Skip to content
Notes

Notes

Short, dated commentary on the current category debates in enterprise voice AI — metrics, integration, latency, operating model. Pieces are intentionally brief and opinionated.

  • Why containment rate is the wrong KPI to put on a dashboard

    Containment rate is easy to measure, easy to game, and a poor proxy for what actually matters: whether the customer's problem was solved. A note on the metric voice AI programmes should use instead.

  • The integration tax nobody prices in

    Voice AI business cases routinely treat integration as a phase-two implementation detail. In production, integration depth is the single biggest predictor of whether the deployment can actually resolve calls.

  • Latency budgets and why 800 ms breaks the illusion

    Conversational realism collapses above roughly 800 ms of turn-taking latency. A note on where the milliseconds go and which optimisations actually move the dial.