Getting Started with the OpenAI Agents SDK
Published by O'Reilly Media, Inc.
Building reliable agentic apps
Course outcomes
- Learn how to build end-to-end agent applications using the OpenAI Agents SDK
- Discover how to orchestrate specialized agents to solve complex problems
- Understand and learn to implement simple, effective guardrails and safety mechanisms
- Learn how to create custom tools and integrate with external services
Join expert Lucas Soares to discover how to use the OpenAI Agents SDK, a powerful framework for building sophisticated AI applications that can reason, plan, and take action. You’ll learn to create agent-based systems that can solve complex problems through tool use, handoffs, and structured workflows.
What you’ll learn and how you can apply it
- Build end-to-end agent applications using the OpenAI Agents SDK
- Orchestrate specialized agents to solve complex problems
- Understand and implement simple effective guardrails and safety mechanisms
- Create custom tools and integrate with external services
This live event is for you because...
- You’re a software developer with Python experience.
- You’re an AI/ML engineer who’s looking to build production-ready agent applications.
- You’re a technical product manager who wants to understand the capabilities of agentic systems.
Prerequisites
- Basic programming experience (Python preferred)
- Familiarity with API usage and generative AI
Recommended follow-up:
- Read Building Applications with AI Agents (book)
- Take Working with o1, Deepseek and Gemini 2.0 Reasoning Capabilities (live online course with Lucas Soares)
- Read AI Agents with MCP (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Foundations of agent systems (60 minutes)
- Presentation: Evolution from LLMs to agents; OpenAI Agents core SDK concepts; setting up an AI agent development environment
- Group discussion: What are your current challenges with LLM applications?; personal contexts where agent systems transform your projects
- Hands-on exercise: Build your first “Hello World” creative assistant agent
- Q&A
- Break
Tools and function calling (60 minutes)
- Presentation: Creating and using Python function tools; error handling and advanced tool techniques
- Hands-on exercise: Implement basic tools for weather lookup and data processing
- Q&A
- Break
Agent orchestration and safety (60 minutes)
- Presentation: Multi-agent systems and handoffs
- Hands-on exercise: Create a simple multi-agent workflow with handoffs
- Q&A
- Break
Safety and guardrails (50 minutes)
- Presentation: Guardrails and safety mechanisms
- Hands-on exercise: Add basic guardrails to a multi-agent system
- Group discussion: Roadmap for implementing agent systems in your organization
Wrap-up and Q&A (10 minutes)
Your Instructor
Lucas Soares
Lucas Soares is a machine learning engineer who has worked at K1 Digital and Biometrid, where he developed computer vision and NLP models for applications such as document verification, OCR-based applications, and recommender systems. Lucas has also developed various ML models, including neural networks, Siamese networks, convolutional neural networks, LSTMs, and genetic algorithms.