# Advanced

> The Advanced tab moves from headline numbers to distribution-over-time, showing how each metric evolved across your date range.

The **Advanced** tab moves from headline numbers to distribution-over-time. Each chart shows how a metric evolved across the date range you picked, so you can spot trends, regressions, and the effect of changes you make to the AI Agent.

## Resolution Breakdown (over time)

A stacked bar chart per day showing the four resolution buckets (Confirmed / Assumed / Small Talk / Unresolved) across the selected range. Watch this after retraining the Knowledge Base or editing the AI Main Prompt to see whether the changes improved your resolution rate.

## Sentiment Analysis (over time)

A stacked bar chart per day showing Positive / Neutral / Negative sentiment counts. A growing red band is a leading indicator that something's wrong — users are getting frustrated — and worth digging into via the Inbox.

## AI-Detected Topics

A separate concept from your user-defined Topics: Quickchat's AI **automatically** discovers topics in your conversation data and surfaces the most-discussed ones over time. No setup required — just open the tab.

The chart shows the top auto-detected topics across the period (e.g., "Pricing inquiry", "AI agent setup", "Discord bot setup", "Out-of-scope question") with a count for each. Use this to:

- Discover topics you didn't think to create as custom Topics.
- Spot emerging issues — a topic climbing the list this week often signals a product or content gap.
- Validate whether your custom Topics actually match what users care about.

## Custom Topics

Distribution of the Topics **you** defined under [Manage Topics](/conversations/insights/manage-topics/). Same time-series shape as AI-Detected Topics, but limited to topics you explicitly track.

## Link tracking

If your AI Agent shares links in its responses, this section tracks how many links were shared, how many were clicked, and the resulting click-through rate. The table below lists the top shared links with per-link counts.

We automatically append UTMs to every link the AI shares so you can attribute traffic and conversions in your own analytics tool:

- `utm_source=quickchat_ai`
- `utm_medium=referral`
- `utm_campaign=widget_{your_agent_id}`
- `utm_content={conversation_id}`

**Tip:** In Shopify, group sessions or conversions by `utm_source` to see traffic from the AI Agent.

## CSAT Ratings

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