Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: prompting
Twelve Patterns for Writing Idiomatic Go With Claude Code
Twelve Claude Code patterns for idiomatic Go: interface-first prompts, test-driven loops, CLAUDE.md rules, error wrapping, concurrency and Plan Mode limits.
7 min readFour AI Agent Roles for Engineers: Coordination, Creativity, Clarity, Coaching
Four AI agent roles engineers can hand real work to: coordination, creativity, clarity and coaching, from a morning briefing to mock interview practice.
6 min readWriting a CLAUDE.md That Claude Actually Follows in Every Session
Stop repeating yourself in each new chat: place the file, replace vague rules with specifics, list real commands, record quirks, and skip temporary notes.
5 min readChaining AI Tools Into Daily Workflows Without Constant Prompting
How to turn separate AI tools into a repeatable pipeline: avoid compounded prompting errors, use a simple orchestrator, and design, test, and validate each stage.
6 min readExtract Your Visual Style, Then Lock It Into an AI Image Workflow
Use Claude Design to extract a color and composition spec from your best work, resolve contradictions, lock a prompt block, and package it as a Skill with audits.
10 min read13 Claude Habits to Fix: Prompts for Agreeable, Confident, Forgetful Chats
Thirteen Claude habits nobody warns you about, from agreeing too fast to sounding sure when it's wrong, each paired with a short prompt that corrects it.
7 min readReAct from scratch: thought, action, pause, observation without a framework
A tiny ReAct loop built by hand on Groq: thought, action, pause, observation, manual first, then regex tool calls, so LLM agent frameworks make sense.
6 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.