theNotebook

Research

How AI agents plan, predict and act safely.

Three directions I am working on now. All of my papers are under review.

Current directions

Three questions

  • World models for enterprise agents that plan under delayed and asynchronous data.
  • Stress testing event-driven agents to find failures that are rare but costly.
  • Governing what an AI agent is allowed to do before it acts.

Research interests

What I study

Some of these are active directions. They are not areas with results to show yet.

Core

  • World Models
  • JEPA
  • Representation Learning
  • Reinforcement Learning
  • Agentic AI
  • AI Safety and Evaluation

Also

  • Predictive State Modeling
  • Model-Based Planning
  • Adaptive Decision-Making
  • AI Agent Memory
  • Human-AI Collaboration
  • Hybrid Neural Architectures
  • Graph-Based Reasoning
  • AI Governance
  • Enterprise AI Systems
  • AI for Energy and Utilities
  • Adaptive Stress Testing

Application areas

  • Energy and gas utilities
  • Demand response
  • Wildfire risk
  • Customer billing
  • Document intelligence
  • Enterprise workflow automation

Papers

All under review.

  • Offline reinforcement learning for a utility billing assistant

    journal · under review

  • World models for enterprise agents that plan under delayed and asynchronous data

    journal · under review

  • Stress testing event-driven agents to find failures that are rare but costly

    conference · under review

Each paper in three voices

Books

In progress

  • Agents with Foresight World Models for Reliable Action in Digital Enterprises. Read a sneak peek.

    Book · writing

  • The World Outside the Model Engineering AI Agents for State, Authority and Reliable Action. Read a sneak peek.

    Book · writing

Sneak peeks at every book

Search the notebook