Isa Fulford, Casey Chu, and Edward Sun from OpenAI’s ChatGPT agent team reveal how they combined Deep Research and Operator into a single, powerful AI agent that can perform complex, multi-step tasks lasting up to an hour. By giving the model access to a virtual computer with text browsing, visual browsing, terminal access, and API integrations—all with shared state—they’ve created what may be the first truly embodied AI assistant. The team discusses their reinforcement learning approach, safety mitigations for real-world actions, and how small teams can build transformative AI products through close research-applied collaboration.
Hosted by Sonya Huang and Lauren Reeder, Sequoia Capital
00:00 Introduction
00:54 The Evolution of AI Agents
02:09 Capabilities and Tools of the New Agent
04:03 Combining Deep Research and Operator
06:38 Real-World Applications and Use Cases
13:55 Training and Reinforcement Learning
17:37 Safety and Security Measures
22:31 Team Collaboration and Development
24:43 Challenges and Future Directions
35:57 What’s Ahead
source