$ hugo --whoami

I orchestrate AI tools
to ship products,
workflows, and integrations.

Shipping production AI at Charmies. Co-developing Kompass. Based in Belgium.

$ hugo --status

status         : ● Open to AI engineering roles
location       : Hybrid · Belgium
daily_driver   : Claude Code
favourite_stack: Next.js · Postgres

$ hugo --now

>Shipping AI integrations at Charmies
>Co-developing Kompass — late-prototype SaaS, in active investor talks
>Building Personal Helper — my own Claude Code skill library

$ hugo --featured

01 / 08

HUGO.CHARMIES(1)

PRODUCTION

STACK

Next.js · Supabase · Vercel AI SDK · tool calls · RAG

NAME

Charmies, operations platform + production agent for a 40 yr old Belgian staffing agency

OPEN

$ hugo --read charmies [click to expand]

02 / 08LIVE ↗

HUGO.KOMPASS(1)

LATE PROTOTYPE

STACK

Next.js · Supabase · react-globe.gl · deck.gl · pmtiles · live AIS feed

NAME

Kompass, opening commodity brokering up

OPEN

$ hugo --read kompass [click to expand]

03 / 08

HUGO.AA(1)

PROTOTYPE

STACK

Next.js · Drizzle · SerpAPI · Cheerio · LLM scoring + briefs

NAME

AA Pipeline, lead enrichment for an AV integrator in New Zealand

OPEN

$ hugo --read aa-pipeline [click to expand]

04 / 08

HUGO.PROSPECTING(1)

HOBBY PROJECT

STACK

Next.js · Prisma · Postgres · better-auth · KBO ingest · SerpAPI · LLM enrichment

NAME

Parallel Studio Prospecting, a CRM I built to find my own clients

OPEN

$ hugo --read prospecting [click to expand]

05 / 08LIVE ↗

HUGO.LOODGIETER(1)

LIVE DEMO

STACK

Next.js · Supabase · Coolify VPS · Codex + Claude two-agent build

NAME

Loodgieter Demo, the platform I built before I sold it

OPEN

$ hugo --read loodgieter [click to expand]

06 / 08

HUGO.BOT(1)

PRODUCTION

STACK

Python · python-telegram-bot · pyrogram · aiohttp · aiosqlite · Docker

NAME

Vanity-handle marketplace, the parts of Telegram that aren't a bot

OPEN

$ hugo --read vanity-handle-bot [click to expand]

07 / 08LIVE ↗

HUGO.PSWEB(1)

LIVE

STACK

Next.js 16 · next-intl · Motion v12 · OGL · Resend

NAME

Parallel Studio, the homepage for a service I run

OPEN

$ hugo --read parallel-studio-website [click to expand]

08 / 08

HUGO.HELPER(1)

PRIVATE

STACK

Claude Code · custom skills · MCP servers · hooks · persistent memory

NAME

Personal Helper, the toolkit that ships my other projects

OPEN

$ hugo --read personal-helper [click to expand]

$ hugo --next

kalai COMING SOON
iOS calorie tracker, camera-first, sub-10-second logging.
Swift 6 · SwiftUI · Vision · SwiftData
sports-event-hub COMING SOON
Started as an airsoft hub. Reframing to a hub for any local sports event.
Next.js · TBD

$ hugo --stack

AI / AGENTIC

────────────

Agentic coding (Claude Code, Codex)
LLM SDKs · OpenRouter
Custom MCP servers
Agent harnesses + skills
Context engineering · evals

PRODUCT ENGINEERING

────────────

TypeScript
Next.js · React
Node.js · Python
PostgreSQL
Tailwind · shadcn
Any language the problem needs

INFRASTRUCTURE

────────────

Cloud: Azure · AWS
VPS-first (Docker · Coolify)
CI/CD · observability
Git

$ hugo --takes

LEAN OVER OVER-ENGINEERED

Most “agents” are one well-written LLM call plus retrieval. Add orchestration when a named failure forces it — long-horizon state, human-in-loop, fan-out you've already hit in production. Frameworks aren't wrong; they're premature.

ORCHESTRATION COMPOUNDS

The harness is the codebase now — SKILL.md, program.md, the context window, the agent graph. Sharpen this primitive and everything downstream multiplies. The catch: orchestration without evals is vibes with extra steps. Build the harness on top of eval discipline, not instead of it.

HUMAN-IN-THE-LOOP AT THE CHECKPOINTS

Models flip from correct to incorrect under casual pushback ~15% of the time. Manage AI like a mid-level report: trust it on execution, gate it on judgment. Continuous supervision is unsustainable; checkpointed approval before irreversible writes is the discipline that ships.

$ hugo --origin

At school we had a client in Leuven who wanted to automate scraping indicators like “what percentage of Belgians are obese.” Until then it was manual work. I'd seen something about n8n's AI agent feature, plugged OpenRouter into the workflow, and watched it scrape and reason about pages we'd have spent weeks on.

A few hours later I realised n8n was just making API calls — we could call OpenRouter directly from our own code. The whole flow migrated to native TypeScript. Around the same time we built the client's site with Bolt and I sat watching it generate a real custom website in minutes.

I haven't manually written code from scratch since. I'd rather spend the time learning to orchestrate agents. Coding ones, image ones, video ones, voice ones. Orchestration compounds across every sector.

EDUCATION

UC Leuven Limburg

BSc Applied Computer Science · 2022–2025

FIRST AI PROJECT

Ecofoodmap · n8n → code-native

CURRENT MODEL

Orchestrator, not writer

$ hugo --archive

prospect-enginenext.js · prisma · KBO datashelved
telegram-botpython · telegram apishipped
agent-orchestratorpython · langgraphresearch
ais-webscraperpython · playwrightshipped
youtube-summarizerpython · openaishipped

$ hugo --contact

hugorohach@gmail.com

linkedin.com/in/hugo-rohach

TWITTER / X

x.com/hugo_rhh