Ai

AI-generated JIRA tickets and PRs have become word walls. Here's why your automation needs both a human summary and a machine-readable payload.

Practical techniques for giving AI agents the context they need: AGENTS.md files, documentation strategies, and plan mode workflows.

Compare GLM, Qwen, and Gemma local LLMs - benchmarks, context sizing, and when home GPU inference beats cloud token costs.

How Claude Code hooks create mechanical enforcement at commit time — blocking violations, injecting warnings, and coaching better habits before code ever reaches review.

How engineering leaders adopt AI coding tools—from completion to agents—without trading speed for quality.

How to architect, build, and evaluate AI agent systems using orchestration frameworks, protocols like MCP and A2A, and RAG pipelines.

Essential resources for mastering agentic AI development — core concepts and guides for GitHub Copilot, Claude Code, Cursor, and OpenAI Codex.

How treating AI tooling like a distracted junior developer resulted in production-quality software

What if your AI agents could learn from their mistakes and get better over time? Check out a sample architecture that does just that.

A blog post exploring my two-week experiment using GitHub Copilot CLI for all coding tasks as a generative AI skeptic.