Fragments: April 29
fragments 29 Apr 2026
fragments 29 Apr 2026
A structured approach to using prompts to guide AI-assisted programming.
fragments 21 Apr 2026
fragments 14 Apr 2026
a short post
fragments 09 Apr 2026
Every AI interaction generates signal: prompts that worked, context that was missing, patterns that succeeded, failures worth preventing. Most teams discard this signal. I propose a structured feedback practice that harvests learnings from AI sessions and...
Principles of mechanical sympathy for creating performant software: Memory access patterns, false sharing, the single-writer principle, and natural batching.
fragments 02 Apr 2026
A mental model for building trust in coding agents through feedforward guides, feedback sensors, and iterative harness engineering.
AI coding assistants respond to whoever is prompting, and the quality of what they produce depends on how well the prompter articulates team standards. Rahul Garg proposes treating the instructions that govern AI interactions (generation, refactoring,...
fragments 26 Mar 2026