# AI Insights

> AI Insights brings higher-level aggregated analysis together: Sentiment, Conversation Outcome, Topics, and Link Tracking.

AI Insights brings the higher-level aggregated analysis together on one screen: Sentiment, Conversation Outcome, Topics, and Link Tracking. Where **Advanced** shows distribution-over-time, **AI Insights** focuses on the latest aggregate state and per-conversation drill-downs.

## Conversation Outcome

See how many conversations end **Resolved** vs **Unresolved** over the period. Outcome is also visible inside each conversation in the Inbox details pane. No setup is required on supported plans.

![Screenshot of the Outcome in Inbox Quickchat AI](https://docs.quickchat.ai/_astro/conv_outcome.i-fXIhMI.webp)

**Why it helps**

- Quickly spot unresolved spikes that may need human follow-up.
- Track whether changes to your AI or content improve resolution rates.

## Sentiment Analysis

Understand how users felt after chatting with your AI: **Positive**, **Neutral**, or **Negative**. Aggregated here, and also per-conversation in the [Inbox details pane](/conversations/inbox/#insights). On by default.

![Screenshot of the Sentiment in Inbox Quickchat AI](https://docs.quickchat.ai/_astro/sentiment.DLwiylyr.webp)

## Conversation Topics

Listening to your users is key, but doing it at scale is hard. [**Topics**](/conversations/insights/manage-topics/) help you track, analyze, and act on the main subjects discussed in your chats without getting lost in the details. The distribution over time is also visible in the Advanced tab.

## Time to First Response

How long a visitor waited for a **human** to reply after a conversation was handed off. The clock starts at the confirmed handoff and stops on the first message sent by a human operator.

This is a measure of your team's responsiveness, not the AI's. It says nothing about how fast the AI Agent answers — the AI replies in seconds and is never counted here. Conversations the AI handles on its own never produce a Time to First Response at all.

The section stays empty until you have had handoff conversations in the selected range that a human actually replied to. A handoff nobody answered contributes nothing, so a suspiciously good number is worth checking against your handoff volume.

## CSAT Ratings

Customer satisfaction ratings collected after handoffs. Empty until you have had handoff conversations with rating prompts in the chosen range.

For satisfaction with the AI itself rather than with your team, use [Conversation Rating](/conversations/insights/conversation-rating/), which prompts every visitor rather than only handed-off ones.

## Per-row badge

Each row in the AI Insights list carries a small **badge**. By default it shows the conversation's **Topic**, but you can change what every badge displays — Sentiment, Intent, Resolution, Language, Channel, or any value from your conversation metadata — from the **[Conversation badge](/conversations/inbox/#conversation-badge)** setting in the Inbox. The same badge appears on the Inbox conversation list, so both surfaces stay consistent.