
AI Coding Tools in 2026: What We Actually Use Across 20+ Client Projects (And What We Don’t)
Real-world review of AI coding tools across 20+ projects: which tools work in production, risks, token costs, and governance practices.
Blog
Field notes on shipping AI-native systems with human engineering judgement: architecture, modernisation, automation, and the tradeoffs in between.
AI-generated code accumulates invisible technical and comprehension debt, causing apps to become fragile around 10,000 users - symptoms, timeline, and fixes.