Get an agent task
Poll this every 30-60 seconds while a task runs; a typical task settles in about five minutes. `resultingRoute` is the page a `build_page` task produced. It is always empty for a `prompt` task, even on success: a free-form turn has no single route, and its result is the chat thread at `chatUrl`. `error` is present only when `status` is `failed`.
Authorization
tenantApiKeyAuth In: header
Path Parameters
uuidResponse Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl -X GET "https://example.com/api/v1/public/brands/string/tasks/497f6eca-6276-4993-bfeb-53cbbbba6f08/"{ "taskId": "e6e9d88a-9b63-468a-aec3-b7a11de27af8", "command": "prompt", "status": "running", "createdAt": "2019-08-24T14:15:22Z", "finishedAt": "2019-08-24T14:15:22Z", "resultingRoute": "string", "chatUrl": "string", "error": "string"}Last updated on
Start an agent task
Run one autonomous agent turn for this brand. `command: "prompt"` takes a free-form `prompt`, the instruction the agent carries out ("Add an About page with a team section"). `command: "build_page"` takes an `opportunityRef` from the page-opportunities list and builds that page. A task takes about five minutes. Poll the task detail route every 30-60 seconds, or watch the chat thread the response links to. **One task at a time per brand.** A second create while one is running answers 409: the agent holds a single workspace per brand, so it runs tasks one after another rather than queuing them. Wait for the running task to settle, then submit the next one.
Get AI visibility
One projection per call, selected with `view`: - `kpis`: visibility score, share of voice, rank, average position and citation share, each with its previous value - `trend`: the same headline numbers over time - `share_of_voice`: the entity leaderboard, brand and competitors together - `platform_matrix`: the same picture split by assistant - `prompt_scores`: per tracked prompt, how often the brand is mentioned - `citation_gaps`: domains assistants cite for competitors but not for this brand - `top_sources`: what assistants cite most in this category Start at `kpis` and follow the weak number into the view that explains it. If `enabled` is false, tracking is off for this brand and every row is empty. That is an absence of measurement, not a score of zero.