Review & Curation

The pipelines propose; a human decides. Review & Curation is the workspace where curators resolve open questions, approve or reject proposed changes, and repair anything that broke - so only reviewed, accepted meaning becomes the truth agents run on. Every action is a governed, versioned change.

The Learning Queue

The Learning Queue is where the semantic layer asks for help. As Colrows scans and reasons over a datasource, it raises typed questions a curator resolves one at a time:

• Missing Category - a coded column whose values need a governed meaning.
• Definition Conflict - two sources disagree on what a term means.
• Semantic Ambiguity - a name or relationship that could resolve more than one way.
• Metric Update and Term Update - proposed changes to an existing metric or business term.

A curator opens an inquiry, reviews the details, and submits a resolution; the item moves from pending to completed. Metric and term updates are shown as an old-vs-new field diff you can approve, reject, or edit inline.

Needs Attention

Needs Attention surfaces assets that fell out of validity - a metric whose table was dropped, a dataset whose column changed - so a curator can repair them. Invalid assets never reach runtime; repairing one re-runs the full validator and, when it passes, restores it to a new valid version. Operators also see processing failures here per datasource.

Pipeline operations

The operations console (Tasks / Pipelines) is where curators and admins drive and watch the build:

• Run and schedule source scans, knowledge generation, publishing, and projection repair; pause and resume schedules.
• Watch run history live, and handle pipeline failures - retry or ignore a failed change so one bad item never stalls the rest.
• Finish onboarding a datasource: profile columns, generate missing descriptions, and publish - moving it from Draft to Ready for AI.

Operation runs report their state as QUEUED, RUNNING, COMPLETED, DEGRADED (completed with issues), FAILED, or CANCELLED.

Manage via API

Review actions are driven from the console, and the same operations are available to administrators and curators on the platform API: