AI Chatbot Support Metrics: Containment, Deflection, CSAT & Cost per Resolution
Intent mix, containment and escalation rates, deflection vs true resolution with the 7-day re-contact test, thumbs-up CSAT, cost per resolution bot vs human, handoff quality and an intent-level ROI roadmap: 8 labs on one fictional SaaS support bot.
The first lesson is free — no account needed.
About this course
An AI chatbot support metrics course that measures one fictional SaaS support bot, Quill Assist, for support leaders, conversational AI teams and CX analysts who need to know whether the bot really helps. You size the monthly workload and intent mix, calculate containment per intent and how much of it is customers giving up, break escalations down by reason, compare the deflection rate with the true resolution rate using a 7-day re-contact test, measure thumbs-up CSAT per intent with a minimum number of ratings, build the cost per resolution of the bot and of human agents and the support cost avoided, audit handoff quality from wait times and repeated questions, and rank planned bot improvements by value per effort day for the roadmap. The first lab is free.
Lessons
- Conversation Volume & Intent MixFree
- Containment Rate: Conversations Without a Human Pro
- Escalation Rate & Escalation Reasons Pro
- Deflection vs True Resolution: the 7-Day Re-Contact Test Pro
- Bot CSAT: Thumbs-Up Rate by Intent Pro
- Cost per Resolution: Bot vs Human Agents Pro
- Handoff Quality: Time to Agent & Repeated Questions Pro
- Intent-Level ROI & Roadmap Prioritisation Pro