Measure what your agent resolves
See measured answers, self-service, channel activity, top questions, open gaps, handoffs, and readiness history—with the counting basis shown beside each available metric.
The report fields you can inspect
Total searches
Answered conversations
Typical first answer
Knowledge gaps
Example dashboard metrics
Insights that drive improvement
Use measured interaction records to choose what to improve
Search analytics
See exactly what customers search for. Understand their language and anticipate their needs.
Top questions
See the most common recent questions, whether each maps to an open gap, and which ones preceded a human-contact click.
Knowledge gaps
Every question the agent can’t answer confidently rolls up into a knowledge gap, so you can fill it before more customers hit it.
Answered interactions
See measured answered conversations and visitor-submitted handoffs from the stored records behind each available report.
Channel activity
Compare measured Floatie searches and chat turns with AI-agent touches from MCP and Ask with my AI.
Readiness scores
Three readiness gauges — answer, sales, and agent — score how ready your agent is and hand you the next best action to raise them.
Turn insights into action
Find content gaps
See what customers search for but don't find. Create content that matters.
Improve weak articles
Identify articles with low satisfaction or high bounce rates.
Report measured activity
Review answered interactions and visitor-confirmed handoffs when supporting rows exist.
Optimize AI
Track AI performance and improve responses over time.
Frequently asked questions
Reports cover measured answers, typical first-answer time with enough events, sales assists, activity by channel, handoffs by source, top questions, open knowledge gaps, and readiness history. A metric with no supporting rows is omitted rather than shown as zero.
The analytics dashboard shows searches that returned no results or low-confidence AI answers. These are content gaps—topics customers ask about but your documentation doesn't cover well. Filling these gaps improves self-service rates.
Reports show answered conversations, typical first-answer time when enough events are available, channel activity, handoffs by source, and open knowledge gaps. Metrics include their counting basis rather than treating missing data as zero.
Reports compute available metrics from stored interaction rows and show the counting basis beside the result. Missing events are omitted rather than treated as zero, and page views are not presented as resolved conversations.
The in-product Reports view is available without a separate export workflow. It shows only metrics backed by measured rows and omits values that cannot be computed. A downloadable analytics export is not currently shipped.