Blog
Notes on making AI support actually work.
Practical writing for the people accountable for an AI deployment — how to measure it, why it fails, and what to do about it. No hype, no manifestos.
Report
The AI Support Deflection Gap: what vendors promise vs. what enterprises get
Vendors sell 80% deflection. The measured enterprise median is around 41%. Here’s the gap, why it exists, and a scorecard to grade your own deployment.
Read PlaybookHow to actually measure AI agent containment (and why your vendor’s number is wrong)
“Deflection” and “containment” are not the same thing — and most dashboards report the flattering one. A practical method for measuring the number that matters.
Read EngineeringWhy RAG retrieval quality — not the model — is why your bot hallucinates your refund policy
When a support agent invents a policy, the instinct is to blame the model. Usually it’s retrieval. A tour of the failure modes and how to fix each one.
ReadNext step
Ready to move your number, not just read about it?
Book the 30-day audit and get a measured baseline plus a costed plan to close the gap.