HUGO.CHARMIES(1)
PRODUCTION
$ hugo --whoami
Full stack developer in Belgium. I build internal tools that replace manual and paper-based work, most recently at Vanwezel Autoparts.
$ hugo --status
status : ● Open to full stack roles location : Limburg · Belgium daily_driver : Claude Code favourite_stack: Next.js · Postgres
$
$ hugo --now
$ hugo --featured








$ hugo --stack
AI
────────────
FULL STACK
────────────
INFRA & TOOLS
────────────
$ hugo --origin
I studied Applied Computer Science in Leuven. For a school project, a client needed indicators scraped from the web, which was all manual work. I automated it with an AI model and saw how much faster you can build now.
Since then I build with AI coding tools like Claude Code, and I test and review what they produce. What I like most is finding a slow process and replacing it with a small app.
EDUCATION
UC Leuven Limburg
BSc Applied Computer Science · 2022–2025
FIRST AI PROJECT
Ecofoodmap · n8n → code-native
WAY OF WORKING
Claude Code, then test and review
$ hugo --archive
$ hugo --contact
$ open ~/projects/prospecting
HUGO.PROSPECTING(1)
STACK
Next.js · Prisma · Postgres · better-auth · KBO ingest · SerpAPI · LLM enrichment
01 / 04
The brief. I run Parallel Studio, a small service that sets up Google Business Profiles and lead-capture for Belgian SMEs. To find clients I had to read the Belgian company registry by hand. Looking up each company in KBO, Googling them, scoring fit, drafting a WhatsApp message. I built the platform that collapses all of it.
02 / 04
The KBO catch. The registry doesn't expose contact info. The companies are names and numbers. Worse, my target clients were the ones with no Google Business Profile, the un-googleable SMEs my whole service exists to make findable. The leads I most wanted to enrich were the leads least likely to auto-enrich. I had to build for that shape.
03 / 04
The bit I'm proudest of. Two-flow enrichment. When the model is confident, it auto-fills contact and decision-maker. When the model is not confident, the CRM surfaces a button that opens a pre-filled Google search for the company. I eyeball it in five seconds, type the missing piece, the pipeline moves on. Five seconds of human attention beats five minutes of model hallucination. AI in the loop, human at the checkpoint, encoded in product not in a slide.
04 / 04
What's there, what's not. Live: KBO ingest, AI enrichment with the two-flow confidence gate, WhatsApp message templates per lead. Not yet: scheduled sends, full AI outreach via WhatsApp. The plan is to close that loop next. Iterating slowly on the side.
SCREENSHOTS
$ Building the tool I needed for my own business, while my own business waits its turn.