Evidence can disagree. It still stays in the case.

Write the hypothesis before the evidence arrives. Attach each interview note, funnel number, and support ticket to the claim it speaks to, whether it supports the claim or contradicts it.

A whole loop on one canvas: the hypothesis, the workstream of tasks it produced, and the evidence and insight linked underneath.

Bring your agents into the loop

Connect Claude, Codex, or Cursor through Model Context Protocol. They can connect directly to a Meridian loop.

Agents stay inside your access

Prima acts on your behalf and cannot open a loop you were not invited to. Human-only actions, including deleting a loop, stay human-only.

Your workspace stays yours

Organization boundaries are enforced in the database on every request. Work from another organization is never returned.

Prima starts with the loop

Ask a question and Prima reads the loop before she answers. Her work goes back onto the same canvas under her own name, where the team can inspect it.

Prima's chat panel docked over the canvas, showing a tool step reading the loop's canvas context and a drafted status update citing the evidence on screen.

Every open question has a state

See which loops are open, which have reached a verdict, and how much evidence and insight each one holds. The activity rail shows what changed and who changed it.

The signed-in home screen listing three loops with their status, evidence and insight counts, alongside an activity rail.

Use the canvas or use the list

Switch to a sortable table when you need status, owner, and due date instead of the whole argument. It is the same set of loops, not a second system to maintain.

The loops table listing every loop with a status pill, owner and due date.

Every Prima chat stays with its loop

Return to the thread that shaped the work without searching a general-purpose chat history. Each conversation names the loop it belongs to.

The chat index, where each conversation with Prima names the loop it belongs to.