Skip to main content
List your company’s conversations with Qobra’s AI agents, most recently active first: who talked to which agent, when, and how many changes each one saved. The list covers the Architect, the Analyst, Qobra AI, Facets and the Sales Coach on the live environment, as the AI conversations tab of the audit trail lists them. Flagging conversations show as the Analyst. Filters combine with AND. Each row is a summary: the opening prompt as title, message_count and write_count. Call get_ai_conversation for the transcript, and list_audit_logs with a conversation_id for the changes the conversation saved. Keep paginating while next_offset is set. Requires read access to the audit trail. A conversation stays readable after its agent is switched off.
Example arguments

Parameters

Body

string
The agent talked to: architect, analyst (flagging included), qobra_ai, facets or sales_coach. Omit for every agent.
string
Id or exact email of the user who talked to the agent, as list_users returns them. Omit for every author.
Text the conversation’s title contains, any case.
string
Inclusive lower bound on when the conversation was last active: an ISO-8601 date/time (‘2026-07-01’, UTC unless it carries an offset) or a duration back from now (‘-P7D’). Omit for no lower bound.
string
Inclusive upper bound on when the conversation started, same forms as after. With after, the conversations active between the two. Omit for no upper bound.
integer
Rows per page, 1 to 75. Default 25.
integer
Rows to skip. Omit it for the first page, never null or the string ‘None’; for the next page pass the previous next_offset.

Response

Body

object[]
integer