What I build

Software for legal

Smart client intake

Intake forms that adapt to the matter type, collect documents and create the matter automatically.

Matter and deadline tracking

Matters, tasks and court dates in one place, with reminders nobody can miss.

Document automation

Engagement letters and standard documents generated from intake data, ready for review.

Client portal

Clients upload documents, sign and see status without emailing for updates.

Internal knowledge search

Your precedents and templates searchable in plain English, with sources.

Firm reporting

Pipeline, workload and billing in one dashboard.

AI, right now

Where AI genuinely helps

Small and mid-size firms spend hours on work that needs no legal judgement: first replies to enquiries, deadline reminders, intake forms and status updates. Legal technology guides for 2026 point to automating exactly those jobs first, and to AI for document review, with lawyers in control.

I haven’t built for a law firm yet, so I won’t pretend otherwise. What I bring is the same building blocks I’ve shipped for real clients, shown below.

  • Document review with sources

    AI extracts clauses, dates and parties from contracts and documents, each linked to its page, for a lawyer to confirm.

  • First reply to every enquiry

    New enquiries acknowledged and qualified instantly, with conflict-check details collected.

  • Routine status updates

    Clients kept informed automatically as matters move, without fee-earner time.

  • Drafting from your precedents

    First drafts based on your own templates, reviewed and owned by a lawyer.

Similar work

Data, security and access

  • AI never gives legal advice or makes legal decisions; lawyers review everything it produces.
  • Client documents stored privately, with access by role and matter.
  • Every AI extraction links back to the source document and page.
  • Audit logs on access to client data.

How a project runs

  1. Call

    A 30-minute call about what you need, who it is for, and what success looks like.

  2. Scope

    A written scope: features, architecture, timeline, price range and risks.

  3. Build

    Working increments you can click through, not a big reveal at the end.

  4. Ship

    Live on your domain and hosting, with a handover so you know how it runs.

More in how I work, or see rag and ai chatbots.

Questions

Common questions

Is AI safe to use with client documents?

It can be, with the right setup: providers that don't train on your data, access by role, sources on every output and a lawyer reviewing everything. That's how I built PayRight's contract analysis.

Why custom instead of Clio or MyCase?

If they fit, use them. Custom tools make sense for a practice area with its own workflow, for connecting systems, or for AI built on your own precedents.

Can it work with our practice management system?

Often, through its API. That's confirmed in the scope.

How much does it cost?

A focused first version is a fixed-price project, scoped and priced after a 30-minute call (MVPs start from $3,000). Ongoing work can run on a monthly retainer.

Want intake and documents to take less of your day?

A 30-minute call is enough to tell whether it fits, what the first version should include, and how long it takes.

Book a 30-minute call