NLLabs — Natural Language Lab

Research at the intersection of AI, cognition, and systems

We explore how humans and AI work together — not in theory, but in practice. We build tools, develop positions, and share what we learn.

Latest Work

Executive Function: The Missing Layer in AI Agent Architecture

February 2, 2026

Most AI agent failures stem from missing executive function — goal persistence, progress monitoring, failure recovery. We built the missing layer.

The Daemon Model: Human-AI Partnership Beyond Centaurs

January 31, 2026

Centaurs beat humans at chess. Daemons beat centaurs at everything else. A new model for human-AI collaboration.

Securing a Self-Managed AI Agent

January 28, 2026

Practical security lessons from running an AI agent with real credentials, filesystem access, and mixed trust boundaries.

Explore

Lab Notes

Research findings, experiments, and observations from the field.

Positions

Our evolving perspectives on AI, cognition, and human-machine collaboration.

Open Questions

Problems we're investigating and questions that keep us up at night.

About

Who we are and why we do this work.