Specialised in agentic automation.
Founder and engineer of Lovguiden, a service for Danish law used by more than 580,000 people in the past year. Its data is collected from over 2,000 public sources and processed automatically, and when a source changes, the system repairs itself. Agentic automation built on the same foundation is also developed for other businesses.
Used every day by legal professionals.
Lawyers, accountants, public servants and journalists use Lovguiden in their daily work. Figures from the site's analytics.
Systems that run by themselves.
The same technology that runs Lovguiden, built around a company's own data and workflows. Every system is designed to run without supervision and to show where its answers come from.
Agentic automation
Recurring work handed to AI agents that run on a schedule: collecting data, checking it, writing and reporting. Every run is logged, and when a source changes, the system diagnoses the fault and repairs it.
- Scheduled agents and data pipelines
- Monitoring, alerts and self-repair
- Runs locally or in the cloud
AI assistants on company data
Search and an AI assistant across internal documents, rules, contracts or case files. Answers come from that material only, and every reference is checked before anyone sees it.
- Answers with verified sources
- Local models when data can't leave the building
- Search tuned to the domain
Company data inside AI tools
MCP servers and APIs that bring internal data into Claude, ChatGPT, Copilot and custom agents, so AI tools work with what the business actually knows. AI assistants such as ChatGPT, Copilot, Gemini and Claude already send around 600 visitors a month to Lovguiden.
- MCP servers with access control
- Documented REST APIs
- Usage-based billing for paid access
AI-run operations
An existing business rebuilt so the routine runs itself: website, bookings, invoicing and back office, plus agents that write content and campaigns every day.
- Website, back office and payments
- AI newsroom and campaigns
- Migration alongside the old system
Document-heavy teams
Hours spent finding, copying or checking information are usually the first thing that can be automated.
Lovguiden. Danish law you can verify.
Legislation, case law, parliamentary work and EU law in one service, with an AI assistant that shows its sources. Used by lawyers, accountants and public servants every day.
Lovguiden brings Danish legislation, rulings, parliamentary work, EU law and preparatory works together in one searchable, cross-referenced service. Everything is kept current automatically, and an AI assistant answers questions with a source behind every statement. The same data is available to other AI tools through an MCP server and to businesses through an API.
- Role
- Founder and engineer
- Live at
- lovguiden.dk · mcp. · data.
Visitors are a 12-month average from web analytics. Organisations and cross-references as published on lovguiden.dk.
I'm very impressed with Lovguiden. It's a tool that has been in demand for a long time. Limiting it to legislation, verdicts and decisions makes the AI search far more trustworthy than the chatbots we know.
Søren Engers
VAT Director, Baker Tilly
A product that creates overview and is intuitively simple to use is something I have missed for about 40 years. Lovguiden is the product that today comes closest to giving me that overview of tax legislation.
Ole Aagesen
Lecturer, CBS, and author
The database gives quick access to legislation, from bill to enactment, along with a large number of rulings and decisions. The chatbot quickly gives an overview of the relevant legislation.
Reza Ahmadian
Lawyer
From a document on a public website to an answer with a source.
How it fits togetherOne search across laws, rulings, hearings, parliament and EU law, ranked for legal relevance.
An AI assistant that answers from the source material and links every reference it makes.
An MCP server that brings Danish law into Claude, ChatGPT and other AI tools.
A REST API for companies that build their own products on the data.
Parliament made readable: votes, debates and a daily tracker for every politician.
Every law consolidated, with its amendment history and the bills that will change it.
Subscriptions, invoicing to public institutions and usage-based billing for the API.
The same approach, for other businesses.
Get in touch// claude_desktop_config.json { "mcpServers": { "lovguiden": { "url": "https://mcp.lovguiden.dk/api/mcp" } } } // 35 tools, e.g. search_love · get_forarbejder · search_domme get_lov_historik · search_eu · oda_get_sag
# verdicts on advisor liability curl "https://data.lovguiden.dk/v1/domme\ ?q=ansvar%20for%20mangelfuld%20r%C3%A5dgivning" \ -H "Authorization: Bearer lg_live_…" # priced per call, surfaced in headers X-Lovguiden-Pris-DKK X-Lovguiden-Prisklasse # OpenAPI 3.1 at /v1/openapi.json · llms.txt at /v1/llms.txt
Fully automated and running locally.
All of Lovguiden's data is collected, processed and updated by a purpose-built system that runs locally. When a public website changes and a data source stops working, an AI agent repairs it and verifies the fix. The figures below are based on the system's own measurements.
Around 40 jobs run on a fixed schedule, day and night.
Connections, database and storage are checked before each run.
Jobs run in parallel within set limits and recover after interruptions.
Every run is logged, and jobs that stop returning data are flagged.
An AI agent diagnoses a broken data source and prepares a fix.
A fix is only applied after it has been tested against the live source.
Self-repair, step by step
An AI agent diagnoses a broken data source and prepares a fix. A fix is only applied after it has been tested against the live source.
Two products, built and operated end to end.
Lovguiden, founded and run by Oscar Lauge Hoffmann, and opkurser.dk, a client project where a course business from 1999 got a new website, back office and an automated newsroom.
From first conversation to a running system.
A small first step, then a system that runs on its own.
- 01
Conversation
The work that takes too long is described, followed by an honest assessment of whether AI and automation can take it over, and roughly how.
- 02
Prototype
A first version on real data, so the result can be seen working before anything larger is committed to.
- 03
Build
The full system, built in short iterations with regular demos, so progress can be followed all the way.
- 04
Operate
Operated and monitored as a service, or handed over with code and documentation to an in-house team.
Is it only for legal tech?
No. Lovguiden is legal, but the methods apply anywhere with many documents, many sources or repetitive work. opkurser.dk is a course business.
Can data stay in-house?
Yes. Lovguiden's data processing runs on local models, and the same setup can run on a company's own infrastructure, so sensitive data never has to leave it.
What happens when something breaks?
The systems are monitored and repair common faults on their own, such as a data source changing its format. Anything they can't fix is flagged.
What does it cost?
It depends on the scope. A concrete proposal follows the first conversation, and the first step is kept small.
Who owns what is built?
It is agreed up front. The full source code and documentation can be handed over.
Which languages?
Danish and English.
SupaChat: an open-source version of Lovguiden.
An open-source starter for AI chat applications, built on the same foundations as Lovguiden.
SupaChat is a free, MIT-licensed release of Lovguiden's application layer, meant as a starting point for others. It includes Claude-powered chat with document search and page-level citations, an artifacts workspace, long-term memory, charts and interactive tools, PDF generation, web search, image generation, per-token usage dashboards and complete user authentication with Supabase.
| Feature | Lovguiden | SupaChat |
|---|---|---|
| Next.js 16 and React Server Components | ||
| User accounts with Supabase | ||
| AI chat with tools | ||
| Document upload and search | ||
| Danish legal database, 2,000+ sources | ||
| Automated, self-repairing data collection | ||
| Set up with a single SQL file |
Founder and engineer, based in Copenhagen.
Oscar Lauge Hoffmann founded Lovguiden in November 2023 and has developed and run it since. It is now used by hundreds of thousands of people a year, and its data operations are fully automated.
The work covers the whole product: data collection, search and AI, the interface and billing. The focus is on systems that run reliably without supervision and can show where their information comes from. Alongside Lovguiden, he builds the same kind of systems for other businesses.
Automation
Recurring work is automated, and the systems are built to detect and repair their own faults.
Runs locally
Data processing runs locally, which keeps costs predictable and the data under full control.
Accuracy
AI output is grounded in source material, and every reference can be checked.
End-to-end ownership
Products are taken from the first data source to the finished interface and the invoice.
What it's built with.
The technologies behind Lovguiden and opkurser.dk.
Automation
01- Scheduled data pipelines
- Self-repairing AI agents
- Linux servers
- Monitoring and alerts
AI
02- Local language models
- Claude and Gemini
- MCP servers
- Retrieval and search
Data
03- PostgreSQL · Supabase
- Vector search
- Web scraping
- REST APIs
Product
04- Next.js · React
- TypeScript
- Tailwind · shadcn/ui
- Stripe
From first commit to today.
Key milestones since 2023.
- Oct 2023
SupaChat released as open source
An open-source AI chat starter, now in its fifth version.
- Nov 2023
Work on Lovguiden begins
It started as a chatbot for Danish law and grew into a complete legal information service.
- Mar 2025
Automated data collection
Collection and processing of public data moved into a dedicated system.
- 2025
Runs locally
All data processing now runs locally and fully automatically.
- Aug 2025
opkurser.dk
A new website, back office and newsroom for Økonomi & Personale.
- 2026
MCP server and public API
Lovguiden's data made available to AI tools and to other businesses.
- 2026
Self-repairing data sources
Broken data sources are now diagnosed and repaired automatically.
Get in touch.
For recurring work that takes up too much time, or data nobody has the hours to go through. A short description of the task is enough to start the conversation.