My Current AI Coding Setup
How I use Codex, JetBrains IDEs, Copilot review, AGENTS.md, reusable skills, and CI checks to make AI coding reliable.
How I use Codex, JetBrains IDEs, Copilot review, AGENTS.md, reusable skills, and CI checks to make AI coding reliable.
A developer-focused summary of the State of AI 2026 survey, covering adoption, coding agents, paid usage, costs, risks, and what engineering teams should take from it.
Why AI coding tools only create lasting velocity when leaders fix trust, feedback loops, governance, and engineering fundamentals.
Why AI coding divides engineers less on capability than on trust, identity, incentives, and what they think the job really is.
How to adapt the Ralph Wiggum loop pattern popularised in Claude Code to Codex using repeatable, bounded non-interactive runs.
Why many teams use agile tooling and ceremonies but still deliver in large, slow, phase-gated batches, and how to get back to real fast-feedback delivery.
Go beyond the basics with panes, copy mode, synchronised input, and shared tmux sessions.
How remote work made voice-first coding practical for me, where it breaks down in open offices, and why I still review every transcribed prompt before sending it.