Writing
Technical writing on AI readiness, deployment risk, and the methodology behind our scoring model.
-
May 3, 2026
The Cost-Latency-Quality Triangle for LLM Features
Every production LLM feature picks two of three: cheap, fast, or good. Most teams pretend they're picking all three, then discover at scale that they picked one. A practitioner's framework for making the trade-off explicit, with the numbers that actually drive the decision.
-
May 3, 2026
Three Signals You Need a Senior ML Engineer, Not a Wrapper
Most teams shipping AI features hire generically. Some features fail loudly when that's the wrong call. Three specific signals that mean the work needs ML-engineer-grade hands, not a junior with a Claude API key — and what production-discipline actually changes.
-
May 3, 2026
What an AI Eval Harness Actually Looks Like in Production
Most teams say they have evals. What they have is a vibe check. Here's what a real eval harness for an LLM feature includes — test set, scorers, regression gate, drift detection — and why it's the most-skipped engineering practice in shipping AI.
-
April 24, 2026
Five Ways Your AI Deployment Will Quietly Fail Before Anyone Notices
The failure modes that don't make headlines until they do. A practitioner's taxonomy of silent drift, stale features, broken evaluation, unowned models, and metric-vs-reality gaps — grounded in the cases that made it to court.
-
April 24, 2026
Why Most AI Readiness Checklists Are Written by People Who've Never Shipped
A practitioner's teardown of the four major AI governance frameworks — NIST AI RMF, ISO/IEC 42001, the EU AI Act, and SR 11-7 — and what each one misses about production reality.
-
April 20, 2026
How We Score AI Readiness
A walkthrough of the pillar-and-maturity rubric behind our AI readiness audit — what we measure, how we score it, and why transparency matters.