Josh Tobin
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
How OpenAI Builds AI Agents That Think and Act with Josh Tobin
- Published
- May 6, 2025
- Duration
- 1h 7m
- Summary source
- description
- Last updated
- Jun 21, 2026
Discusses llm, openai, agents.
Summary
Today, we're joined by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s approach to building AI agents. We cover OpenAI's three agentic offerings—Deep Research for comprehensive web research, Operator for website navigation, and Codex CLI for local code execution. We explore OpenAI’s shift from simple LLM workflows to reasoning mo…
Intelligent report
Sign in to read teasers, or upgrade to Research Pro to commission a new dossier for this episode. Learn more →
Show notes
Today, we're joined by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s approach to building AI agents. We cover OpenAI's three agentic offerings—Deep Research for comprehensive web research, Operator for website navigation, and Codex CLI for local code execution. We explore OpenAI’s shift from simple LLM workflows to reasoning models specifically trained for multi-step tasks through reinforcement learning, and how that enables agents to more easily recover from failures
Themes
- llm
- openai
- agents