Explains why coding agents struggle with image-based architecture diagrams and advocates for code-based diagrams like Mermaid.
Explores loop engineering, a new approach where developers design systems that prompt AI agents instead of manually prompting them.
How to place low-level architecture documentation in the codebase for better clarity and AI agent support.
A curated daily reading list covering AI coding agents, Bigtable history, prototyping speed, design patterns, and tech industry trends.
Explores 10 essential design patterns for coding agents and agentic software delivery, moving beyond AI-assisted coding to AI-augmented development.
Uber caps employee AI coding tool spending at $1,500/month per tool to manage costs after overspending its 2026 AI budget.
Uber caps employee AI coding tool spending at $1,500/month per tool to manage costs after overshooting its 2026 AI budget.
Explores the paradox of AI tools boosting productivity yet causing distraction, with personal anecdotes and ADHD perspectives.
Explores the paradox of AI tools boosting productivity while causing attention fragmentation and project overload.
A comprehensive overview of agentic coding tools in 2026, covering CLI agents, UI-based IDEs, autonomous agents, and model routers.
Explains why coding agents need architectural context via Architecture Decision Records (ADRs) and how to make them accessible.
Analysis of MiniMax M2 LLM technical report highlighting production-oriented design choices like full attention, fine-grained MoE, and agent training pipelines.
Explores a third approach to using coding agents: implementing backpressure mechanisms like tests and types to validate work before human review.
Explore three static code analysis sensors for maintainability in AI-assisted coding, covering linting, dependency rules, and coupling data.
Explores how coding agents boost productivity but require strong technical skills to use effectively, debunking the myth that AI replaces developers.
Explores the challenges of using local AI models for coding agents, focusing on usability gaps like tool parameter streaming.
GitHub Copilot Individual plans are changing with tighter usage limits, paused signups, and new pricing tiers due to increased compute demands from agentic workflows.
Speculative analysis on the future of agentic AI in software development, focusing on economic sustainability and geopolitical implications.
Explains how Agent Skills can capture institutional knowledge for coding agents, ensuring consistent adherence to internal frameworks and practices.
A review of Harbor, a framework for evaluating and optimizing AI coding agents and models in container environments.
