We won the Open Agentic AI Innovation Award at the first AAIF Technical Excellence Awards.We won the Open Agentic AI Innovation Award Read why

AI contract analysis against your own playbook

Every clause checked before your lawyer reads it

An agent reads each incoming contract, compares its clauses with your playbook and gives your legal team the deviations with their source lines.

Book a free consultation How we build agents
contract-review

  1. Procurement leadYour team

    A supplier sent back our services agreement with edits. Can the review agent check it before Friday?

  2. Review agentAgent

    1. docs.fetch_contract redlined agreement and annexes
    2. clauses.extract liability, termination, payment
    3. playbook.compare each clause against your positions

    The liability cap was removed and the payment terms changed. Every other clause matches your playbook.

    Needs a personLiability cap removedOutside your fallback positions
    Decided by Legal counsel

  3. Review agentAgent

    1. contracts.log_review deviations, sources, decision
    2. calendar.add_dates renewal and notice dates

    Review logged with each deviation and the clause it came from. Renewal and notice dates are in the calendar.

Example data. An agent at work in a team channel, with a person approving the step you choose.
Mixam: conversion to a final sale from about 20% to about 40%
Where agents help

Contracts queue up for a lawyer to read line by line.

Agents read and compare the clauses, and your lawyers decide what to accept.

  1. 01

    Where it stallsLawyers spend hours on clauses that match the standard.

    What we do An agent compares each clause with your playbook, so review starts from the deviations.

  2. 02

    Where it stallsRedlines hide changes inside long documents.

    What we do The agent compares versions clause by clause and points to the line behind every change.

  3. 03

    Where it stallsObligations and renewal dates get lost after signing.

    What we do Key dates and obligations go into your contract register, each linked to its clause.

What we build

What we build for contract analysis

Whatever comes in, every project is built from the same parts below, set up for your files and your systems.

Contracts we read

  • NDAs
  • Master service agreements
  • Supplier contracts
  • Customer contracts
  • Leases
  • Employment contracts
  • Licences
  • Amendments and renewals

How we build it

  • Clause extraction with sources

    Parties, terms, liability and termination clauses read from each contract, each linked to its line.

  • Playbook checks your lawyers maintain

    Your standard positions and fallbacks written as rules, with every clause checked against them.

  • Contract register connections

    Key dates, obligations and signed versions written to your contract register and calendar.

  • Escalation rules your legal team agrees

    Which deviations stop for a lawyer, agreed with your legal team and enforced in the system.

Not seeing your case? Bring the contract type your team reviews most and we start from that.

Tell us about your workflow
How we build agents

Agents that work as part of your team

They work in the tools your team already uses, take on whole tasks and stop for a person where you decide.

  1. Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
  2. Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
  3. Approvals log: each action that waited for a person, with who asked, who decided and when.
Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
Approvals log: each action that waited for a person, with who asked, who decided and when.

Screens from the workspace our agents run in, with example data.

Where it runs

Teams and industries that use it

Each page shows where agents fit in that team or industry.

Engineering in the open

We help build what agentic AI runs on

Open standards, open-source tooling and published research, all public, so you can check our engineering before you hire us.

Shaping agentic AI

Agentic AI Foundation

Vstorm was the first agentic AI engineering company to join the Agentic AI Foundation and received its 2026 Open Agentic AI Innovation Award.

Read the announcement

Open source

We build open-source agent tooling that other engineering teams install

10M+ PyPI downloads
4,000+ GitHub stars
33 public repositories

Framework contributors

When the framework breaks, we fix it at the source

We maintain our own open-source agent framework and contribute fixes to the frameworks our agents run on, through official partnerships with their teams. Breaking changes reach us before they reach your codebase.

Research

Our engineers and PhDs publish peer-reviewed research

Peer-reviewed papers on agent architectures, evaluation and AI security, and an open benchmark anyone can rerun against our results.

Track record

Frontier AI teams now build on what we shipped first

Our client agents were in production before most of today's agent frameworks had a stable release. You get a team that already knows what breaks between a promising demo and a system people rely on every day.

Case studies
All case studies
Engagement models

Ways to start

Each path starts with a free call with a founder or senior AI engineer. A build goes ahead only after its Proof of Value meets the agreed threshold.

Start with one workflow

We map one workflow with your experts and agree a success threshold before any build.

Best whenYou want the success test agreed before you commit to a build.

Book a free consultation
  1. Process redesign and build Best whenYou want one team accountable for the outcome.
FAQ

AI contract analysis, answered

What is AI contract analysis? +
AI contract analysis uses an agent to read a contract, extract its key clauses and compare each one with your playbook. The agent lists every deviation with the line it came from, pulls out renewal dates and obligations, and passes the list to your legal team. Your lawyers decide what to accept, push back on or escalate, and the agent prepares that review.
Which contracts suit AI contract review first? +
High-volume agreements with a clear standard, such as NDAs, supplier terms and customer order forms. Your team already knows the acceptable positions there, so they can be written down as a playbook and tested. Measure the agent on contracts your lawyers have already reviewed, then move to longer agreements with more negotiated clauses.
Have you built AI contract analysis before? +
We have no published case on contract analysis yet. The closest builds read long documents against fixed rules. Real estate due diligence was cut from weeks to minutes. For a US health insurer, claim processing was cut from 3 hours to 8 minutes, with a specialist still deciding. Our guideline-executing agent scored 98% on an open 50-scenario clinical benchmark, against 42% for a raw LLM.
How do you make sure the agent does not miss a clause? +
Every clause the agent reads is linked to its line in the document, and code checks that each section of the contract was covered. Clauses the agent cannot match to your playbook are listed for a lawyer to read. The agent is tested on contracts your team has already reviewed, and each correction goes back into that test set.
How do you know it works before the full build? +
We agree a success threshold with your team before the build and test the agent on your own cases in a Proof of Value. It measures accuracy and running costs, and the build goes ahead only when the threshold is met. Corrections from your team go back into the test set, so every later version is checked against them.
Who owns the system, and which models does it run on? +
You own the code, prompts, evaluation sets and rules by contract. The agents run in your environment on hosted or open-weight models. The model sits behind an interface in code, so you can change it when accuracy, speed or your hosting rules change, without rebuilding the agent.
Start with one workflow

Test one workflow on your own data

A Proof of Value shows accuracy and running costs before the full build.

Book a free consultationRead case studies
From the blog

Reading on document review with agents

All articles
Engineering

When clean text is not enough: structured extraction for RAG

When Clean Text Is Not Enough: Structured Extraction for RAG enables richer retrieval and accuracy—explore smarter solutions.
Engineering

Agentic RAG: Architecture, Knowledge, Access Control

How agentic RAG changes architecture, knowledge and access control: corrective vs self-reflective designs, what they cost, and where permission checks belong.
Agentic AI

Human in the loop for AI agents: when the agent needs permission to change the plan

Human in the loop for AI agents: who approves a change of plan, what evidence they need, how to stop approval fatigue and keep bookings matched to approvals.