Agentas AS designs, builds, and operates software the AI-native way — from industrial control systems to LLM-driven systems, agentic automation, and custom applications, taken from brief to production. Grounded in eight years delivering software for industrial and critical systems, from subsea control to operator tools.




Delivered for operators, EPCs, and system integrators on the Norwegian Continental Shelf — and for Norwegian industry onshore.

Production LLM-driven systems built to run, not just to demo — agents, retrieval (RAG), tool-use, and continuous evaluation harnesses that measure output against real data. Designed for reliability, observability, and cost control.

Agentic pipelines and integrations that replace recurring manual work — data ingestion, document processing, and scheduled jobs that feed your business systems. The automation discipline from industrial control, applied to software.

Full-stack applications with AI at the core — Go, React, and TypeScript, self-hosted and secure by design. From internal tools to public products, built end-to-end and operated in production on our own infrastructure.

Programming industrial controllers (PLCs) that automate and monitor equipment on Siemens platforms. We build custom control logic, reusable software libraries, and simulation systems for underwater and platform-based operations.

Designing the screens and dashboards that operators use to monitor and control industrial processes. We build complete visual systems for real-time monitoring, alarm handling, and step-by-step operator guidance.

Complete software for controlling underwater oil & gas equipment — from the communication between surface platforms and seabed devices, to integrating valves, sensors, and hydraulic power systems. Proven delivery on active Norwegian Continental Shelf projects.

Making different industrial systems talk to each other. We set up secure, reliable data connections between physical equipment, controllers, and business systems using industry-standard communication protocols and cloud platforms.

Tailor-made software built to solve your specific problems. From automation scripts and data tools to complete web applications — using Python, LUA, and modern web technologies to fit industrial and business needs.

Hands-on support when systems go live — both on-site and offshore. We handle factory acceptance testing, on-site verification, equipment testing, and production startup to ensure a smooth handover from development to daily operations.
The industrial delivery record that underwrites everything Agentas ships — eight years of software for systems where downtime is measured in lost production and failure is not an option.
Siemens Energy — Ivar Aasen
Software Lead for the complete control system. Built the software that manages communication between the platform and underwater equipment, operator screens, simulation tools, and integration of valves, flow meters, and hydraulic systems. All four underwater production wells are now online — first oil achieved.
Read the case study →
Siemens Energy — Ivar Aasen
Complete control system software development on Siemens platforms, including operator interfaces and standardized subsea communication. Successfully delivered through all testing phases, on-site startup, and now running in production.
Read the case study →
OneCo Technology
Building a backup water supply system for Norway's capital. Developing the control software and operator screens that ensure reliable operation of this critical city infrastructure.
Read the case study →
OneCo
Smart building automation for one of Norway's largest hospital construction projects. Programming intelligent lighting control and building management systems that keep the hospital running efficiently.
Turfpal
Custom software development for intelligent turf lighting systems. Control logic and automation for mobile sports field lighting rigs used across professional and municipal facilities.
Siemens
Modernizing and digitizing control systems on the Valhall offshore platform. Upgrading monitoring software and producing safety documentation to Norwegian industry standards.
At Agentas, AI is not a buzzword — it is how we work every day. We use Anthropic's Claude Code as our primary development tool, harnessing its full capabilities to write code faster, solve problems smarter, and deliver projects more efficiently. This website itself was built, deployed, and is maintained entirely through Claude Code — living proof of what AI-powered engineering can deliver.
A selection of LLM-driven and AI-augmented systems Agentas runs end-to-end on our own infrastructure. Each entry focuses on the engineering — the back-end, the architecture, and the operational discipline — rather than the specific domain it serves.
A public analytics platform with a server-side parsing pipeline (worker-thread architecture for high-throughput ingestion), normalised relational storage, and a modern web frontend. Runs across four isolated containers — dev + prod per tenant — behind a shared reverse proxy. Built and operated single-handedly.
View details →A computational simulator written in Go with a browser-based UI and a continuous evaluation harness that compares simulator output against real observed data — surfacing discrepancies explicitly rather than papering over them. Built on a multi-class architecture with a shared widget system across simulators.
View details →Self-hosted file management platform (Go + React) built around a deliberate security model from day one — access control, audit logging, encrypted backups, and regularly rehearsed recovery. Designed so that “self-hosted” is safer than the cloud alternative, not an excuse to be sloppier.
View details →An automation pipeline that pulls live vehicle telemetry into a structured database, then runs scheduled jobs that feed mileage and timesheet entries to downstream business systems. Replaces a recurring monthly manual task entirely — small in scope, real in time saved.
View details →A multi-server environment evolved over two years into a small private cloud — 15+ services across web apps, automation, monitoring, and home systems. Standardised deployment pipeline, layered defence-in-depth security, three-tier backups with rehearsed recovery, and a living architecture reference maintained like a runbook.
View details →Internal projects that stress-test the AI-native workflow — games, apps, and home systems built with the same engineering discipline.
Self-hosted smart-home platform integrating Z-Wave and Wi-Fi devices, scheduled automations, multi-room control, and energy monitoring. All configuration version-controlled and deployed through an automated pipeline — the same engineering discipline applied at home as in client systems.
View details →A top-down 3D survival game built in TypeScript and Three.js — an R&D project exploring game development and real-time 3D rendering with the same AI-augmented workflow used across the rest of the work.
View details →A top-down isometric gothic action-RPG — Diablo-leaning combat and a legible loot loop, built in TypeScript, Three.js and an ECS on the Frostwake engine foundation. A playable prototype exploring real-time 3D combat with the same AI-augmented, multi-session workflow.
View details →A no-BS gym app — only the stuff you use at the rack: sets, reps, kg, a rest timer, heart rate. Local-first, no account, no subscription. Built as a React + TypeScript PWA, packaged for Android with Capacitor, with its own landing page and public APK download.
View details →Click any card for details and screenshots. Several projects are live and linked; the rest are kept private — code walkthroughs and demos are available for serious enquiries, just get in touch.
A call or a written scope — we ask the questions that matter and give an honest read on feasibility.
Fixed scope or running engagement, with explicit assumptions and success criteria.
Short iterations with working software early and AI in the loop — you see progress continuously.
We run what we ship — or hand it over documented and tested.
Agentas AS is a Norwegian software engineering consultancy led by Martin Davidsen. We design, build, and operate software the AI-native way — LLM-driven systems, agentic automation, and full-stack applications, shipped end-to-end and run in production. AI is not an add-on to how we work; it is the method.
That practice is built on eight years of delivering software for industrial and critical systems — subsea production control, offshore platforms, and operator tools across the energy sector. Based in Rogaland, with a background in maritime electrical automation and certified electrician credentials, we understand systems from the field hardware up to the software that runs them — and we bring that same discipline to every AI system we ship.
Every project is designed, built, and shipped with AI in the loop — from prototype to production and ongoing operation on our own infrastructure.
Certified electrician with Siemens expertise and offshore commissioning credentials.
Track record with Siemens, Siemens Energy, and major Norwegian infrastructure projects.
Agentas is led and operated by Martin Davidsen — a Norwegian software and automation engineer with eight-plus years of experience building software for complex industrial environments. Originally trained in maritime electrical automation, with certified electrician credentials and offshore commissioning experience, with a track record across Siemens Energy and Aker BP subsea developments, OneCo automation projects, and major Norwegian infrastructure work.
Alongside industrial delivery engagements, Martin builds and operates Agentas' own LLM-driven systems end-to-end on company infrastructure. Real users, real traffic, real consequences when something goes wrong. That work is showcased in the AI & Innovation section above.
The combination — industrial discipline paired with hands-on AI engineering — is what Agentas brings to every project.
Whether you need expert automation engineering, custom software, or guidance on integrating AI into your workflows — we're ready to help.