Run a GEO prompt sequence now
Changed onRuns the sequence now. API-based answer engines run synchronously: the request stays open while every turn plays against each of them, which can take several minutes, and checks, mentions and engines report their result. Tracked consumer apps (ChatGPT, Perplexity, Gemini, AI Mode, Copilot) answer far more slowly, so they are queued as a background scan instead: queuedScanId names it and queuedEngines lists the apps it covers. Poll GET /v1/projects/{projectId}/geo/scans/{scanId} for that part. A run with only consumer apps answers right away with checks: 0. Runs also work while automatic scans are paused. Use a client timeout of at least five minutes; after four minutes the API stops waiting and answers 409 while the run finishes on its own. Do not retry; read the result from the project's GEO checks. The work happens inside the Notra dashboard, which owns the model credentials and billing gates; the public API never calls an answer engine itself. Results also land in the project's GEO checks.
Request
- Base URL: https://api.usenotra.com
- URL: https://api.usenotra.com/v1/projects/{projectId}/geo/sequences/{sequenceId}/run
- Auth: HTTP bearer
Path parameters
Response
API-based engines finished; a queued consumer-app scan is named by queuedScanId
Changes
- info
added the optional property
to the response with the status - info
added the optional property
to the response with the status
- info
- info
endpoint added
- info