Skip to content

Industries · Legal-tech & Law Firms

AI for legal teams, built for confidentiality.

Legal work runs on documents, precedent and confidentiality, which is exactly where generic chatbots fail. I build legal AI that retrieves the right passage with a citation, protects personal data before anything is indexed, and respects who is allowed to see what. One of these systems indexes more than 50,000 French-language court decisions in production.

Book a free discovery call See the work
Where AI pays off

What I build for teams like yours.

  • 01

    Case-law and precedent search

    Semantic and keyword search across decisions, with metadata filters and appeal chains.

  • 02

    Cited legal Q&A

    Answers grounded in your corpus, every claim linked to its source paragraph.

  • 03

    Anonymization for publication

    Names, addresses and identifiers masked consistently, with stricter rules for minors.

  • 04

    Drafting from precedent

    First drafts assembled from retrieved precedent, cutting drafting time.

What makes it hard

The constraints are the project.

The model is rarely the problem. These are the requirements that decide whether a system ships, and they are designed in from the first week.

  • Confidentiality

    NDA before details, least-privilege access and deployment in your environment.

  • Accuracy you can verify

    Citations on every answer and an evaluation set built with your lawyers.

  • Personal data

    PII detected and anonymized in the pipeline, never left to a prompt.

  • Multi-jurisdiction rules

    Jurisdiction-aware processing, including OHADA conventions.

Proof

Relevant case studies.

legal-search · data-greffe-justice
Hybrid · RBAC
résiliation abusive d’un bail commercial, OHADA

50K+ décisions· < 2 s· BM25 + vecteurs· réponses citées

  • Cour d’appel · Commercial0.94

    …la juridiction relève que [PARTIE A] a procédé à la résiliation du bailsans préavis, en méconnaissance de l’Acte uniforme OHADArelatif au droit commercial général…

    [1] Arrêt n° ••• · chaîne d’appel ↗

  • Tribunal de commerce · Bail0.86

    …[PARTIE B], preneur, sollicite des dommages-intérêts pour rupture abusive…

rôle : juristePII masquées3 index
Illustrative interface · client data never shown
01Data Greffe JusticeLive in production

Enterprise Legal Intelligence Platform

A production RAG platform that turns 50,000+ French-language court decisions into a searchable, privacy-safe knowledge base, with triple-search retrieval, role-based access, compliance-grade PII anonymization and AI-assisted drafting.

Legal documents indexed
50K+
PII detection accuracy
98%
Query response time
<2s
Read case study
anonymizer · triple-search
98% detection

Original

Le mineur Koffi A., domicilié à Cocody, rue des Jardins, représenté par sa mère Awa D.… K. Adjouaconfirme…

Anonymized

Le mineur [MINEUR 1], domicilié à [ADRESSE], représenté par sa mère [PARTIE B]… [MINEUR 1]confirme…

  • Pass 1Contextual entities (Claude)
  • Pass 2Patterns & identifiers
  • Pass 3Variants & later mentions

4 entities · 1 variant spelling caughtminor-protection rules applied

Illustrative interface · client data never shown
02Legal Anonymization Engine

Multi-Jurisdiction PII Anonymization Engine for Court Decisions

A compliance-grade anonymization engine for legal case decisions. A triple-search architecture finds personal data that single-pass detection misses, reaching 98% detection accuracy with dedicated safeguards for minors and vulnerable parties.

PII detection accuracy
98%
Independent search passes
3
Decisions anonymized before release
100%
Read case study
Enterprise Knowledge Management5 stages
  1. 01PDF
  2. 02Image
  3. 03Clean
  4. 04OCR
  5. 05Structure

Stage 1, PDF: Scanned document intake. Stage 2, Image: Page-to-image conversion. Stage 3, Clean: Preprocessing for OCR accuracy. Stage 4, OCR: Text extraction. Stage 5, Structure: Vector-ready JSON.

03Document Intelligence Pipeline

OCR-to-RAG Document Ingestion Pipeline

A five-stage pipeline that converts scanned PDFs into clean, structured, vector-ready JSON, opening up archives that search and RAG could not read before.

Processing stages
5
Unstructured to structured
Scan → JSON
Vector-store output
RAG-ready
Read case study

Services for Legal-tech & Law Firms

Other industries

AI project estimator

Get a tailored project plan in 60 seconds.

Five questions about what you’re building. Instantly see the recommended architecture, delivery phases and a realistic timeline, then email it to yourself.

  • Architecture
  • Phased plan
  • Timeline

Step 1 of 5 · What are you building?

Start the estimator
FAQ

Legal-tech & Law Firms: common questions.

Can legal AI work with French-language or multilingual documents?

Yes. The flagship legal platform runs on French-language court decisions, and modern retrieval and LLMs handle most major languages when the pipeline is tuned and evaluated for them.

How do you stop the AI from inventing case law?

Answers are generated only from retrieved documents, each claim carries a citation, and the system says so when the evidence isn't there. An evaluation set built with your lawyers catches regressions before release.

Can client data stay inside our firm's infrastructure?

Yes. The system can run in your cloud account or VPC, with role-based access, and personal data is anonymized before indexing.

Available for new engagements

Have an AI initiative in mind? Let’s scope it in 30 minutes.

Free discovery call. You'll leave with a clear view of the architecture, risks and next steps, whether or not we work together. I reply within 24 hours.

Book a free discovery callSend project details

Not ready to talk yet? Get an instant project plan.