James Fan
Researching how to make LLM agents safe to deploy — focusing on security gaps in AI agents, such as LangGraph agents.
Previously cofounded two AI startups, led Google Cloud Speech Group, taught at Columbia University and was one of the main inventors of the IBM Watson question answering system that beat the best human contestants on Jeopardy!. Now mostly thinking about what happens when you give an AI agent access to real tools.
Background
AI Startup Cofounder (×2)
Google Cloud — Speech Group
Columbia University
IBM Research — Watson / Jeopardy!
Recent writing
Apr 2026 2. LangGraph Architecture Primer: Understanding the Machine Before You Secure It
security 15 min
Apr 2026 Thoughts on Agent Frameworks
ai 2 min
Apr 2026 3. Mapping the Attack Surface: Everything Your Agent Reads Can Hurt You
security 15 min
Apr 2026 1. LangGraph Agent Security: What I Wish Someone Had Told Me Before I Started
security 18 min
Apr 2026 Openclaw and Bleeding Edge
ai 2 min
Apr 2026 The Claude Code Leak
ai 3 min