AI and automation for law firms
The billable hour is the wrong place to lose an afternoon.
Intake, conflicts checks, document collection and file admin are absorbed by people who should be doing legal work. An Edgerton assessment measures how much of the week that takes, then proposes what can safely be automated with EdgeKeeper.
Built forPartners, practice managers and legal operations leads who suspect administration is crowding out billable and client-facing work.
01 / The outcome
What you get.
- A measured view of where repetitive work takes time
- Ranked opportunities with assumptions, estimated capacity value and costs made clear
- A report and full proposal you keep, whether or not you commission a build
- An assessment-fee refund if we find no clear ROI path
The scope
What's included.
- A paid Edgerton assessment over ten business days on the computers you choose, with your team’s knowledge and consent
- A report covering the work observed and the limits of the measurement
- A proposal with build scope, cost, timeline and estimated payback
- An optional, separately agreed EdgeKeeper build and ongoing support
02 / Delivery
How we do it.
- 01
Measure the work
We agree the assessment fee, participating computers and visibility level before installation. Your team knows what is measured and consents to it.
- 02
Review the proposal
We explain the findings, costs, dependencies and estimated payback. Recovered time is capacity, not a promise of cash savings. You decide whether the build makes sense.
- 03
Build and support
If you go ahead, we run our EdgeKeeper software on a dedicated Microsoft Azure server, connect the approved tools and build the agreed workflows. Your team works in Switchboard for answers, reports and dashboards from the systems we connect for you. A named lead supports your team under the service agreement.
Confidentiality
Is AI safe for confidential client files?
That depends on the controls around the AI, not on a promise about the AI itself. With EdgeKeeper, your firm decides which matter information the system can use. Each connection is scoped to the systems and folders you approve, and starts read-only.
A person approves any change, and anything sent outside the firm. Access is recorded for review. The AI model behind EdgeKeeper is our engine and may change over time; we document model use, retention and access for your review.
Whether a particular use fits your professional obligations is your firm's decision. We give you the documentation to make it. We do not certify compliance.
Most firms also need a written AI use policy: which tools staff may use, and what client information may go into them.
03 / In practice
What this can look like.
Illustrative workflows. Your assessment determines the scope.
Intake preparation
Organize enquiry details and prepare conflict-screening information for staff review. Your firm makes acceptance decisions.
Document preparation
Assemble draft documents from approved templates and source material. An attorney checks accuracy and authorizes use.
Matter reporting
Bring together matter status and billing information for a reviewer, subject to the access your firm permits.
What a legal assessment looks at.
These are possible workflows, not a prebuilt legal package or a promise that every connection is available. Your assessment checks the work, vendor access, permissions and expected value before we propose a build.
The promises we put in writing.
If we don't find ROI, you get the fee back.
Edgerton measures how your team's work really happens (with your team's knowledge and consent) and puts a dollar figure on what it finds. If there's no clear ROI path, the verdict is 'don't build', and the Assessment fee comes back. The report is yours to keep either way.
Production by a fixed date.
Set during the Build. If we miss it, additional weeks of build are on us.
You keep your data, whatever happens.
Your records, everything the brain learned about your business, the log: yours in the contract, with full export rights. The server and the software are ours; the knowledge is yours. Leaving is a documented handover, not a hostage negotiation.
Your rules decide what the AI sees.
Only what you approve goes in. Nothing you don't approve comes out. And every access is written down, so "what did it see?" always has an answer.
A named engagement lead.
Not a queue, not a rotation. You know their name, they know your business, and they pick up the phone.
Before you decide
Questions we get.
Can our team make its own AI agents?
Yes. Once EdgeKeeper is running, make as many read-only AI agents as you want in Switchboard, for any job. Describe the work you need help with. Agents read the systems we connect for you and can prepare reports and dashboards. Apps and automations that make changes are built with you, with a business case. A person approves writes and outbound actions.
Do we have to buy the build?
No. The assessment is a separate paid engagement. You keep the report and full proposal. If we find no clear ROI path, we refund the assessment fee.
Will this work with our existing software?
We confirm access, licensing, vendor restrictions and permissions during scoping. Your proposal identifies the connections we can support and any dependencies before you approve the work.
Who approves changes?
Connections start read-only. A person approves writes and outbound actions. Your team reviews drafts and retains responsibility for professional and operational decisions.
Who owns the data?
Your business data and knowledge remain yours, with full export rights and a documented handover. The EdgeKeeper software and the server we provide remain ours.
Related guides.
Your next step
Start with an Assessment.
We install Edgerton on the computers you choose, with your team's knowledge and consent. After ten business days, you get a report and a proposal to help you decide what to do next.