Strange Lab

We get your company ready for Agents.

We turn the work record into a canonical event spine, find the workflows agents should learn, package the safe ones as governed skills, and check every rollout against what happens next.

The first output is an Agent Deployment Map: what agents can train on, what they can shadow, what they can run, and where a human gate stays in the loop.

The world model sits underneath that map. Pick a point in the record, hide everything after it, test a possible action, and compare the forecast with what came later.

Start with the examples: Bismarck turns one dense PDF into a scored historical forecast, Enron replays internal company forks, and public-history examples test both current macro data and Civil War-era news from dated records.

Agents need more than context. They need company state, task boundaries, policy gates, and a score. That is the job of the work record.

Essays, Papers, and Code