outbound-agents

Propose better prompts from the agent's feedback

Rewrite the agent's prompts from what people said needs work (a thumbs down, a note, a rewrite), and return the before and after for each one; a Looks good never trains. Nothing is written until the proposal is accepted. Spends one of the workspace's daily assistant turns.

post/outbound-agents/{agent_id}/proposals/

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/outbound-agents/{agent_id}/proposals/
  • Auth: one of:
    • API key in header X-API-Key
    • HTTP bearer

Path parameters

agent_idstring uuid required

Request body

also_slotsstring[] nullable

Teach the same feedback to these prompts too, even though none was given on their messages. Feedback names the one message it was given on, so without this a note on the opener can only ever change the opener. Each prompt is still rewritten against its own wording.

revision_requeststring

What to change about a proposal already seen.

slot_keysstring[] nullable

Only rewrite these prompts; every prompt that has feedback when null.

Response

Successful Response

agent_idstring uuid required
base_versioninteger required
feedback_countinteger required
feedback_cutoffstring date-time nullable
feedback_idsstring[] required

Changes

No recorded changes to this operation across all 1 revision of this API.