The Chats section is accessible in two ways: via the left menu (all dialogs across all agents) or via the Live chat button in the AI employees list (dialogs for a specific agent).
Persona
Define dialog behavior and escalation rules
Notifications
Set up alerts for critical conversations
Quick Answers
Templates for instant responses
Profiles
View client data collected during chats
Why Use Chats
- Monitor how AI employees communicate with clients
- Quickly find a specific dialog by client name, channel, or employee
- Intervene in a conversation when the situation requires a human
- Handle escalations — cases when an agent has handed the dialog to a manager
- Evaluate AI employee performance on real conversations
Interface Overview
Dialog List (Left Panel)
The left side of the screen displays a list of all chats. Each list item is a separate dialog with a client. Dialogs are sorted by time: the most recent ones appear at the top.| Element | Description |
|---|---|
| Client name | Name or identifier if the name is not available |
| AI employee name | Which agent is handling the dialog |
| Channel | Where the client came from: Telegram, amoCRM, Bitrix24, website widget, etc. |
| Time | Time of the last message |
| Message preview | A snippet of the last message |
| Status | Active, paused, or completed |
Conversation View (Right Panel)
Click on any dialog in the list — the full conversation history opens on the right. Messages are displayed like a regular messenger: client on the left, agent on the right. Each message includes a timestamp. At the bottom of the conversation window is a message input field — this is how a manager can reply to the client manually.Search and Filtering
Search bar
Search bar
At the top of the dialog list there is a search bar. Enter a client name, keyword, or conversation fragment — the list filters in real time.
Filter by employee
Filter by employee
Shows dialogs for a specific AI employee only. Useful when you have multiple agents.
Filter by channel
Filter by channel
Filters by source: Telegram, amoCRM, Bitrix24, web widget, etc.
Manager Intervention
One of the key capabilities of the Chats section is manual manager intervention in a conversation that an AI employee is handling.How to Intervene
Read the conversation history
Assess the conversation context and decide whether intervention is needed.
What Happens After Intervention
As soon as a manager sends a message, the AI employee automatically pauses in that specific dialog. It will not interrupt the human.| Behavior | Description |
|---|---|
| Client messages | Continue to arrive and are saved in history |
| AI employee | Remains paused while the manager handles the dialog |
| Auto-resume | After 10-20 minutes of manager inactivity, the AI may automatically resume work |
Agent Control Commands
Managers can control an AI employee directly from a messenger using service commands. Commands are configured in the Additional Settings tab for each agent.| Command | What it does |
|---|---|
| AI start command | Activates the agent in the chat (set by you) |
| AI stop command | Pauses the agent (set by you) |
| Clear memory command | Resets the dialog context — the conversation starts from scratch (default: delete all) |
| Protection command | Activates protection against prompt injection attempts (set by you) |
Escalation — When an Agent Hands Off to a Manager
Escalation is a situation when an AI employee recognizes that it cannot or should not handle a request on its own and transfers the dialog to a human.When Escalation Triggers
Escalation is triggered in cases that you define in advance:- In the agent’s Persona (the “When to call a manager” or “Escalation” section)
- In Notifications (triggers that send an alert and pause the chat)
- In Quick Answers (actions of the “Chat management” type with a pause)
What It Looks Like for a Manager
Receive a notification
The manager receives a notification in Telegram (or via webhook) that the agent has handed off the dialog.
Find the dialog in Chats
In the Chats section, the dialog is displayed with a status indicating that intervention is needed.
Agent Behavior During Escalation
| Trigger setting | Behavior |
|---|---|
| Pause chat for N time | The agent pauses for the specified duration. If the manager does not connect, the agent resumes automatically |
| Forced pause | The agent stops completely. Work resumes only manually (via the start command or the interface) |
Dialog Details
When you open a specific chat, in addition to the conversation history, additional information is available:- Client profile — filled fields: name, language, preferences, and any data the AI extracted from the conversation
- Communication channel — which messenger or CRM the conversation is going through
- AI employee name — which agent is handling this dialog
- Dialog status — whether the agent is active or paused
Related Sections
| Section | How it relates to Chats |
|---|---|
| Persona | Defines how the agent conducts dialogs and when to call a manager |
| Notifications | Configures escalation triggers: when and how the manager learns about problematic dialogs |
| Quick Answers | Can manage the chat: pause, transfer to another agent |
| Profiles | Client data visible in the chat |
| Auto Follow-up | Follow-up messages if the client goes silent |
| Additional Settings | Agent control commands from the messenger, message limits |
| Channels | Sources through which messages arrive in the chat |
Practical Tips
Review dialogs regularly
Review dialogs regularly
Especially in the first days after launch. Browse conversations in the Chats section at least once a day during the first week of operation.
Use filters for systematic analysis
Use filters for systematic analysis
Filter dialogs by a specific employee and review the last 10-15 conversations. This gives you an understanding of where the agent performs well and where adjustments to the persona or knowledge base are needed.
Don't hesitate to intervene
Don't hesitate to intervene
If you see that the agent is not responding correctly, step in and reply yourself. The agent will automatically pause. After the conversation, adjust the settings so it handles similar cases on its own next time.
Set up notifications for critical situations
Set up notifications for critical situations
Create triggers in the Notifications section for complaints, returns, VIP clients, and questions outside the agent’s competency. You will receive an alert in Telegram and can quickly step in.
Share control commands with your team
Share control commands with your team
FAQ
Are chats stored forever or deleted?
Are chats stored forever or deleted?
Chat history is stored on the platform. For some channels, an Auto-clear history setting is available in the Channel tab — it allows automatic deletion of old dialogs.
Can I reply to a client from the Chats section if they wrote in Telegram?
Can I reply to a client from the Chats section if they wrote in Telegram?
Yes. When you send a message through the Chats section, the client receives it in whichever messenger they used to reach out. You do not need to open Telegram or amoCRM — everything is managed from one window.
What happens if two managers reply in the same chat simultaneously?
What happens if two managers reply in the same chat simultaneously?
The client will receive both messages. It is recommended to coordinate within your team who handles a specific dialog to avoid duplication.
The agent paused after my reply. How do I resume it?
The agent paused after my reply. How do I resume it?
Three options: (1) wait 10-20 minutes — if auto-resume is configured, the agent will start on its own; (2) send the AI start command in the messenger; (3) manage through the platform interface.
Can I view chats from all employees in one place?
Can I view chats from all employees in one place?
Yes. The Chats section in the left menu shows dialogs across all agents. Use the employee filter to narrow the selection.
Does the client see that they are talking to a manager, not AI?
Does the client see that they are talking to a manager, not AI?
In most cases, the client sees messages from the same contact (bot or account) through which the AI employee was communicating. The transition is visually seamless for the client.
Is there a message limit per chat?
Is there a message limit per chat?
Yes. In the Additional Settings tab for each agent there is a Message limit setting — a cap on the number of messages in one chat per 24 hours. If no limit is set, there are no restrictions.