List of live conversations
The Live Conversations page allows you to monitor in real time all active interactions between users and Smart Assistant. It provides visibility into ongoing sessions, helping you identify which users are currently engaged, track conversation flow, and intervene when human assistance may be required.
This section is particularly useful for operational teams and managers who need to supervise current activity or ensure that escalations are handled promptly.
Conversations listed here are continuously updated as messages are exchanged. A conversation that remains inactive for four hours without any interaction will automatically transition to the Archived Conversations section. Similarly, a previously archived conversation can reappear in this list if the user sends a new message, resuming the interaction.
Period selection and filters
At the top of the page, you can select the Time Range you want to analyze. The available options are Last 24 hours, Last week, Last month, Last year, or a Custom range.
To refine your search, use the Filter panel to focus on specific parameters:
- Rated: displays only conversations that received user feedback.
- Claim of an agent: filters conversations that were taken over by a human operator.
- Client: shows conversations belonging to a specific identified user.
- Assigned to: allows filtering by the Agent responsible for the conversation.
- Language: limits results to conversations held in a particular language.
- Topic: filters by main subject of the conversation.
- Subtopic: refines the selection within a specific Topic , helping locate precise types of user requests.
Filters can be combined to narrow down results, for example: “English conversations about returns that were escalated to an agent and received a rating.”
Click Apply to refresh the list, or Reset to clear all filters and return to the full dataset.
Conversations table
The main table displays all currently active conversations that match your filters. Each row represents a live Conversation , updated dynamically as users and Smart Assistant continue to exchange messages.
| Column | Description |
|---|---|
| ID | The unique identifier assigned to each conversation, used for reference and tracking. |
| Start / Last Message | Shows when the conversation began and the timestamp of the most recent message. |
| Duration | The total elapsed time since the conversation started. It updates dynamically while the conversation remains active. |
| Queries | The number of distinct user questions detected so far. Useful to gauge the complexity of the ongoing interaction. |
| Messages | Total number of messages exchanged to date between the user and Smart Assistant. It increases as the conversation evolves. |
| Rating | Displays the user’s satisfaction score if already provided (from 1 to 5). A red dot next to the score indicates that the user added a feedback comment. |
| User | The name or alias of the person currently interacting with Smart Assistant. |
| User ID | The internal identifier assigned to that user within your system. |
| Escalated | Indicates whether the conversation has been transferred to a human agent. |
| Assigned | Shows the Agent or team currently managing the live conversation. |
| Language | The detected language of the conversation. |
| Location | The geographical origin of the user. |
| Channel | The Channel where the conversation is taking place (e.g., web, WhatsApp, Messenger). |
| Device | The device type used by the user (desktop, mobile, tablet, etc.). |
The table supports sorting and pagination, allowing you to focus on the most relevant data.
Click any conversation ID to open its detailed view, where you can review the full message history, ratings, and associated metadata.
How to use this page
The Live Conversations page is designed for real-time supervision and quality monitoring. It allows managers to ensure timely responses, detect bottlenecks, and verify that both automated and human interactions are performing correctly.
This view also helps in identifying conversation peaks or moments when additional agent resources might be needed.
Notes and Recommendations
- Use the Claim of an agent filter to monitor human-managed sessions separately from automated ones.
- Pay attention to Duration and Queries to identify long or complex interactions that may require escalation.
- Conversations that stay inactive for over four hours are automatically archived but can return to live status if the user re-engages.
- Use this section together with the Escalated Conversations page to analyze follow-up actions and human handovers.