Building Agentic AI: A 5-Week Hands-On Bootcamp with the OpenAI Agents SDK
Details
Welcome to Session 5 of our 5-week bootcamp.
This session will focus on multi-agent systems and how multiple specialized agents can work together to solve more complex tasks. We’ll explore common multi-agent design patterns, including handoffs and agents as tools, and look at when each approach is most useful.
We’ll then bring these concepts together through multi-agent development, building systems where agents can coordinate responsibilities and collaborate as part of a larger workflow.
By the end of the session, you’ll have a stronger foundation for designing agentic applications that go beyond a single agent and use multiple agents effectively.
What We'll Cover
Session 1: Agent Foundations — September 10
- Effective Prompting
- Understanding Tokens
- Models and Instructions
- Building Your First Agent
Session 2: Controlling Agent Behavior — September 17
- Pydantic Fundamentals
- Context and Runtime Data
- Dynamic Instructions
- Structured Outputs
Session 3: Memory and Tools — September 24
- Memory and Context
- Creating Tools
- Tool Calling
- Using Multiple Tools
Session 4: Building More Capable Agents — October 1
- Connecting Agents to Web Search
- Retrieval Augmented Generation and File Search
- Connecting Agents to MCP Tools
- Adding Guardrails
Session 5: Multi-Agent Systems — October 8
- Multi-Agent Design Patterns
- Handoffs
- Agents as Tools
- Multi-Agent Development
Prerequisites: A basic understanding of Python is recommended. You do not need prior experience building AI agents or working with the OpenAI Agents SDK. Familiarity with Python classes, functions, type hints, and basic API usage will help you get the most out of the bootcamp.
You should also create and securely save an OpenAI API key that you'll use throughout the bootcamp to run examples, build agents, and interact with OpenAI models from your Python code. Make sure you can access your key before the session begins.
We hope you join us!
AGENDA
- 6:00 p.m. – Welcome
- 6:05 p.m. – Review Session 4
- 6:10 p.m. – Multi-Agent Design Patterns
- 6:20 p.m. – Multi-Agent Development
- 6:40 p.m. – BREAK
- 6:50 p.m. – Handoffs
- 7:10 p.m. – Agents as Tools
- 7:30 p.m. – Orchestration
- 7:45 p.m. – BREAK
- 7:55 p.m. – Multi-Agent Capstone
- 8:40 p.m. – Questions/Discussion
- 9:00 p.m. – End