This is a step-by-step walkthrough for onboarding to OpenAI Codex. It covers installing the CLI and VS Code extension, configuring your workflow with agents.md and config.toml, and applying effective prompting patterns. The session also dives into advanced use cases, including integrating external tools via MCPs, running Codex programmatically in headless mode, and building multi-agent systems with the Agents SDK.
A deep dive into building sophisticated voice agents using OpenAI's Realtime API and Agents SDK. The session covers architectural patterns like chained vs. end-to-end models, the use of multi-agent systems with handoffs for specialized tasks, and best practices for production including debugging with traces, implementing guardrails, and creating robust evaluations.
A deep dive into building agentic systems using OpenAI's latest APIs. The session covers the core concept of 'agentic tool calling' (reasoning + tools), outlines a four-part framework (Agent, Infrastructure, Product, Evaluation) for designing long-horizon tasks, and provides a hands-on demonstration of building a non-blocking task processing system with a real-time progress UI.