Showcase · Neuralex Legal

Dutch case law, searchable with proof

The lab's main project: a platform that indexes the complete Dutch case law locally and puts an AI layer on top that never answers without a source. Below you'll see exactly how the technology fits together — the result you can see live.

949,000
rulings searchable in full text
3.7M
rulings searchable on metadata
70–300ms
search response (FTS5)
16
law books linked
Architecture

From question to substantiated answer

Everything runs on our own hardware in the Netherlands. The edge is Cloudflare, the rest is self-built and self-hosted — including the entire search index.

User browser · mobile Cloudflare Edge WAF · CDN · tunnel Flask + Gunicorn ±70 routes · streaming API launchd KeepAlive · self-healing LLM chain any API · EU-hosted · local cost & latency per call uitspraken.db SQLite FTS5 · 19 GB 949,000 full-text · 16 law books dossiers.db accounts · dossiers knowledge base · metrics pgvector (NAS) :5434 · semantic search layer NEXT STEP rechtspraak.nl open data · nightly ingest
The RAG chain

Five steps, every claim traced to its source

The core of every Neuralex product: retrieval first, language model second, and an answer that only exists if the source carries it.

01

Question in plain language

The user describes a situation or asks a legal question — no jargon or ECLI numbers required.

02

Retrieval over 19 GB

An FTS5 full-text index searches 949,000 rulings in full and 3.7 million on metadata, plus 16 law books, in 70–300 ms.

03

Context with sources

The most relevant rulings and statutory articles go to the language model as context, complete with ECLI references.

04

LLM chain with fallback

A model-agnostic chain: any API can be plugged in — EU-hosted models or fully local — with cost and latency measured per call.

05

Answer with proof

Every claim in the answer gets a clickable source card: ECLI plus exact quote. No source, no claim.

Tech in detail

What's under the hood

FTS5 on 19 GB of SQLite

The complete Dutch case law in one local full-text index. No external search service, no data that leaves the building — yet responses in milliseconds.

Provider chain with cost tracking

Every AI call runs through an ordered chain of providers. The layer is model-agnostic: any API works, from models hosted exclusively on European servers to a model running fully on-prem. If a provider fails, the next one takes over — with model, tokens and cost logged per call.

Citation verification

The answer is only finished once every claim can be traced back to a real ruling or statutory article. Source cards show ECLI and the exact quote — verifiable in one click.

Self-healing deployment

The app runs under launchd with KeepAlive: if a process crashes or the machine restarts, the portal is back up within seconds. A health endpoint feeds external monitoring.

Daily data pipeline

New rulings from rechtspraak.nl are automatically imported, indexed and linked to statutory articles every night. The knowledge base publishes daily from a queue.

On-prem & GDPR — and what the demo does

The corpus — 949,000 rulings in full text, 3.7 million on metadata — sits on our own Dutch hardware and search happens entirely locally: the index never touches an external service. The language model is a separate choice. In the public demo the answering step currently runs through an external API, because that is cheap testing on public case law. When processing client data, that step runs EU-hosted or fully on-prem — which is exactly why the layer is built model-agnostic.

Built with PythonFlaskGunicornSQLite FTS5pgvectorModel-agnostic LLM layerCloudflare Tunnellaunchdn8n
Why this works

AI you can build on

Most AI fails on trust: it makes things up, it leaks data, or it doesn't fit the process. This portal flips those three around — and that's the blueprint for every Neuralex product.

Citations, verifiable

Every answer points to the exact ruling. The pipeline checks that a cited ECLI actually exists and supports the passage; where a claim fails that check it is flagged, not papered over.

Data stays in the Netherlands

On-prem or in a GDPR-proof environment. Sensitive data doesn’t leave the building and doesn’t go to an American cloud.

Built for the domain itself

Built on the processes, documents and hardware of the judiciary itself — with source attribution and citation verification on every answer.

Measurable results

An evaluation harness objectively measures quality and hallucination rate. We steer by numbers, not by feel.

See it yourself

The demo is the portal itself

Ask a real legal question and see how every claim is backed by ECLI sources. This is the same RAG blueprint as behind the other projects in this lab.