Building Agents with OpenAI Agents SDK : Create Practical AI Agents and Agentic Systems Through Hands-On Projects.

Format:

Book

Author/Creator:

Habib, Henry.

Language:

English

Subjects (All):

Artificial intelligence.

Computer programming.

Chatbots.

Application program interfaces (Computer software).

Physical Description:

1 online resource (277 pages)

Edition:

1st ed.

Place of Publication:

Birmingham : Packt Publishing, Limited, 2025.

Summary:

Master OpenAI's Agents SDK to design production-ready AI agents and agentic systems that solve real-world problems with practical guidanceGet your book with a free PDF, AI Assistant, and Next-Gen Reader Key Features Gain a complete understanding of the OpenAI Agents SDK features including models, tools, memory, guardrails, orchestration, tracing.

Contents:

Cover

Title Page

Copyright Page

Contributors

Table of Contents

Preface

Your Book Comes with Exclusive Perks - Here's How to Unlock Them

Part 1: AI Agents

Chapter 1: Introduction to AI Agents

Technical requirements

Overview of AI agents

What is an AI agent?

Understanding AI agents with a simple analogy

Strengths and weaknesses of AI agents versus traditional systems

Practical applications of AI agents

Productivity gains

Better interactivity

New businesses

Build methodology of AI agents

Anatomy of an AI agent

Model

Tooling interface

Memory and knowledge

Design patterns

CoT

ReAct (Reasoning + Acting)

Planner-execution

Hierarchical/multi-agent

Summary

Chapter 2: Introduction to OpenAI Agents SDK

Design features of OpenAI Agents SDK

Framework for building AI agents

Multi-agent orchestration

Minimal abstraction

Pythonic, extensible, and open sourced

Core primitives

Agent

Runner

Tools

Handoff

Guardrails

Tracing

Chapter 3: Environment Setup and Developing Your First Agent

Environment setup

Python version and dependencies

Project directory, virtual environment, and installations

Registering for OpenAI API and setting up the API key

Verifying the environment setup

Alternative methods: Google Colab

Development prerequisites

Python functions architecture

Python asynchronous programming

Python Pydantic data validation

Developing your first AI Agent

A simple customer service agent

Adding a tool

Adding a handoff

Part 2: OpenAI Agents SDK

Chapter 4: Agent Tools and MCPs

Using custom tools with Python functions

Defining a new tool

Agent and tool behavior

Tool choice.

Tool use behavior

Complex tool inputs with Pydantic

Examples of custom tools

Arithmetic computation tool

External API call tool

Database query tool

Chained tool calls

OpenAI hosted tools

WebSearchTool

FileSearchTool

ImageGenerationTool

CodeInterpreterTool

Handoff versus agent-as-tool patterns

Functionality

MCP

What is MCP?

Adding an MCP server as a tool

Chapter 5: Memory and Knowledge

Working memory

Managing inputs and responses

Chat conversations

Conversation management with Sessions

Managing large conversation threads

Sliding message window

Message summarization

Long-term memory

Persistent message logs

Structured memory recall

Training knowledge

Retrieved knowledge

Unstructured data

Document ingestion

Retrieval

Using vector stores and FileSearchTool in the Agents SDK

Limitations

Chapter 6: Multi-Agent Systems and Handoffs

Multi-agent orchestrations

Deterministic orchestration

Dynamic orchestration

Handoffs in OpenAI Agents SDK

Introduction to handoffs

Multi-agent switching

Customizing handoffs

Handoff prompting

Multi-agent patterns

Centralized system

Hierarchical system

Decentralized system

Swarm system

Chapter 7: Model and Context Management

Model management

Adjusting the underlying model

Adjusting the model settings

Third-party models

Context management

Local context

Chapter 8: Agent System Management

Agent visualization

Input guardrails

Output guardrails

Logging, tracing, and observability

Custom traces and spans

Grouping multiple traces and spans together

Disabling traces

Agent testing.

End-to-end testing

Unit testing

Part 3: Build AI Agents

Chapter 9: Building AI Agents and Agentic Systems

Building a customer service employee AI agent

Setting up the database

Setting up a vector store

Creating a function tool to query data

Creating a vector store search tool

Creating an input guardrail

Creating a retention agent

Creating a customer service agent

Building the runner

Testing the agent

Orchestrating an automated multi-agent workflow

Setting up a customer database

Setting up the transcripts JSON

Creating function tools to retrieve data and search the web

Creating the customer research agent

Creating the email creation agent

Orchestrating the workflow

Testing the workflow

Packt Page

Other Books You May Enjoy

Index

Blank Page.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

1-80611-200-0

OCLC:

1543000013