Engineering
Long-form writeups on the architecture behind autonomous code review and remediation.
Anthropic's September 1 release of two safeguard regimes for the same model reshapes how engineering teams should think about autonomous review economics and governance.
Manifold Security disclosed 8 flaws across 7 CLI coding agents where a malicious .git/config triggers RCE before any user prompt, with 4 still unpatched.
Anthropic's 75% cache price drop makes whole-repo context viable for every PR. Here's what that means for code review tooling, regulated teams, and tiered model access.
Vulnerabilities, supply chain, audit trails, and the attack surfaces AI opened up. For the people responsible when something gets through.
View all 57 posts →Build systems, CI design, vendor moves, and tool evaluations. The substrate the rest of the engineering org runs on.
View all 32 posts →How AI tools change the way teams write, review, and ship code. Productivity studies, workflow shifts, and language-by-language realities. It cross-cuts every other category.
View all 32 posts →Org design, metrics, hiring, scaling, and the calls a CTO is paid to make. How to run an engineering function in the AI era without burning out the team.
View all 12 posts →The state of the codebase and the practices that keep it sound. Decay, duplication, readability, refactoring, and the review gates that catch problems before they ship.
View all 6 posts →Design decisions, tradeoffs, and the architectural patterns that age well. Long-form technical writing for the engineer who keeps a copy of Fowler nearby.
View all 6 posts →The Dispatch
One email every Friday on AI velocity, codebase excellence, and the future of product-grade engineering. No noise. Unsubscribe anytime.
