Skip to main content
Send a conversation as raw text. The API parses it into messages, stores it as a run, and returns the speakers it found plus a guess at which one is your agent. Nothing is audited yet — the run is parked until audit_launch confirms the agent. Send the text exactly as you have it. Timestamps, usernames, join/leave notices, and platform decoration are all handled; you do not need to strip or reformat anything.

Authorization

string
required
Your bearer token: Bearer <token>. See Authentication.

Request body

string
required
The conversation, as text. 1–300,000 characters. Longer than that is rejected with 422 before any charge.

Request

Response

string
The run’s id. Pass it to audit_launch and to audit-run.
integer
How many messages were parsed out of your text. The whole transcript is stored — nothing is dropped.
string[]
Every speaker found, in the order they first speak. These are exactly the values audit_launch accepts as agent_name.
string | null
Which speaker looks like an AI agent. Use it to pre-select an option; do not treat it as the answer. null when the transcript gives no clear signal, which is a normal result and not an error.

Errors

The over-cap message names both numbers so you can act on it:
Send the most recent 250 messages and call again. See Size limits. Next: Launch a run.