> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qobra.co/llms.txt
> Use this file to discover all available pages before exploring further.

# list_ai_conversations

> List your company's conversations with Qobra's AI agents, most recently active first, to review who asked which agent what and how many changes each saved.

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`](https://docs.qobra.co/mcp_documentation/tools/get_ai_conversation) for the
transcript, and [`list_audit_logs`](https://docs.qobra.co/mcp_documentation/tools/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.

```json Example arguments theme={null}
{
  "agent_type": "architect",
  "after": "-P7D"
}
```

## Parameters

> [accordion] Body
>
> **agent\_type** `string`
>
> The agent talked to: `architect`, `analyst` (flagging included),
> `qobra_ai`, `facets` or `sales_coach`. Omit for every agent.
>
> **author\_id** `string`
>
> Id or exact email of the user who talked to the agent, as list\_users returns
> them. Omit for every author.
>
> **search** `string`
>
> Text the conversation's title contains, any case.
>
> **after** `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.
>
> **before** `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.
>
> **limit** `integer`
>
> Rows per page, 1 to 75. Default 25.
>
> **offset** `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

> [accordion] Body
>
> **conversations** `object[]`
>
> **object properties**
>
> **id** `string`
>
> **resource\_url** `string`
>
> Link opening this conversation in the audit trail.
>
> **agent\_type** `string`
>
> The agent talked to: 'architect' (designs compensation plans), 'analyst'
> (builds reports, flagging records included), 'qobra\_ai' (the assistant
> every user talks to), 'facets' (builds Facets), 'sales\_coach' (answers
> questions on a statement). One of: `architect`, `analyst`, `qobra_ai`,
> `facets`, `sales_coach`.
>
> **title** `string`
>
> The prompt the conversation was opened with, cut at 200 characters
> (`title_truncated` says when). Null on a conversation opened without
> one.
>
> **title\_truncated** `boolean`
>
> **author** `object`
>
> The user who talked to the agent. Null when they are no longer a user of
> the company.
>
> **object properties**
>
> **id** `string`
>
> **email** `string`
>
> **name** `string`
>
> **started\_at** `string`
>
> **last\_active\_at** `string`
>
> **message\_count** `integer`
>
> Messages the transcript holds: the author's, the agent's answers and the
> app's notices, its tool calls folded into the answers.
>
> **write\_count** `integer`
>
> Changes the conversation saved, as audit-trail entries:
> [`list_audit_logs`](https://docs.qobra.co/mcp_documentation/tools/list_audit_logs) with this
> `conversation_id` lists them, beside the entry of its opening. A
> compensation edit not saved yet is not counted.
>
> **next\_offset** `integer`
