Arca — applied AI studio · Norway

AI systems that read your documents, so your engineers don’t have to.

I turn decades of scattered files and manual processes into structured, searchable, automated systems — built for industrial companies that need working software, not demos.

Start a project See the work ↓

arca (lat.) — chest, vault; the root of “archive.”

01 — About

I’m Nicholas Johnsen. Arca is my studio.

I’m an AI engineer based in Norway, and I work on a specific kind of problem: decades of knowledge trapped in documents, and skilled people spending their days moving information around by hand.

My work spans applied AI end to end — document intelligence, retrieval-augmented generation, and agentic automation — with a strong bias toward systems that run where your data lives. When confidentiality matters, I build on local, self-hosted models: your documents never leave your infrastructure.

I’m not an agency. When you work with Arca, you work with the engineer who scopes the problem, builds the system, ships it — and answers for it afterwards.

Based in
Norway
Focus
Applied AI for industry
Methods
Document intelligence · RAG · agents
Privacy
Local & self-hosted models
Clients
Industrial & engineering companies
02 — Work

Case study 01 · Energy · Oil & Gas equipment

From forty years of files to one system that knows what’s in them

Before

A major energy-sector equipment company had decades of engineering knowledge locked in a legacy document system — heat & material balances, process flow diagrams, drawings, datasheets. Finding a value meant knowing which PDF to open and where on the page to look. Tendering meant engineers reading balance sheets line by line and re-typing values into component datasheets, by hand, for every single bid.

After

Arca built an internal platform that ingests the entire archive and makes it structured, searchable and intelligent — including search inside PDFs and drawings, not just across filenames. On top of it sits an AI agent that automates the tendering process: it reads HMBs, PFDs and engineering drawings, and auto-populates the standardized datasheet template for each component. Engineers review the result instead of producing it.

What it does

  • Full-archive ingestion — decades of legacy files, one structured index
  • Search inside documents: PDFs, drawings and datasheets, down to specific values
  • AI tendering agent that reads HMBs, PFDs and drawings
  • Auto-populated component datasheets from standardized templates

What changed

  • Datasheet population went from hours of manual entry to minutes of review
  • Any value in the archive is one query away instead of one afternoon away
  • Faster, more consistent tenders with fewer transcription errors
  • One source of truth replacing a clunky legacy system

Selected work 02 · Coming soon

Next case study in progress

A second project is being written up. If you want references in the meantime, just ask.

Selected work 03 · Coming soon

This slot is reserved

Architecture visualisation, interactive 3D, web rebuilds — more selected work will appear here.

03 — What I can build for you
  • 03.1

    Document intelligence & smart search

    Decades of legacy files become one searchable system — inside PDFs, drawings and scans, not just filenames. Ask a question; get the page.

  • 03.2

    AI process automation

    Repetitive engineering paperwork handled by an agent: datasheet population, form filling, tender preparation. Your people review — they stop retyping.

  • 03.3

    Private RAG & self-hosted AI

    AI on your data, under your rules. On-premise or private-cloud systems for confidential documents — nothing leaves your infrastructure.

  • 03.4

    AI consulting & implementation

    From “where would AI actually help us?” to a shipped system. Scoping, prototyping, delivery — one engineer, accountable end to end.

Every engagement starts the same way: a short call about the problem, then a concrete proposal. Tell me what’s slow.

04 — Contact

Tell me what’s slow.

A document archive nobody can search. A process your engineers do by hand. An AI idea you want a second opinion on. Send a few lines — no deck required.

Prefer email? Write to nicholas.johnsen@outlook.com

Usually replies within one working day