Legal Research AI,
for EU and French Law.
Memo, brief and pleading templates. For legal questions, the Sovereign Legal AI agent can pull EUR-Lex and Légifrance search results into the prompt; check every citation yourself. Outputs are not legal advice.
Available in chat from Plus $20; Pro adds DeepSeek-V3.2-TEE reasoning.
Jurisprudence corpus
Primary sources, refreshed regularly.
The agent is grounded in EU and French primary sources only. No mid-tier blogs, no unverified summaries. Citation extraction runs on EUR-Lex, Légifrance, and curated CJEU and Conseil d'État decisions.
- · TFEU + TEU consolidated
- · Regulations (current)
- · Directives (transposed FR)
- · Charter of Fundamental Rights
- · CJEU decisions
- · General Court rulings
- · Advocate General opinions
- · Pending references for preliminary ruling
- · Civil
- · Commerce
- · Travail
- · Consommation
- · Construction
- · Pénal
- · CGCT
- · Cour de Cassation
- · Conseil d'État
- · Cours d'Appel selected
- · Conseil Constitutionnel
- · CNIL délibérations
- · AMF doctrine
- · Autorité de la concurrence
- · ARCEP / ARCOM
- · CCBE guidance
- · CNB position papers
- · EDPB guidelines
- · EU Commission communications
Hallucination guard
Citations resolved before they reach you.
Every output goes through a deterministic citation-check pass. The agent enumerates all cited references, court decisions, code articles, regulations, AG opinions, and resolves each one against the primary-source corpus. References that cannot be matched are stripped automatically. The remaining citations are guaranteed to point to a real, verifiable source.
Step 1, Enumerate
Extract every citation pattern in the draft response.
Step 2, Resolve
Match each citation against Légifrance, EUR-Lex, court bulletins.
Step 3, Strip
Remove unmatched references before the response is returned.
Step 4, Stamp
Each retained citation is labelled with publication date and source URL.
Output templates
Memo, brief, pleading, client letter.
Legal memo (IRAC)
Question presented · short answer · issue / rule / analysis / conclusion. Check every citation against the official text.
Pleading skeleton
Assignation or conclusions structure with factual background, legal basis (codes + jurisprudence), prayer for relief.
Client letter
Plain-French explanation with legal basis broken out separately. Cites stripped from main body, listed in annex.
Comparative analysis
EN vs FR vs DE on a focused question (e.g. non-compete enforceability, indemnity caps, IP assignment).
Comparison
VoltageGPU vs Lexis+ AI vs Doctrine.
Pricing
Pro
$1,199
Up to 10 seats · OpenAI-compatible API
Enterprise
$3,499
R1-TEE reasoning · SSO · attestation receipts
FAQ
Frequently asked questions.
Has there been a real legal sanction for AI hallucination?
Yes, Mata v. Avianca (S.D.N.Y., 2023) is the textbook case. Attorneys filed a brief that cited six fictitious decisions generated by ChatGPT. The court imposed a $5,000 penalty and ordered letters to the judges falsely named as authors. Similar cases have followed in the United States and elsewhere. No tool removes this risk: check every citation yourself before you rely on it.
Can I trust the agent on niche French law areas?
Treat it as a starting point. The model answers from its training plus the EUR-Lex results and Légifrance link it is given. It is weaker where law changes fast or varies locally, such as recent tax positions, local administrative law and family law. Always verify outputs against a canonical source before relying on them.
Does the agent train on my queries?
No. We do not train models on your queries, and we do not store your prompts; chats stay in your browser. The model weights are frozen and shared across all customers. For the EUR-Lex lookup, a shortened search query, with emails, phone numbers, IBANs and French ID numbers stripped, is sent from our servers to EUR-Lex. Matters (Beta) at /workspaces can hold your files as notes, but the assistant does not read them yet.
Can it watch Légifrance and EUR-Lex for changes affecting our matters?
No. The regulatory-change monitor is disabled. Scheduled tasks at /scheduled can run a custom prompt on a cron and email the result, but they check no live source.
How current are the sources?
There is no stored corpus to go stale: EUR-Lex is queried at question time, and the Légifrance link opens a live search. The model's own knowledge stops at its training cutoff, so check the date and current version of every text it cites.
Verifiable citations or none at all.
Try the Legal Research agent on a Pro plan. Hallucination guard, primary-source corpus, EU-controlled.