A chronological collection of insights on technical specification, product strategy, and AI-driven documentation.
AI Coding (18 articles)
Clear filtersA practical workflow for turning an approved spec into a clean, testable implementation—from breaking down acceptance criteria into tasks to structuring your final PR, with AI as a guardrail-driven assistant.
Spec-first AI coding replaces vague prompts and chaotic code generation with a simple workflow: clarify requirements, write a spec, then let the AI implement exactly what you approved.
EARS (Easy Approach to Requirements Syntax) provides five simple patterns that turn vague, natural-language requirements into precise, testable specifications that AI and humans can reliably implement.
A three-role system for AI-assisted software development: an architect who designs, a developer who implements, and independent reviewers who critique.
A practical operating model for running multiple coding agents in parallel using tmux and Markdown Feature Designs as the coordination backbone.
OpenAI’s GPT-5.3-Codex-Spark is a speed-optimized coding model co-developed with Cerebras, delivering over 1,000 tokens per second and a 128k context window for rapid, interactive software development.
An overview of the Ralph Wiggum Technique, a 2025-era approach to running autonomous AI coding agents in continuous loops, its timeline, core insights, and philosophical implications.
2025 reshaped the AI landscape: reasoning-first LLMs, mainstream coding agents, Chinese labs leading open-weight benchmarks, a command-line renaissance, and a shift from raw capability to deployment safety at scale.
OpenAI’s GPT-5.2-Codex is an advanced agentic coding model with native context compaction, enhanced visual understanding, and top-tier cybersecurity performance, including leading scores on SWE-Bench Pro, Terminal-Bench 2.0, CVE-Bench, and CTF evaluations.
Anthropic has introduced Claude Opus 4.5, its most capable and robustly aligned AI model to date, delivering leading coding and agentic performance with significantly reduced token usage and competitive pricing.
