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

# Conversations

> Monitor, analyze, and manage all conversations between users and Agents

The Semantiks Console dashboard gives enterprises real‑time visibility into conversations led by AI agents across all connected channels. Its design supports two complementary objectives: understand system‑level behavior (volumes, duration, engagement) and quickly drill into any single session for evidence‑based decisions (retuning prompts, updating knowledge, or handing issues to operations). Start with the high‑level structure to frame what you're seeing, then use the right‑side panel to read details without losing your place.

<Note>
  Around the first week of September 2025, the Conversations Dashboard will be updated to include a unified filter that applies both to the KPIs and the Conversations Table, ensuring consistent data views.
  Additionally, our team is currently working on fixing certain reporting bugs affecting KPIs to improve accuracy and reliability.
</Note>

## Overview of the Dashboard

When you access the **Conversations Dashboard**, you will see:

* **KPIs (Key Performance Indicators):** High-level metrics summarizing performance.
* **Conversations Table:** A detailed list of all conversations with users.
* **Conversation Panel:** A right-side panel that shows more details when you click on a conversation.

***

## KPIs Cards

The top section provides at-a-glance metrics:

* **Total conversations** – The number of conversations in the selected time range.
* **Average duration** – The average length of conversations.
* **User messages** – Average number of messages sent by users.
* **Agent messages** – Average number of messages sent by the agent.

<Note>Green arrows indicate growth compared to the previous period, while red arrows indicate a decrease.</Note>
<Tip>You can filter the time range by selecting **Today, 7D, 30D, or Year**.</Tip>
----------------------------------------------------------------------------------

## Conversations Table

Below the KPIs, you will find a table with all recorded conversations. Each row represents a conversation with details such as:

* **Status:** Current status of the conversation (Active, Ended, or Not Started).
* **Start:** Date and time when the conversation started.
* **Channel:** The communication channel used (e.g., Freshchat Bubble, WhatsApp).
* **Tools:** Tools or skills used by the agent during the conversation.
* **Control:** Indicates who handled the conversation. For AI-handled conversations, a generic label is shown (e.g., "AI"). For human-handled conversations, the **name of the specialist** attending is displayed.
* **Profile Name:** Name of the user (if captured by the channel).
* **External ID:** User ID from the channel.
* **Number of Messages:** Total messages exchanged (with the AI agent).
* **First Response Time (FRT):** The time elapsed between the user's first message and the agent's first reply. Displayed in a human-readable format (e.g., `45s`, `2m 30s`, `1h 15m`).
* **Average Response Time (ART):** The average time the agent takes to respond across all messages in the conversation.

### Table Controls

* **Search:** Filter conversations by keyword across multiple fields.
* **Date range:** Select a preset (Today, 7D, 30D, Year) or define a custom range.
* **Columns:** Show or hide columns using the column visibility selector.
* **Pagination:** Navigate through pages of results.

***

## Conversation Panel (right-side detail view)

Clicking any row in the table opens a **right-side panel** with three tabs: **Details**, **Chat**, and **Summary**.

### Details Tab

Displays metadata about the conversation:

* **Started:** Date and time when the conversation began.
* **Status:** Active, Ended, or Not Started.
* **Channel:** The channel where the conversation took place.
* **CSAT:** Customer satisfaction score (if available).
* **Message Count:** Total number of messages exchanged.

### Chat Tab

Shows the full transcript of the conversation. Messages are displayed in a chat-like layout with:

* **User messages** on one side and **agent messages** on the other.
* **Human specialist messages** are distinguished when a handoff occurred.
* **Tool invocations** are shown inline with an expandable section that reveals the tool name, input, and output.

#### Campaign / Proactive messages

Messages sent through **Campaigns** or **proactive messaging** (including WhatsApp templates) are visually distinguished in the chat transcript:

* They appear in a **green-styled bubble** to differentiate them from regular agent replies.
* A **"Campaign" badge** with a megaphone icon is displayed at the top of the message bubble.

This makes it easy to identify which messages were sent proactively by a campaign rather than as part of an organic conversation flow.

<Tip>
  Use the Campaign badge to quickly audit which outbound messages were triggered by your campaigns when reviewing a conversation.
</Tip>

### Summary Tab

Provides an AI-generated summary of the conversation, including:

* **Topic:** The auto-classified topic.
* **Sentiment:** User sentiment (positive, neutral, negative).
* **Task success:** Whether the agent resolved the user's request.
* **Key points:** Bullet-point summary of the conversation highlights.

***

## Common Actions

* **Review agent performance** — Open individual conversations to read transcripts and evaluate the agent's responses.
* **Identify patterns** — Use KPIs and table filters to spot trends in conversation volume, duration, or channel distribution.
* **Audit tool usage** — Check which tools the agent invoked during a conversation and whether they executed successfully.
* **Verify campaign messages** — Look for the green Campaign badge in conversation transcripts to confirm that proactive messages were delivered correctly.