Posts

Essays on AI and platform engineering for technical executives, newest first.

• AI Approval Gates: Engineering Oversight at Machine Speed

  11 Jun, 2026 • Updated 1 Oct, 2026

  AI approval gates: reversibility-tiered human-in-the-loop design with four health metrics that prevent reviewer atrophy at machine speed.

• AI Adoption in Engineering: Breaking the 50% Plateau

  29 May, 2026 • Updated 4 Oct, 2026

  Purpose-built AI tooling cuts per-task cost 21-68%. Three-cohort model and four-phase operating framework for engineering leaders past the 50% adoption plateau.

• AI Delivery Decision Frameworks: Type 1, Type 2, DACI

  22 May, 2026 • Updated 4 Oct, 2026

  Misclassifying reversible decisions costs more than the decision itself. Four frameworks unblock AI delivery: Type 1/Type 2, Eisenhower, DACI, and PMBOK.

• SRE for AI Agents: Error Budgets, Trust, and 90 Trials

  9 Mar, 2026 • Updated 4 Oct, 2026

  Can an AI agent predict scope without hallucinating? We ran 90 trials. It added 1.7 phantom files per change. Error budgets and trust ladders are the gate.

• What a Null Result Taught Us About AI Agent Evaluation

  23 Feb, 2026 • Updated 4 Oct, 2026

  We tested prompt repetition on 20 parallel AI agents. Ceiling effects dominated both experiments. The null result is a finding about evaluation design.

• Why Your AI Agent Failed in Production

  2 Feb, 2026 • Updated 4 Oct, 2026

  Why your AI agent failed: missing decision provenance, not metrics. The 3 observability gaps traditional monitoring won't catch.