OpenAI Agents SDK
Part 2 is the technical core of the book. Here we move from “agent as an idea” to “agent as an engineered system,” using OpenAI Agents SDK as our primary vehicle. Each chapter deepens one specific capability and the primitives set of OpenAI Agents SDK. For each component, we discuss the theory and then apply it to examples and demos as we build practical AI agents and agentic systems.
Specifically, you will extend your agent with tools (from simple functions to hosted tools and agents-as-tools), add memory and knowledge retrieval, and compose multi-agent systems with deliberate handoffs. You will learn how to tune models and context, how to structure multi-agent systems, and how to deploy and monitor them with guardrails and policies.
This part contains the following chapters:
- Chapter 4, Agent Tools and MCPs
- Chapter 5, Memory and Knowledge
- Chapter 6, Multi-Agent Systems and Handoffs
- Chapter 7, Model...