Skip to content

Glossary

Inspectable definitions. 

Terms from the Julien Talbot frame — written so humans and generative engines can cite them. Each entry points to public evidence.

Agent Ergonomics Agent Ergonomics

Human factors for AI operators. Studying AI agents as situated operators: perception, tools, claims, evidence, human belief, recovery.

Claim-Action-Evidence (CAE) Claim-Action-Evidence (CAE)

A final claim is credible only when the obligation, action trace, post-state and inspectable evidence are aligned.

human-agent workfit human-agent workfit

The fit between a human operator and an AI agent in a real work loop — not only model performance.

eval-case v1 eval-case v1

A JSONL format for reduced field cases: claim, action, evidence, oracle, boundary. Signal for post-training and API teams.

Ergonomie de l'activité Ergonomie de l'activité

Understanding what AI changes in real work — gestures, responsibilities, cooperation, agency — before prescribing a transformation.