# Jan Willem Altink

> AI builder and product owner writing on AI and Technology

## About

This is Jan Willem Altink's personal website and blog.
Topics include coding, AI agents, developer tooling, and software development.

## Pages

- [Hi](https://janwillemaltink.com/index.md): Home page: a short intro, recent writings, and how to connect.
- [Believes](https://janwillemaltink.com/believes.md): A living document of principles and beliefs I try to live by, across craft, learning, and collaboration.
- [Resume Jan Willem Altink](https://janwillemaltink.com/resume.md): Resume of Jan Willem Altink - AI builder and product owner with experience in AI engineering, web development, and product management.
- [Writings](https://janwillemaltink.com/writings.md): A list of my writings on coding, agents, and building software, with short descriptions and links to each post.
- [Writings archive](https://janwillemaltink.com/writings/archive.md): A complete archive of all my writings on coding, agents, and building software, organized by year.
- [Tags](https://janwillemaltink.com/tags.md): Full tag map (by topic)
- Tags index (HTML): https://janwillemaltink.com/tags/

## Writings

- [Sticker Generator with n8n and Gemini](https://janwillemaltink.com/writings/n8n-sticker-generator-with-gemini-and-supabase.md): An n8n workflow that generates stickers with Gemini, removes backgrounds using Python task runners, and stores results in Supabase.
- [My Agent Rules](https://janwillemaltink.com/writings/my-agent-rules.md): Guidelines for structuring and operating codebases to maximize safe autonomy, high-quality output, and efficient use of agent context.
- [The Case for Simple Agent Structures](https://janwillemaltink.com/writings/simple-loops-beat-multi-agent-architecture.md): Why a bash while loop often outperforms elaborate multi-agent systems. Research shows single agents with good validation beat coordination overhead.
- [Good Validation Enables Good Agents](https://janwillemaltink.com/writings/good-validation-enables-good-agents.md): A walkthrough on building a unified validation system with gates and transformers that works across Claude Code, Cursor, and git hooks.
- [My Principles for Successful Coding Agents](https://janwillemaltink.com/writings/my-principles-for-successful-coding-agents.md): A mental model for working with coding agents: Rules, Scopes, Validators, and Gates (RSVG). How to use deterministic checkpoints to guide probabilistic agents.
- [New Macbook Guide](https://janwillemaltink.com/writings/new-macbook-guide.md): My personal migration guide for setting up a fresh MacBook with 1Password, Homebrew, Zsh, and a developer-focused toolchain.
- [We Are Learning to Speak Machine](https://janwillemaltink.com/writings/we-are-learning-to-speak-machine.md): The story of AI has been about machines understanding us. But something else is happening: we are changing how we write.

## Prompts

AI prompt templates for assisted reading of articles on this site.

- [Find More Resources](https://janwillemaltink.com/prompts/find-resources.md): Find additional high-quality resources related to an article's topics
- [Interview Questions](https://janwillemaltink.com/prompts/interview-questions.md): Generate thoughtful interview questions based on this resume
- [Candidate Summary](https://janwillemaltink.com/prompts/candidate-summary.md): Generate a concise executive summary of this candidate for hiring managers
- [Summarize Article](https://janwillemaltink.com/prompts/summarize.md): Generate a TL;DR and key takeaways from an article using expert analysis
- [Match Job Requirements](https://janwillemaltink.com/prompts/match-job.md): Help recruiters assess how this candidate's experience aligns with a specific job opening

## Links

- Website: https://janwillemaltink.com/
- RSS Feed: https://janwillemaltink.com/rss.xml