Chatbot analytics
Use chatbot analytics for conversations, leads, response time, usage, cost estimates, unanswered questions, source references, and training gaps.
Metrics
Metrics
Conversation trends, message totals, leads, countries, devices, domains, and top pages.
Answer quality signals such as knowledge answers, fallback answers, blocked answers, and greeting turns.
Response time, AI token metadata, estimated cost, and whether a real AI call happened.
Training health, failed sources, top unanswered questions, contacts, and visitor context.
Quality
Answer quality
Answer kinds include knowledge, fallback, greeting, and blocked. Fallback heavy behavior usually means the training set needs better coverage.
Gaps
Unanswered questions and source references
Use unanswered questions to decide which website pages, manual Q&A, or files need stronger coverage.
Review source references in transcripts to understand which approved content shaped an answer.
Use knowledge gaps and generated FAQs to prioritize improvements.
Connect lead analytics with conversation context before changing forms or follow up rules.
Visitors
Visitor context
Visitor analytics use coarse context such as country, region, city, device, browser, OS, language, timezone, screen, viewport, referrer, and page URL.
Credits
Credit usage
Analytics are available with the product. Token and cost tracking are reporting signals, while AI work is debited from workspace credits.