Tool Gate · How it works
How the Support Deflection Honesty Grader gate works
How the Support Deflection Honesty Grader scores a deflection rate on your own numbers — the genuinely-resolved share is the score: a hollow-deflection gate forces FALSE DEFLECTION when a third or more of the 'deflected' bucket is really abandonment plus repeat contact.
How the 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. Each control is marked from your own evidence and weighted into a 0–100 score — and then the score is run past a gate that can only make the verdict worse.
The 4 weighted controls
| Signal | Weight |
|---|---|
| Genuinely self-served & resolved | 55 |
| Abandoned / gave up | 25 |
| Repeat contact within window | 15 |
| Reached a human anyway | 5 |
| Total | 100 |
The verdict bands
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.
In the worked sample it scores 55 out of 100 and still reads FALSE DEFLECTION — 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%. The one thing to fix first: Abandoned / gave up — 25% of the 'deflected' bucket gave up. Find where the bot buries the path to a human and fix that first; those give-ups are hidden demand, not resolution..
Common questions
Can something score well on the How the Support Deflection Honesty gate works and still fail?
Yes. The weighted score is run past a worsen-only gate — the Hollow-deflection — that can only make the verdict worse. In the worked sample it scores 55 out of 100 and still reads FALSE DEFLECTION, because 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%.
What is a worsen-only gate?
A dispositive rule that can only lower a verdict, never raise it. One fatal flaw overrides an otherwise-good score, because a single disqualifying gap shouldn't hide behind a high average. The tool also names the one thing to fix first — here, "Abandoned / gave up — 25% of the 'deflected' bucket gave up. Find where the bot buries the path to a human and fix that first; those give-ups are hidden demand, not resolution.".
Grades a metric claim from your own data — not people, and not a guaranteed or benchmarked rate.
Embed this diagram
Free to share and embed with attribution (CC BY 4.0) — keep the link to redhub.ai.
Interactive — renders the live diagram
<iframe src="https://redhub.ai/visuals/tool/support-deflection-honesty-grader.html" title="How the Support Deflection Honesty Grader gate works — RedHub AI" width="760" height="1625" loading="lazy" style="border:0;width:100%;max-width:760px"></iframe>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai/visuals/tool/support-deflection-honesty-grader">How the Support Deflection Honesty Grader gate works</a> — by <a href="https://redhub.ai">RedHub AI</a>, the AI that tells you when to doubt it.</p>Image + link — a static picture for any blog
<a href="https://redhub.ai/visuals/tool/support-deflection-honesty-grader"><img src="https://redhub.ai/visuals/tool/support-deflection-honesty-grader-share.png" alt="Diagram of the Support Deflection Honesty Grader: resolution shares scored to a true deflection number and a hollow-deflection gate forcing FALSE DEFLECTION when hidden demand dominates." width="760" loading="lazy" style="max-width:100%;height:auto;border-radius:16px"></a>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai">RedHub AI</a> — the AI that tells you when to doubt it.</p>
This is how Support Deflection Honesty Grader works. More diagrams in the Visual Field Guide.