LeanLaw
Agent-ready · MCP private beta

Your firm’s AI can be a user, too.

Give your firm’s own AI a path to LeanLaw’s billing and trust accounting rails. An agent can use the public API today; LeanLaw’s MCP layer is in private beta.

Tell us what you’re building Read the API docs
Public API
Available today
MCP layer
Private beta

Private beta on purpose: billing and trust accounting have unforgiving failure modes, so the guardrails come before the capability.

What becomes possible

Start where systems meet.

The first opportunities are not isolated tasks inside LeanLaw. They connect the firm’s existing systems to the operation that turns work into collected revenue. These prompts show the shape of private-beta scenarios; they are not committed product features.

01 Cross-system · Onboarding

From signed engagement letter to live matter.

Sample prompt

“Here’s the signed engagement letter. Prepare the client, matter, and fee structure in LeanLaw. Show me what you’re about to create before you save.”

A firm’s agent could read the letter in its existing system, prepare the client, matter, rates, and retainer request for LeanLaw, then pause for confirmation.

Revenue move

Start billing from the day of signing and keep invoice terms aligned with the agreement.

02 Cross-system · Client picture

See the money and the work before the meeting.

Sample prompt

“What’s happening with Henderson? Bring together the LeanLaw picture with the latest email and Teams threads.”

A firm’s agent could combine LeanLaw balances, unbilled work, and recent activity with the conversation happening in email and Teams, then prepare one brief.

Revenue move

Bring the money conversation into the meeting and spot scope creep earlier.

03 Cross-system · Time capture

Reconstruct the day from where work happened.

Sample prompt

“Draft today’s time from my calendar, sent email, and documents edited. Add UTBMS codes and let me review before posting.”

A firm’s agent could assemble a draft from calendar, email, and document activity, map it to matters, and keep a person in the review step before anything posts.

Revenue move

Recover time that is often undercounted when reconstructed from memory.

“Not one tool that tries to do everything, but one connected experience across the systems a firm already uses — and now that includes the firm’s own AI.”

Fred Willerup · CTO, LeanLaw
The next four workflow shapes

Quieter work. Real revenue leaks.

Fred’s remaining scenarios focus on review, follow-up, insight, and firm-specific rules. They are illustrative possibilities—not commitments about which tools or actions are in the private beta.

04 Pre-bill review

Illustrative workflow

A possible workflow would review pre-bill data for vague narratives, block billing, budget overruns, duplicates, or incorrect rates—and suggest rewrites for a person to review.

Revenue move

Help prevent write-downs and disputes before an invoice leaves the firm.

05 Collections and trust follow-up

Illustrative workflow

A possible workflow would rank aged receivables, surface relevant trust or evergreen-retainer context, and draft follow-ups for review.

Revenue move

Make consistent follow-up far less labor-intensive.

06 Ask the firm a question

Illustrative workflow

A possible workflow would answer plain-language questions about profitability, billing velocity, or realization using the firm’s LeanLaw data.

Revenue move

See revenue leaks without waiting for a custom report.

07 Long-tail billing rules

Illustrative workflow

A firm could describe rules such as interest on aged invoices, sliding rates, or negotiated discounts once, then run them on a schedule through the API.

Revenue move

Apply firm-specific terms more consistently.

One MCP server · Two surfaces

The working surface changes. The LeanLaw connection does not.

A firm could put Claude or Copilot to work on LeanLaw data. Which surface fits depends on where the rest of the workflow lives.

Claude

A natural surface for multi-step scenarios such as onboarding, a client picture, pre-bill review, firm insight, or long-tail rules.

Microsoft Copilot

A natural surface when time capture or collections work begins in Outlook and Teams.

These are illustrative private-beta scenarios based on Fred’s use-case set, not a list of committed product features.

MCP, in plain language

A standard interface designed with an AI user in mind.

“Systems talk to each other through APIs. An MCP is essentially a specialized kind of API that an AI agent has an easier time working with. We have an API an agent can already use, and our MCP layer is in private beta today.”

Fred Willerup · CTO, LeanLaw

An open standard, not a proprietary bet.

MCP was donated to the Linux Foundation’s Agentic AI Foundation at the end of 2025. The foundation was co-founded by Anthropic, Block, and OpenAI. Read the Linux Foundation announcement.

Agent Experience (AX)

Design the product for an agent acting on a user’s behalf.

Agent Experience — AX — is the emerging product and API-design discipline for making a system legible and reliably usable to an AI agent. It is not the separate use of AX to describe workforce readiness.

Gartner tracks Agent Experience in its 2026 Hype Cycle for Agentic AI. Agent-ready is LeanLaw’s plain-language phrasing for what that discipline produces.

Public API
An agent can use it today
MCP layer
Private beta
Firm’s AI
Run by the firm, not LeanLaw
Explore the public API
Private beta on purpose

Guardrails before capability.

“We’re moving deliberately here, and it’s in beta on purpose. This is a system that touches billing and trust accounting, where the failure modes are unforgiving — so the guardrails come before the capability. I’d rather work closely with a small number of firms and get it right than ship it wide and find out.”

Fred Willerup · CTO, LeanLaw

Two distinct modes

Embedded AI and agent-ready solve different problems.

One answers questions within LeanLaw. The other makes LeanLaw usable by the firm’s own AI across a connected stack.

Embedded AI Live · Early

ClerkAI

Ask plain-language questions about your firm’s LeanLaw data—especially complex questions that are difficult to pull from standard report filters.

Where it works
Inside LeanLaw
What it does
Answers questions
Actions
None · Read-only
Agent-ready MCP private beta

Public API + MCP layer

Give the firm’s own AI a path to pull information from one system, work with LeanLaw, and continue across the stack. LeanLaw does not run that AI.

Who runs it
The firm
Public API
Available today
MCP layer
Private beta
Frequently asked questions

What’s live, what’s early, and what’s in beta.

Is LeanLaw’s MCP server available?

It’s in private beta. MCP is an open standard governed by the Linux Foundation’s Agentic AI Foundation.

Does LeanLaw use AI?

Yes, in two ways. Embedded AI features inside the product — like ClerkAI, which answers plain-language questions about your firm’s data — and agent-readiness: making LeanLaw work with a firm’s own AI agents through our API and an MCP layer, currently in private beta.

What is Agent Experience (AX)?

An emerging discipline — tracked by Gartner alongside more established fields like developer experience — for designing products so AI agents acting on a user’s behalf can reliably use them. LeanLaw’s MCP work is our implementation of it.

What is ClerkAI?

LeanLaw’s natural-language assistant for asking questions about your firm’s data, especially complex questions that are hard to pull from standard reports. It’s early and read-only today.

Does LeanLaw train AI on client data?

No. LeanLaw uses third-party AI providers that don’t train on customer data without permission, and we don’t grant it. We don’t sell client data.

MCP private beta

If your firm is building agent workflows, we’d like to hear what they need to do.

We’re taking a small number of firms into the private beta. The firms in it will help shape how their own AI works with LeanLaw’s billing and accounting data.

Tell us what you’re building Read the API docs

This is a design-partner conversation, not a general-availability signup.