Tag
Matt Pocock shares a daily prompt idea: retroactively analyze GitHub PR review comments from a team and generate suggestions for updating CODING_STANDARDS.md, turning past code review feedback into forward-looking coding guidelines.
The tweet advises that a CODING_STANDARDS.md file should be actively used to document issues with AI coding agents, starting empty and filling it based on errors.
Matt Pocock shares a slide from his upcoming talk at AI Engineer Paris, discussing the idea of hiding coding standards from implementer agents to fix them in review.
A NASA/JPL researcher discusses the ineffectiveness of traditional coding standards and introduces 'The Power of Ten' rules to prevent defects in safety-critical software through simplicity and metrics-driven practices.
A tweet explores the gap in AI skills for process improvement over time, suggesting a potential tool like '/improve-me' to update coding standards and refine agent behaviors.
Matt Pocock shares how he customizes the /code-review skill by writing issues into CODING_STANDARDS.md, which the agent then enforces during reviews.
The article argues for using unsigned integers more often in programming, refuting common arguments against them.
Orthodox C++ is a minimal subset of C++ that avoids modern features, advocating for a simpler, C-like style to improve readability and compatibility.
Matt Pocock live streams building a 'delivery calendar' feature for his course video manager using AI tools like Grill with Docs. He focuses on aligning terminology and data models with AI agents, and discusses the importance of coding standards for agent experience (AX).
The article discusses the idea of using a small local language model to continuously check code quality and enforce coding standards, aiming to keep codebases clean and secure without relying on cloud LLMs.