Not five separate screens — one connected workspace you move through, from discovery to a defensible choice. Each moment below is a live prototype: try it right in the preview, or open it full-screen. The Next control in any header walks the whole flow end to end.
Intent-first discovery across the project hierarchy and map. One Decision-intent control re-prioritises the whole workspace around what you're trying to do, so the right data surfaces first.
Interrogate one dataset before trusting it. A legible evidence map, explainable confidence and a reasoning layer connect the evidence to the judgment, so the verdict is never a naked number.
Compare viable datasets on decision-relevant evidence rather than raw specs, and see the inherited risk that travels with each option, so the trade-off is explicit before you commit.
The data manager's console — a prioritised queue of what to fix next, with downstream impact and a clear certification path. It closes the loop by producing the trust the other screens rely on.
After a choice is made, an embedded AI companion reviews it like a senior colleague — evidence, trade-offs and a second opinion with a confidence delta. Every recommendation is explained, and final approval always stays with the human. Not a chatbot; responsible AI inside the workflow.