Departments/Legal
Legal work that keeps pace with the business.
AI agents handle intake, first-pass contract review against your playbook, and the tracking of obligations and renewals. Your lawyers spend their time on the matters that need judgement.
How the agents work in legal.
01Reads
Requests, contracts and the documents attached to them.
02Checks
Each clause against your playbook, and each request against your intake rules.
03Acts
Drafts from your templates, marks up the differences and files the signed version.
04Asks
Sends non-standard terms to a lawyer, with the playbook position alongside.
Where the agents work.
Each one starts as a single process with a measure agreed before anything is built.
01Legal intake
- Today
- Requests arrive by email and chat with half the details missing.
- With agents
- Each request is captured complete, sorted by type and sent to the right person.
- Measured in
- Time to first response
02Standard agreements
- Today
- Lawyers review routine agreements that rarely change.
- With agents
- Standard agreements are drafted and checked against the playbook. Only the differences are reviewed.
- Measured in
- Agreements needing a lawyer
03Contract review
- Today
- Every third-party contract is read end to end before anyone knows where the issues are.
- With agents
- The contract arrives marked up against your positions, with the issues listed first.
- Measured in
- Review time per contract
04Obligations and renewals
- Today
- Renewal dates and obligations sit inside signed PDFs.
- With agents
- Key dates and obligations are extracted, tracked and raised with the owner ahead of time.
- Measured in
- Missed renewals
05Contract search
- Today
- Finding which contracts contain a clause means opening them one by one.
- With agents
- Anyone with access can ask a question across the contract set and get the answer with its source.
- Measured in
- Time to answer
06Policy questions
- Today
- The business asks legal the same questions again and again.
- With agents
- Routine questions are answered from approved guidance, with a route to a lawyer.
- Measured in
- Questions reaching legal
Works inside
- Contract repository
- Document management
- E-signature
- Matter intake
- CRM
What stays with your people.
The agents prepare, check and record. The calls that carry judgement or risk stay with a named person on your team.
- 01Legal advice and judgement on risk.
- 02Negotiation and anything non-standard.
- 03Final approval on every agreement.
Guides for this team.
- Guide
Guide
Rule or agent
A one-line test for each step
AI agents or workflow automation: which does your process need?
What separates workflow automation from an AI agent, a one-line test for each step of a process, and why most useful first systems use both.
GuideHow do you keep AI secure and compliant without a security team?
For companies with a small IT team: control what AI can see, who can use it and what gets logged, and answer customer security questionnaires with confidence.
Questions
Questions we hear first.
Is the output legal advice?
No. The system prepares work for your lawyers against the positions they've set. A lawyer approves anything that leaves the team.
How is privileged and confidential material handled?
It stays in your document systems. Before we build, you sign off exactly what the system can read, where it's processed and which model provider, if any, receives it.
Can it work from our own playbook and templates?
Yes, that's the starting point. We build the checks from your templates, fallback positions and approval rules, and test them on your past agreements.
Why not just use ChatGPT or Copilot?
They're good tools for one person doing one task. The systems we build run a whole process: they connect to your systems of record, follow your rules, hand exceptions to a named person and log every step. The two work well side by side.
Why not build this ourselves?
You can, and some teams should. What we bring is a team that does this every day, a tested way of working, and people who stay to run it. Everything is set up in your accounts, so your team can take it over when it's ready.
Make your business AI-native.
Start with a short call about where your team's hours go and what you want to change.