Generate an agent draft from a task, streaming its work
Expand a natural-language task into a complete agent draft (a structured prompt with {{input}} placeholders, a name and icon, typed output fields and sample test cases), streamed as Server-Sent Events. The first frame is turn, carrying the generation_id a Stop is sent to; then a step frame for each thing the builder actually did (read_context when the workspace has written its business context, write_instructions, choose_outputs, write_examples, finish), each with its measured duration; then one result frame with the draft.
Failures arrive as an error frame, because the stream has already answered 200: reason limit or paused when the workspace's daily AI Assistant allowance refused the build, stopped when the caller stopped it, and no reason for anything else. Counts against the allowance; a stopped or failed build gives its turn back.
Closing the connection does not stop the build; the Stop route does.
Request
- Base URL: https://api.getoneprofile.ai (the document declares no server; this is the origin it was published from)
- URL: https://api.getoneprofile.ai/table-enrichments/saved-agents/generate/stream/
- Auth: HTTP bearer
Request body
Response
A stream of Server-Sent Events; the final result frame's data is the generated draft.
Changes
No recorded changes to this operation across all 1 revision of this API.