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

# Conversations console

> Every conversation and every run in one place, with what the assistant did and what it cost.

The **Chats** section is the account's activity in one list: conversations from every assistant, wherever they came from — the console, an embedded widget, the API, an inbound email or a trigger.

<img src="https://mintcdn.com/devic/DKyKkxiOLW4okLYC/images/chats/console.png?fit=max&auto=format&n=DKyKkxiOLW4okLYC&q=85&s=bf0460309168a38f8b31a5600d27b9e7" alt="Chats console" width="1605" height="642" data-path="images/chats/console.png" />

***

## Finding a conversation

Filters narrow the list along the axes that matter in practice:

| Filter                 | Use it to                                                  |
| ---------------------- | ---------------------------------------------------------- |
| **Assistant**          | Look at one deployment at a time.                          |
| **Tenant / subtenant** | See what one customer, or one of their users, experienced. |
| **Tags**               | Group conversations your own integration labelled.         |
| **Date**               | Bound the window.                                          |

There is also full-text search inside a conversation's messages, for when you remember what was said but not where.

***

## Reading one

<img src="https://mintcdn.com/devic/DKyKkxiOLW4okLYC/images/chats/detail.png?fit=max&auto=format&n=DKyKkxiOLW4okLYC&q=85&s=121a3cd72c0156667d64f757c1ddfdfc" alt="Conversation detail" width="1609" height="692" data-path="images/chats/detail.png" />

A conversation shows more than the transcript:

* **Tool calls**, expandable to their arguments and results — the fastest way to see why an answer was wrong.
* **Recalled memories**, when the assistant used [memory](/devic/memory/index): what it brought in and from where.
* **Cost and tokens** for the conversation.
* **Feedback** left on individual messages, thumbs and comments.

<Tip>
  When an answer is wrong, the tool calls usually explain it before the prompt does. A tool that returned an error, or was never called at all, is a different fix from a prompt that asked for the wrong thing.
</Tip>

***

## Conversations that were blocked

A conversation stopped by a [usage limit](/devic/multi-tenant/usage-limits) is marked as such, with the rule that blocked it, the current value, the ceiling and when the window resets. The mark clears itself as soon as a later message goes through.

***

## Agent runs

Agent threads have their own equivalent view, with the run's state, its tasks, approvals and pauses. See [Logs](/devic/agents/continuous-optimization/logs).

***

## Through the API

Everything here is available programmatically — [list conversations](/api-reference/endpoint/get-api-v1-assistants-identifier-chats), [read one](/api-reference/endpoint/get-api-v1-assistants-identifier-chats-chatuid), [search inside it](/api-reference/endpoint/get-api-v1-assistants-identifier-chats-chatuid-search) and [submit feedback](/api-reference/endpoint/post-api-v1-assistants-identifier-chats-chatuid-feedback) — which is how you build your own review workflow or export the lot.