Model Dossiers

Which model is suited to which job? Model Dossiers brings reviewed model evidence together with evaluations, receipts, and history from your own projects, so you can choose with both shared evidence and your work in view.

A track record, not a benchmark

The reference records reported capabilities, limitations, and evidence model by model. Published evidence is labelled with its source and conditions. Project evaluations, receipts, and history remain private to your tenant and are presented alongside the shared reference.

Strengths only when the evidence says so

A dossier does not guess. It names a strength or a weakness only when the numbers separate a model from its peers measured the same way: at least ten observations, a material gap, and a margin of error that clears the pack. Every figure shows its sample size, its range, the conditions it was measured under and the receipt it came from. What a model's profile only declares is labelled as declared, never passed off as a measurement.

“Which of my models is most reliable for chapter drafts, and what is that based on?”

You choose, with the record in front of you

The dossier informs your choices; it never makes them. Use shared evidence and your own project history to decide which model to put on a kind of task, and which two or three contenders to bring into a Workshop run. Nothing in a dossier switches a model, reroutes a task or changes your setup on its own.

Ask in plain language

Open Model Dossiers in the Command Center, or ask the assistant: "What is this model good at?" or "Which model should I use for coding?" The answer brings the published reference together with your project evaluation history.

Included reference

Model Dossiers is part of the core studio in every package. Shared evidence and project-specific evaluations, receipts, and history appear together while remaining in their respective privacy boundaries. Eval provides the evaluation workspace.