, I will share how we built an AI home security system using .NET, Semantic Kernel, Telegram, and Raspberry Pi. Stay tuned. ~  

My new course “Aligning Generative AI with Business Cases” is LIVE on top training platform Pluralsight !   In this course, you’ll learn how to identify, develop, and evaluate suitable use cases for GenAI in your business:   First, you’ll explore how to evaluate and leverage GenAI for your business.   Next, you’ll discover the tools and concepts involved when developing GenAI solutions.   Finally, you’ll learn how to create an agentic AI solution that provides grounded, contextual, and relevant answers in natural language using the latest Microsoft and Open AI technologies.     When you’re finished with this course, you’ll have the skills and knowledge to help you identify, develop, and evaluate suitable use cases for GenAI in your business. ~ Demo Rich This no-fluff course is demo and code heavy.  It's aimed at an intermediate level audience. With 4 modules running just under 60 minutes, the course rapidly accelerates your learni

In this demo and blog, we take a different direction and look at how to give your AI agent access to your own documents using Retrieval Augmented Generation (RAG). Instead of relying solely on the LLM’s training data, the agent searches a vector store before each response and grounds its answers in your content. Why RAG Matters for AI Agents? LLMs are powerful but they have a fundamental limitation, they only know what they were trained on. They can’t access your internal documentation, product guides, company policies, or domain-specific knowledge. RAG solves this by retrieving relevant documents at runtime and injecting them into the model’s context. The result is an agent that answers questions using your data, not generic knowledge. This is useful when you want your agent to: - answer questions grounded in your data - cite sources so users can verify information - avoid hallucinations by constraining responses to known content RAG also helps your agent stay current without retraining the unde

In earlier posts in this series, we’ve explored how to extend AI agents using function tools, how to compose agents together as function tools, and how to build and debug MCP servers in .NET. In this demo, we look at how you can take an existing AI agent built with the Microsoft Agent Framework and expose it as an MCP tool, thereby making it available to any MCP-compatible client. This is where the two worlds collide. We already know how to build agents. We already know how to build MCP servers. Now we combine them. The idea is simple: take an agent, convert it to a function, wrap it as an MCP tool, and serve it over HTTP. Deep dive code and blog: https://jamiemaguire.net/index.php/2026/02/08/microsoft-agent-framework-exposing-an-existing-ai-agent-as-an-mcp-tool/

In earlier blog posts we created a personal trainer agent.  It featured capabilities to process bookings search for and generate high protein recipes by using function tools and custom service classes. We saw how to implement human develop within the context of a payment scenario. In this blog post we look at how you can give agents access to memory across conversational threads. The following is covered: why give your agent memory overview of AI context provider how to persist agent memory how to fetch agent memory creating a function tool to calculate weight loss time serialising agent memory   We also look at events you can subscribe to when working with agent memory. We see how this can be used to give an LLM additional context or to ensure the LLM has all relevant information before processing a prompt. Code and a demo are included. Let’s dig in.   ~ Why Give Your Agent Memory When people interact with your agent it can be helpful to persist ce

In this demo we see how you build AI agents and advertise them as function tools to other agents. There are a few reasons why you might want to do this. The following is covered: -why implement an agent as function tool -how to implement an agent as function tool -creating a nutrition agent that can find protein rich foods -extending a personal trainer ai agent use the nutritionist agent -implementing the nutrition agent as a function tool -testing personal trainer ai agent new capabilities Dive deeper in the blog: https://jamiemaguire.net/index.php/2025/11/22/microsoft-agent-framework-using-agents-as-function-tools/

In recent blog posts we have implemented at personal trainer agent called Iron Mind AI. We implemented features in this agent to let it make bookings and find high protein recipes using function tools. Consider a scenario where our agent may have to interact with a real-world system such as stripe for payments. In these types of use case, human oversight is required. In this blog post and demo, we’ll see how to implement human in the loop approval when creating agents using the Microsoft Agent Framework. The following topics are covered: -why human in the loop matters -how to implement human in the loop -creating a human in the loop experience to handles payments -extending the Iron Mind AI agent to handle human in the loop Full code and a video demo are also included. Detailed Blog: https://jamiemaguire.net/index.php/2025/12/06/microsoft-agent-framework-implementing-human-in-the-loop-ai-agents/

In recent blog posts we have implemented at personal trainer agent called Iron Mind AI. We implemented features in this agent to let it make bookings and find high protein recipes using function tools. Consider a scenario where our agent may have to interact with a real-world system such as stripe for payments. In these types of use case, human oversight is required. In this blog post and demo, we’ll see how to implement human in the loop approval when creating agents using the Microsoft Agent Framework. The following topics are covered: -why human in the loop matters -how to implement human in the loop -creating a human in the loop experience to handles payments -extending the Iron Mind AI agent to handle human in the loop Full code and a video demo are also included. Detailed Blog: https://jamiemaguire.net/index.php/2025/12/06/microsoft-agent-framework-implementing-human-in-the-loop-ai-agents/

In an earlier blog post, we looked at how you can manage conversations using threads with the Microsoft Agent Framework. In this post, we look at how you can extend an AI agents intelligence using function tools. The following is covered: What is a function tool What can you do with function tools The anatomy of a function tool How to create an agent with a function tool Extending an ai agent to use function tools   A video demo is also included.  Let’s dig in. ~ What Is a Function Tool A function tool is code that your agent can use at run-time when required.  They are like plugins and native functions in Semantic Kernel. Learn more about plugins and native functions in one of my earlier blog posts. Any method you write in C# can be repurposed as a function tool. ~ What Can You Do with Function Tools Function tools let you augment your AI agent’s intelligence.  For example, LLMs have a training cut-off date and no access to your internal or curre

  In last week blog post, we saw how to extend an AI agents intelligence using function tools. In this post, we see how you build AI agents and advertise them as function tools to other agents .  There are a few reasons why you might want to do this. In this blog post we cover: why implement an agent as function tool how to implement an agent as function tool creating a nutrition agent that can find protein rich foods extending a personal trainer agent to use the nutritionist agent implementing the nutrition agent as a function tool testing personal trainer ai agent new capabilities   A video demo and full code examples are included. ~ Why Implement an Agent as Function Tool You might want to use this pattern to isolate behaviours and responsibilities during your AI agent development. With this approach, you can build multiple agents, use them individually, or augment an existing AI agent’s capability with behaviours from other agents. Applying this approach remov