Analytics, rebuilt from the ground up
A brand-new Analytics section: Overview, Topics, Sentiment, Ratings, AI Insights, and Team — powered by a new analysis pipeline that reads every conversation.
The old Insights page answered “how many conversations did I get?”. The new Analytics section answers the questions that actually change your week: what are customers asking about, how do they feel, where is the AI struggling, and what should you fix first.
- Topics — every conversation is clustered into the themes customers actually talk about, ranked by volume.
- Sentiment & Ratings — how conversations feel, plus the reasons behind every thumbs-down.
- AI Insights — an automated feed that flags anomalies and opportunities before you go looking for them.
- Team — response and resolution performance for your human agents.
- Visitor context everywhere — conversations now carry location and device, so you know who you're talking to.
One overview, honest numbers
The overview opens with five KPIs — conversations, messages, AI resolution rate, transferred to human, and CSAT — and every number compares itself against the previous period of the same length, so you see direction, not just totals. Below the tiles, the period breaks down into conversations per day, a resolution breakdown, busiest weekdays and hours, channels, languages, countries, devices, and a table of the pages on your site where conversations start.

Topics and AI Insights
Topics clusters every conversation into the themes customers actually talk about, ranked by volume — no manual tagging. AI Insights is an automated feed that reads your conversations overnight and flags what deserves attention: anomalies, recurring complaints, opportunities.


At the bottom of AI Insights, Knowledge Gapslists the questions your AI couldn't answer, grouped into topics, each with an Add answer → retrainaction that drafts a knowledge base article and retrains the agent in one step — and a before/after trend once it's published.

Sentiment, Ratings, and Team
Sentiment tracks how conversations feel over time. Ratings collects end-of-chat CSAT — scores out of five, the reasons behind every thumbs-down, and written feedback. Team shows response and resolution performance for your human agents after handoff.

See what's new in your workspace
Everything on this page is live today. Asks trains on your website and resolves customer conversations on every channel — free to try, live in minutes.