Your precedent bank, searchable by argument.

• 01

  Precedent and clause retrieval

  Find how you've drafted a limitation of liability across matters, ranked by similarity of facts rather than keyword overlap.

• 02

  Matter document Q&A

  Ask a question across a matter's document set and get the passages that answer it, with the citation a partner can check in thirty seconds.

• 03

  Obligation extraction

  Renewal dates, notice periods and reporting duties extracted from executed contracts into a register that can raise a reminder.

• 01

  Every claim carries its source

  Answers return the clause and the document, and refuse when retrieval is weak. An unsourced legal answer is worse than no answer, and the eval suite scores it as a failure.

• 02

  Privilege and confidentiality are architectural

  Matter-level access control in retrieval, deployment inside your tenancy, and no training on your documents — stated in the contract, enforced in the build.

• 03

  The lawyer signs, always

  The system drafts, redlines and flags. Advice and filing stay with an admitted practitioner, and no pathway lets generated text reach a counterparty unreviewed.

1. 1

   Data inventory

   What docs / databases / APIs / feeds matter? What's PII vs public? What changes daily vs quarterly? We map it before writing code.

2. 2

   Retrieval architecture

   Hybrid (BM25 + vector) retrieval, chunking strategy, reranking, citations. Tuned for your domain not a generic benchmark.

3. 3

   Eval suite

   Real-world question set with golden answers. Faithfulness, context precision, latency. So you know when changes ship a regression.

4. 4

   Guardrails

   Prompt-injection defense, PII scrubbing, refusal patterns, output schemas. Especially critical for customer-facing deployments.

5. 5

   Production + iterate

   Cost-effective inference (caching, fallback models), monitoring, weekly eval reports. Fine-tune when the data justifies it.

• iManage & NetDocuments
• SharePoint
• DocuSign & Adobe Sign
• Contract lifecycle management tools
• Microsoft 365 & Word add-ins
• Postgres with matter-level access control

FAQ

RAG for legal documents and precedent: your questions.

• What stops it inventing a case or a clause?

  It never generates a citation — it returns retrieved passages and links to them. If retrieval finds nothing, it says so. The failure mode that produced the well-known sanctions cases is designed out rather than prompted against.

• Can it search across matters when privilege differs?

  Only where the user's DMS permissions already allow it. Retrieval inherits your existing access model rather than introducing a second one that will drift out of sync.

• Should I use RAG or fine-tuning?

  RAG for facts that change. Fine-tuning for style, format, or domain reasoning. Most production systems use both — and we'll tell you which mix is right after a 1-week discovery.

• Can I use my own LLM (open-weights)?

  Yes. We work with Llama, Mistral, Qwen, and similar — useful for data residency, cost predictability, and air-gapped environments.

• AI agents for contract reviewAgents that triage incoming contracts, redline against your standard positions, and route to the right reviewer with the deviations already summarised.Read
• AI governance for legal teamsAcceptable-use policy, confidentiality controls, and an approval process for AI tools that lawyers are already using with or without permission.Read

• RAG for banking and financial servicesRetrieval over circulars, product terms and internal procedure — returning the clause, the revision date, and a link to the page it came from.Read
• RAG for healthcare and clinical documentsRetrieval over clinical guidelines, payer policy and internal SOPs — with the citation, the version, and an explicit refusal when the library doesn't cover the question.Read
• AI product search and catalogue RAGSemantic search and grounded product Q&A over your catalogue, reviews and size guides — with stock and price read live rather than remembered.Read