Skip to content
Projects

What I build, and how

Own projects where I build the whole chain — from raw source to a working dashboard or AI application, with the full approach and the code in the open so you can see how I work.

01 — Own project

Digital twin: an AI agent that answers for me — with sources

A LangGraph agent over my CV, projects and writing that answers visitors' questions in a streaming chat: every claim cited, refusal when there is no source, a hard daily cost cap, and human approval before it acts on my behalf.

GenAI
Agents
LLM
Python
Guards

Fail closed, no model

Eval gate

95% tools · 90% tasks

Risky actions

Human approval

02 — Own project

Open data warehouse: a Kimball star schema on RDW and CBS

End-to-end ELT platform on Dutch open data: Python ingestion, dbt transformations and a documented star schema — with tests and CI on every pull request.

dbt
SQL
Python
DuckDB
Data Engineering
Star schema

3 documented grains

CI on every PR

Lint + build + tests

From zero

One command

03 — Own project · 3 weeks

Real-time public transport streaming pipeline on Kafka

Every vehicle in Dutch public transport, streamed live — from GTFS-realtime feed to a map of the whole country, with the correctness guarantees to go with it: per-partition watermarks, at-least-once with idempotent upserts, a dead-letter queue and replay from the raw archive.

Kafka
Streaming
Python
Postgres
Docker
Morning rush

176 messages/s

Windows

5 min · 4 dimensions

Failure path

DLQ + replay

04 — Own project

Strafrecht-RAG: no source, no answer

RAG over 1,906 Dutch criminal-law rulings with one rule: no source, no answer. Every claim ends in an ECLI, section and paragraph — and that reference is checked in code, not requested from the model.

GenAI
RAG
Python
LLM
Source accuracy

100%, by construction

Claim acceptance

89%

Corpus

1,906 rulings · 0 parse errors