Ralph Wiggum loops with Codex: run iterative agent passes until done
How to adapt the Ralph Wiggum loop pattern popularised in Claude Code to Codex using repeatable, bounded non-interactive runs.
Recent Insights Page 2
Why Agile Teams Still End Up Doing Waterfall
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.
tmux Advanced Workflows
Go beyond the basics with panes, copy mode, synchronised input, and shared tmux sessions.
Never Roll Back, Always Fix Forward
Why fix-forward is usually safer than rolling back when deployments touch databases, background jobs, and other non-idempotent state.
Using Agent Skills with AI Agentic Coding: A Practical Workflow
A practical guide to structuring skills so AI coding agents produce faster, safer, and more reproducible software delivery.
Preparing Documents with Docling for CAG, RAG, and Embedding Pipelines
A practical guide to converting, chunking, and ingesting documents for CAG, RAG, and hybrid AI knowledge systems.
How LLMs Come Into Being: A Beginner-Friendly Guide to Data, Tokens, Training, and Inference
A beginner-friendly but detailed guide to how large language models are built, trained, aligned, and run in production.
ARIA vs Semantic HTML: Practical Accessibility Patterns for Dialogs and Chat UIs
A practical guide to when ARIA is necessary, what common attributes mean, and where semantic HTML should be your first choice.