Global law firm
≈ $3B+ revenue · Thousands of lawyers · dozens of offices
Walled-matter research assistant
Document search and drafting inside the firm's own tenancy: every answer cited to its source, every matter isolated by role, and nothing ever sent to a third-party model.
- Organization
- Global law firm
- Constraint
- Client matters must be walled from each other and from outside models
- Runs on
- The firm's own cloud tenancy
- Scope
- Research and drafting inside the wall
Where they started.
The firm benchmarks every AI tool on the market and has the productivity numbers to prove the category works. What it cannot do is send client documents to a vendor's model, or let a lawyer on one matter retrieve documents from another. The frontier agents are built on both.
What was built.
- FlatClaw deployed inside the firm's tenancy with role-based access mapped to matter teams.
- Retrieval scoped before the model sees a document: a lawyer's agent can only search the matters that lawyer is on.
- Every answer cited to its source document, so a draft can be checked rather than trusted.
- The same governed agent for research, drafting and summarization, with the firm's own style and precedents in its knowledge base.
What changed.
- The productivity of a frontier agent with the data posture the firm's clients require.
- Matter isolation enforced by the system, not by policy reminders.
- Answers that carry their citations into the work product.
- A platform the firm owns and can extend for practice groups.
Privilege and confidentiality are not features a vendor can promise on a firm's behalf. Running the model inside the tenancy keeps the obligation where it belongs.
The firm's own cloud tenancy
Components involved.
More like this.
Multi-brand industrial manufacturer
≈ $200M revenue across five brands (approx.) · 5 brands · 4 ERPs · 1 CRM
- Use Case:
- Consolidation, forecast and pricing intelligence across four ERPs
- Results:
- One governed lakehouse behind an AI agent: audit-grade consolidated financials that trace to the source transaction, forecast and pipeline by business unit, large-job margin watch, and plain-English inquiry over all of it, inside the company's own Azure tenant.
Healthcare receivables agency
≈ $10M revenue (approx.) · ~60 employees · national client base
- Use Case:
- Placement-file intake automation
- Results:
- Placement files arriving in any layout are normalized into the agency's existing upload format, with a human approval queue before anything reaches the system of record. A one-and-a-half-person manual job becomes a review step.
Healthcare receivables agency
≈ $10M revenue (approx.) · ~60 employees · regulated healthcare receivables
- Use Case:
- Protected-health-information send gate
- Results:
- Every outbound file that carries protected health information is checked against the placement it belongs to and held for human approval, with an audit trail of who released what, and when.
Have one like it?
Every spotlight started as a conversation about a process nobody liked doing, under a data-locality constraint.