Read through complex agreements for the clause that matters, compare against precedent and prior drafts, and log every finding.
Review this master services agreement against our playbook and rank what matters.
These are exchanges the team published, replayed here. Nothing on this page calls a language model, and nothing claims to.
A prompt library, a node-by-node board, a financial model you can argue with, and the API as it is actually documented.
Each agent below is configured for Legal, compliance and internal audit work, and carries its own measured throughput, accuracy and latency.
Reviews an agreement against your own playbook, marks what departs from it, and drafts the redline you would have written.
Samples transactions against the control they are meant to satisfy, and writes the working paper with the evidence attached.
Every template is a chain of nodes with a trigger at one end and something the business actually needed at the other.
An agreement arrives, is classified, reviewed against the playbook, and every dated obligation it creates is written into the calendar of whoever owns it.
Contracts read against your playbook, obligations diarised, controls tested with reproducible samples and working papers that stand up.
Problem
Routine agreements queue behind the ones that matter.
After
The routine ones come back reviewed and ranked; counsel spends their attention on the three that need it.
Problem
Obligations are agreed, signed and then forgotten until they are breached.
After
Every dated obligation is extracted at signature and diarised to a named owner.
Problem
A sample that cannot be reproduced is a finding that can be argued away.
After
The selection seed and method are recorded in the working paper.
Positions are configured by the firm. The agent compares against them rather than against a notion of market standard.
Eleven deviations sorted by what they could cost, not by where they appear in the document.
Output is a first-pass review and is labelled as such. Nothing here is legal advice, and the interface says so where a reader will see it.
It does the reading. We still do the judging. That division is exactly right, and it is the reason the partners signed off.
A worked example, not a promise. Change the inputs on the full model and the arithmetic changes with them.
repetitive hours a year across 40 people at 8 hours each per week
hours automated at a 62% automation rate
labour value released a year, at $40 an hour fully loaded
Forty-six working weeks a year, before licence cost. Released hours are hours people spend on something else — whether that becomes cash depends on what you redeploy them to, and this figure does not assume you will.
One REST surface, documented request and response for each route, and a token you can revoke.
Routes
{
"data": [
{
"id": "agt_8fk2",
"name": "DataPulse",
"model": "nexus-dense-70b",
"status": "ready",
"quota": { "used": 4120311, "limit": 120000000 }
}
],
"has_more": false
}
Every tier states its own ceilings. Where a limit is not listed, there is not one.
For a team automating its first few processes.
Billed monthly, cancel at any time
For a department running automation as part of how it works.
Billed monthly, cancel at any time
For an organisation with regulators, auditors and a security review.
Billed monthly, cancel at any time
For deployments that cannot touch a public network at all.
Scoped to your deployment
For a team automating its first few processes.
20% below the monthly rate of $299
For a department running automation as part of how it works.
20% below the monthly rate of $1,290
For an organisation with regulators, auditors and a security review.
20% below the monthly rate of $4,900
For deployments that cannot touch a public network at all.
Scoped to your deployment
It does the reading and we do the judging. I would still like better handling of governing-law interactions, but the division of labour is right.
First-pass review down 71%
Verified customer, 7 months on the Enterprise plan.