How to Build ChatGPT - Part 3: Agentic Search & Agents SDK
Learn how to build your own ChatGPT from the ground up! 🚀 In this series, we cover prompting, RAG, agents, reasoning, and more—rooted in the same journey OpenAI’s product team took, now evolving with GPT-5 and gpt-oss. In Part 3, we dive into the OpenAI Agents SDK and best practices for agentic search.
Join us every Wednesday at 1pm EST for our live events. SUBSCRIBE and RING THE BELL to get notified!
Join our community to start building, shipping, and sharing with us today!
/ discord
Take the AI Engineering Challenge today!
https://bit.ly/4mDP7Cd
For team leaders
https://bit.ly/41YtlA7
LLM Foundations, a free 5-day email-based course
https://bit.ly/4izQVKk
LLM Engineering - Open-Source!
https://bit.ly/42ha7Xy
Speakers:
Dr. Greg, Co-Founder & CEO @ AI Makerspace
/ gregloughane
The Wiz, Co-Founder & CTO @ AI Makerspace
/ csalexiuk
00:00 From LLMs to AI Agents: Intro
06:13 What Is an Agent? Core Definitions
12:12 Agentic Search and Reasoning Patterns
19:19 Context Engineering & Agents
24:22 Complexity, Agency & Workflows
32:00 Single vs Multi-agent Systems
40:52 Agentic Design Patterns & SDK Breakdown
46:38 Live Coding: Building a Research Bot
55:01 Q&A: Agent SDK, Evaluations & Alternatives
01:02:03 Wrap-up & How to Get Started