The Question
How do you stop a model from being confidently wrong?
  • How do you stop a model from being confidently wrong?
  • How do you digitize a workflow without killing the judgment that made it work?
  • What's the MVP for a tool someone will actually open twice?
  • How do you decide which requests get the expensive model?
  • How do you design for a user whose worst day is your average Tuesday?
  • How do we ship public-interest software on a non-profit budget?
Production system

Not a prototype.
A system in production.

One platform I built and operate end to end — the figures below are measured, not modeled.

Comments processed
5.4M+

26,000+ posts monitored

Tokens per cycle
1.4B

~€0.0035 per unit, blended

Production services
19

Owned end to end

Self-hosted GPUs

A100 / H100 / H200, multi-GPU inference

Criminal statutes
12

Structured legal evaluation, not keywords

Min. evaluation-gate agreement
90%

Benchmarked vs. a certified EU dispute-settlement body

Lower inference cost
~65%

vs. running a frontier model on everything

Of measured community reach
81.6%

Identified via network/graph discovery

Systems

Systems I build.

Not a skills cloud — the categories a production AI system actually needs.

  1. I

    AI & inference

    Serving and evaluating models in production, not just calling an API.

    • vLLM
    • Qwen3
    • OpenAI / Anthropic / Gemini APIs
    • Multi-GPU serving
    • A100 / H100 / H200
    • Tensor parallelism
    • Structured / grammar-constrained decoding
    • Prefix caching
    • Model benchmarking & evaluation
    • Inference cost optimization
  2. II

    Data & distributed systems

    The pipelines and queues that move millions of records without losing any of them.

    • Python
    • FastAPI
    • PostgreSQL
    • Redis / BullMQ
    • Distributed queues
    • Worker architectures
    • Large-scale ingestion
    • Corpus construction
  3. III

    Production infrastructure

    I own the infrastructure this system needs to stay up — deploys, rollbacks, and the pager.

    • Docker
    • Kubernetes
    • GCP
    • AWS Lambda
    • Hetzner
    • Monitoring & telemetry
    • Deployment
    • Rollback
  4. IV

    Application engineering

    The operator console that separates what the machine decided from what a human decided.

    • TypeScript
    • NestJS
    • Next.js
    • RBAC
    • Audit logging
    • Operator consoles
    • Case review workflows
  5. V

    Automation

    Where a report has to come from a real device, not an API call.

    • Appium
    • REST APIs
    • Physical-device orchestration
    • Evidence capture
The Bridge

Half a career on each side
of the same gap.

I've spent the years since 2019 building production software where regulation actually bites — ERP and indirect-tax compliance, security operations, and now production AI systems for civic accountability and legaltech. Every regulated domain shares the same problem shape, and engineers who can cross between the legal, product, and infrastructure sides of it are rare.

Today I build and operate a production AI system out of Berlin — model serving, evaluation, and the infrastructure underneath — for civic accountability work in German criminal law. I don't make legal decisions. I build the systems the people who do rely on.

Notes

Latest notes.

Field notes on product, process, and the places where law and software disagree.

  1. No. 002·2026-04-08

    The cost of a hallucinated citation

    4 min
  2. No. 001·2026-04-05

    Why we optimize for removal, not detection

    3 min
Get in touch

Get in touch.

A few questions, so I know what you're working on. No newsletter, no follow-up — I read every one myself.

Question I of IV

What's this about?