Skip to main content
Artifacts are the tangible outputs workflow runs produce: posts, calendar entries, documents, files, CRM diffs, and CSVs. The Artifacts API backs the Results Vault in the Command Center and powers the quality flywheel. All endpoints are scoped to the authenticated workspace. Requests without a workspace return HTTP 401.

The artifact object

Key fields on every artifact:

List artifacts

Returns artifacts for the workspace, newest first. Query parameters:

Get the content calendar

Returns up to 100 post artifacts ordered by scheduled date, formatted for the Command Center calendar view, plus counts by status:

Download an artifact

Streams the artifact’s raw content as a file attachment. csv artifacts download with a .csv extension and text/csv content type; all other types download as .md with text/markdown. The filename is derived from the artifact title and a short ID suffix. Returns HTTP 404 if the artifact is not found in the workspace.

Update artifact status

Moves an artifact through its lifecycle. Body fields:

Evaluate an artifact

Re-scores the artifact against the quality rubric (brand alignment, actionable CTA, factual integrity, formatting) and updates its qualityScore, qualityGrade, and verificationNotes in place.
An artifact passes when its composite score is 70 or higher and it contains no template placeholders. Grades map to score bands: A (88+), B (75-87), C (60-74), F (below 60).

Refine an artifact

Rewrites the artifact and saves the result as a new revision. Body fields: Refinement evaluates the original content, then rewrites it with Gemini (gemini-2.5-flash) when a Google AI API key is configured. Without a key, it falls back to deterministic placeholder and filler cleanup. It then re-evaluates the result and inserts a new artifact with an incremented revisionVersion and parentArtifactId set to the original. The original artifact is never modified.

Get artifacts for a run

Returns all artifacts produced by one workflow run, oldest first. See the Runs API.