AI by industry

AI for legal teams

An eighty-page contract arrives for review. Before a lawyer reads a line, its structure has to be mapped, the clauses that depart from the template found, the cross-references, the definitions. An hour of preparation for an hour of useful reading. The task that costs is that hour — not the opinion, which stays with the lawyer, and must.

5 tasks documented below1 limit no opinion, no characterisation, no strategyLegal privilege closed perimeter, written into the quote2 to 6 weeks before the first system is open
Spot the clauses that depart from the template
Build the file
Track the monitoring

The tasks we remove first in this industry

The cost

What this industry pays when nothing moves.

Ranges, not promises. They come from tasks we meet in this industry and orders of magnitude we measure in the survey — yours may fall outside, in either direction.

Changing nothing
Preparing a contract before reading45 min to 2 h
Building a file (documents, chronology)2 to 6 hours
Monitoring actually read each weeka fraction
Internal ‘where is the matter’ requests10 to 20 per day
Non-billable time per lawyer1 h 30 to 3 h per day
Billable hours lost per lawyer per month15 to 30
The preparation system, opened
Preparing a contract before reading5 to 10 minutes of review
Building a file (documents, chronology)30 to 60 minutes, reviewed
Monitoring actually read each weekwhat affects your matters, flagged
Internal ‘where is the matter’ requests2 to 5 per day
Non-billable time per lawyer30 to 60 minutes per day
Billable hours lost per lawyer per month5 to 10
Five tasks

What we remove, and what we leave.

Each task is described with what the agent takes on and what stays with a person. If the second column is empty, we have not understood the industry.

01

Prepare the reading of a contract

What the agent does
It maps the structure, the definitions, the cross-references, and sets each clause against your template, flagging deviations — without saying whether they are acceptable.

What stays with a person
The reading itself, and the opinion. ‘This clause differs from the template’ is an observation ; ‘this clause is risky’ is an opinion, and it belongs to the lawyer.

02

Build a file

What the agent does
Documents, correspondence, chronology : it assembles the file in your format, every fact pointing to its document, and flags what is missing.

What stays with a person
The characterisation of the facts and the strategy. The file is ready ; what is done with it is not.

03

Track the monitoring

What the agent does
It reads the sources you designate and flags what affects your matters or your templates, with the exact extract and the reference.

What stays with a person
The interpretation and the update of templates. It alerts ; the lawyer decides.

04

Answer first-line internal requests

What the agent does
‘Where is the matter’, ‘which template for’, ‘have we dealt with’ : it answers from the file and the template base, citing.

What stays with a person
Any question whose answer is an opinion. It says ‘template X was used three times for this case’, not ‘use template X’.

05

Write up notes and attendance notes

What the agent does
From hearing, meeting or client notes, it produces a note in your format, with the points to action.

What stays with a person
The review, and what was said. The note is the lawyer’s, not the machine’s.

What we do not do

No legal opinion is produced by an agent. Ever.

It is one of the three founding limits of the agency, written on every quote. An agent spots, assembles, compares to a template and cites. It does not characterise, recommend or advise. The line between ‘this clause differs’ and ‘this clause is risky’ is the one in the diagram below.

A contract arrives for review — a diagram, not a screenshot
1Contract received, applicable template identifiedtrigger
2Structure, definitions, cross-references mappedreading
?Does the clause match the firm’s template?condition
if yes
4Clause marked as matching the template, reference citedobservation
otherwise
5Deviation flagged: template text and received text side by sideobservation
6The lawyer reads, characterises, decideshuman

In both branches, the agent produces an observation. The opinion appears nowhere in this diagram — deliberately.

The method, in one sentence

Ten systems, one survey, one system opened at a time — the one with the shortest payback. Read the full method, or go back to the AI agency page.

The tools

What we open it with, and why here.

The choice of tool comes last, and it is reversible. But in this industry, three constraints keep coming back and steer the choice before we even start.

A closed perimeter, covered by privilege
Files are covered by legal professional privilege. Before any agent, we decide where the documents live — on your premises, in most cases — and who has access. Nothing is used to train a model.
A readable template base
The agent is only worth what your templates are worth. The first job is often to gather them, date the versions and remove duplicates.
A model set to compare, never to characterise
It puts two texts side by side and cites. It does not say which is better. As soon as a question calls for an opinion, it hands over.
The objections

What we hear in this industry, before we start.

Is legal privilege compatible with an agent ?

With an agent installed inside your perimeter, yes : the documents do not leave it, access is named, and nothing is used to train anything. It is the first decision of the workshop. If it does not suit you, we stop there.

An agent that flags deviations — isn’t that already an opinion ?

No : a deviation is a fact. ‘Clause 12 received differs from clause 12 of the template’ can be checked in one click. Saying whether the deviation is acceptable is the opinion — and the agent never formulates it, technically as much as by rule.

Our templates are out of date. Is that a problem ?

It is the most frequent case, and it is the first job : gather, date, de-duplicate. An agent comparing against an outdated template flags deviations that are not — we know it, we start there.

And for an in-house legal team ?

The tasks are the same, plus internal requests : ‘can we sign this’, ‘which template for’. The agent answers ‘this template served three times for this case’, never ‘sign’.

Where this industry concentrates

The areas where we are called most for this.

Related industries

The same tasks, in neighbouring industries : AI for banking, AI for real estate, AI for insurance.

First call — fifteen minutes

We will tell you which system to open first.

Describe the task that costs you the most. We will tell you what is feasible, how long it takes and what it costs. If the answer is no, you will leave with the two reasons why.