Know what your agent is really doing
Conversation activity, funnels, channel mix and per-session traces show where the agent helps, where it hands off and what to fix next.
What was handed off
What went unanswered
Analytics
Improve answers with evidence
Averages hide problems. Open any session to see what the shopper asked, which sources the agent used and where the conversation went.
What it does
What it does for your team
- 01
Overview
Conversation activity, funnels, sessions versus drop-offs and channel mix.
- 02
Agent sessions
Per-agent Analyze view with every step and source.
- 03
Handoff reasons
See why conversations reached a person and reduce the avoidable ones.
Setup
How to get started
Watch the overview
Check activity and handoff rate weekly.
Open sessions
Read the conversations behind any spike or dip.
Fix and republish
Adjust knowledge or workflows and publish a new version.
FAQ
Questions, answered
Still curious? Ask our team
Can I export data?
Business and Enterprise teams can export reports and use APIs and webhooks.
Which metrics matter most?
Start with AI resolution rate, handoff rate and time to first reply; our guide on measuring AI agents goes deeper.
Keep exploring
- BlogMeasuring AI agent performance: beyond “conversations handled”The metrics that show whether your AI agent is working: resolution rate, handoff reasons, accuracy reviews, first reply time and revenue influence.Learn more
- FeatureAI agentAnswers product, order and policy questions from your own data.Learn more
- FeatureCall recordingsConsent-based recordings and transcripts of every call.Learn more
- FeatureAI voice agentReal-time spoken conversations with the same agent and knowledge.Learn more
Try it on your own store
Paste one snippet. Ask it what your customers ask.