chapter one

1 From Conventional Code to Agents

 

This chapter covers

  • The rise of Generative AI and Large Language Models (LLMs)
  • Key features of Agent Framework for AI integration
  • Comparison with other AI tools such as LangChain and ML.NET
  • Overview of Agent Framework architecture and components

Generative AI and Large Language Models (LLMs) are increasingly integrated into software development workflows. Here, we explore how Microsoft Agent Framework enables .NET developers to incorporate agents and agentic AI into their applications in the .NET ecosystem. Through intuitive analogies, we'll discuss the architecture and components of these tools so we can become proficient practitioners in the AI-driven era of programming.

1.1 Introducing Microsoft Agent Framework

Let's take a look at Agent Framework, an SDK for building AI agents and multi-agent workflows in .NET. Instead of wiring models, tools, and orchestration by hand, we use Agent Framework to define agents, connect them to LLMs and other services, and coordinate them into reliable workflows that solve real problems in our applications.

Note

We’ll use Agent Framework instead of Microsoft Agent Framework for brevity. The official name remains Microsoft Agent Framework.

1.1.1 The Rise of Generative AI and LLMs

1.1.2 Why Agent Framework?

1.2 Agent Framework and Other Frameworks

1.2.1 Agent Framework and Microsoft.Extensions.AI

1.2.2 Agent Framework and LangChain

1.2.3 Agent Framework and Microsoft ML.NET

1.2.4 A Glimpse into Agent Framework Code

1.3 How Agent Framework Works

1.3.1 Human Body Analogy

1.3.2 Primary Components of an Agent

1.3.3 Stateless Agent Architecture

1.3.4 Standard Agent Architecture

1.3.5 Enterprise-Ready

1.4 Conclusion

1.5 Summary