Quoted by complexity
CI/CD & quality-gate setup
One deterministic rule set - format, lint, types, tests, coverage, security - that runs identically in the editor, before push and in CI. Ratcheted so legacy code can adopt it on day one.
For AI agents: a documentation index is available at /llms.txt. Every page also has a Markdown version at its URL plus .md.
← What I do
~/what-i-do/platform
Platform & Infrastructure
Good platforms are paved roads: the safe, observable, repeatable way is also the quickest way to ship. I build the plumbing that makes that true, from pinned toolchains and scaffolding to config and policy as code.
01What I can do for you
Quoted by complexity
AI platform engineering
One shared way for every team to use LLMs: a provider-agnostic gateway with cost-aware model routing, usage and spend per team, guardrails, caching and evals, so each new AI feature starts on a paved road.
02How I work
Paved roads over gatekeeping
Make the right way the default with templates and shared workflows, instead of reviewing every team into compliance.
Seen in: Foundry →
Everything as code
Pipelines, configuration and policy live in the repo, reviewed and versioned like any other change.
Seen in: Foundry →
A golden path with an escape hatch
The default is opinionated, and there is a documented, reviewed way off it. Teams that can’t leave the road route around it instead.
Seen in: Foundry →
Adopt it one small PR at a time
An existing codebase comes up to standard in small, reviewable steps alongside normal work, not in a big-bang migration that stalls everything else.
Observable by default
Logs, run summaries and cost figures come with the template, so the first question about a running system has an answer before anyone asks it.
Pin the tool, not just the action
Shared workflows are versioned, and every tool they install has an exact version. Nothing resolves to "latest" and breaks on a Tuesday.
Seen in: Foundry →
03What I’ve built
Illux Product AI
Generative-AI product enrichment & room visualization for Shopware 6
- PHP 8.2+
- Shopware 6.6-6.7
- Symfony Messenger
- RabbitMQ
Foundry
A polyglot engineering gate for AI-assisted development
- GitHub Actions
- mise
- Python
- POSIX shell
jev-tools
Three TypeScript tools that put a cheap, typed model in front of the expensive one
- TypeScript
- Node.js
- Jev
- GitHub Actions
04Writing
AI in the webshop: from a slick demo to something that holds up in production
What it takes before AI-generated product copy can run in a real webshop - lessons from a solution that has enriched more than 3,000 products.
Five tasks a small business can automate - and how to find them
How to spot the manual work that's worth automating, with five typical examples from small and medium-sized Danish businesses.
Case study: a cheap, typed model in front of the expensive one
Three open-source tools - an agent guardrail, a GitHub issue-triage Action and a bulk classifier - built on one pattern for AI automation that's cheap enough to run on everything.
Case study: automating product data for 3,000+ products with an LLM
How a Shopware 6 plugin turned product images into multilingual copy, SEO and categories for Illux - and the guardrails that made it safe to run unattended.