m4labs:~$ ls research/

What we work on.

agents/
Agents

Systems that plan and carry out multi-step work, and know when to stop and ask. We study how to make them reliable enough to hand real tasks to.

learning/
AI for learning

Tools that help people understand and remember, not just get answers: explanations you can check and practice that adapts to you.

interfaces/
Human-AI interfaces

How people and AI share work: where the AI acts, where you decide, and how you see exactly what it did.

cd ~next: status ->