RedHub AI
How the gate works
How the Support Deflection Honesty gate works
This tool grades the honesty of a support deflection rate on your own numbers — the genuinely-resolved share is the score, and hidden demand floors it. It scores 4 weighted controls into a 0–100 number — then a gate that can only make the verdict worse.
The 4 weighted controls
When a third or more of the deflected bucket (35%+) is abandonment plus repeat contact, that's hidden demand, not resolution — it floors the verdict to FALSE DEFLECTION regardless of the score, until that demand is actually resolved.
Why: The Billing bot claims 62% deflection, and 55% of the deflected bucket genuinely self-served — an honesty score of 55 that on its own reads SOFT DEFLECTION. But 40% of the bucket is hidden demand: 25% abandoned and 15% came back within the window. The hollow-deflection gate fires — give-ups wearing a good metric's clothes — so it's FALSE DEFLECTION, and the real defensible rate is just 34%.
A high score didn’t save it. The score is context; the gate is the answer — and it names the one thing to fix first. Grades a metric claim from your own data — not people, and not a guaranteed or benchmarked rate.