The playbook is a PDF
Positions are written down, but applying them means reading the contract and the playbook side by side. Under time pressure, nobody does.
Legal playbook software for contract teams
Legal playbook software that turns your review rules into decisions — on every contract, every version.
Treasure Contracts stores your criteria, targets and no-gos in a playbook and applies it with AI, with a traffic light per criterion.
Your playbook stops being a PDF nobody opens. It becomes the standard every contract is reviewed against, tested before go-live and documented in the audit trail.
ISO 27001 · Hosted in Frankfurt · GDPR · 4-week right of withdrawal
In short
What is legal playbook software?
Legal playbook software stores a legal team's contract positions — acceptable terms, fallback positions and no-gos — and applies them to incoming contracts. In Treasure Contracts, a playbook combines criteria, targets, no-gos, your party perspective and reference documents. AI checks each contract against it, rates every criterion as compliant, moderate or critical and suggests compliant wording for each finding.
Key facts
- Playbooks with criteria, targets, no-gos, party perspective, reference documents and custom contract types
- Golden-set tests with synthetic documents measure playbook quality before go-live
- Every playbook change and review result is recorded in the audit trail
The problem
Most legal playbooks exist. Few are actually used.
Somewhere there is a Word document with your standard positions. It is outdated, hard to find and applied differently by everyone who opens it.
Knowledge sits with individuals
Which liability cap is acceptable in which deal is known by two senior lawyers. When they are away, reviews stall or run without a standard.
Inconsistent answers for the business
Sales gets a yes from one reviewer and a no from another for the same clause. Trust in legal suffers, and escalations multiply.
No way to measure quality
Nobody knows whether the playbook actually catches the risks it should. Gaps only surface when a problematic contract has already been signed.
Your outcome
Legal writes the rules once. The playbook does the repetitive work.
A playbook becomes valuable when it is applied automatically, consistently and verifiably — not when it is written.
Your outcome
Every incoming contract is reviewed against your playbook, with a traffic light, rationale and compliant wording per criterion.
Why it works
Golden-set tests show whether the playbook flags what it should before it reviews real contracts. Reviewer feedback keeps improving the results.
How fast
In the demo, you see your own contract reviewed against your criteria. In the Proof Sprint, playbooks for two contract types go live within ten working days.
How little effort
You do not write the playbook from scratch. We derive it with you from 10–20 historical contracts and your existing guidelines; legal confirms each rule.
Features
What legal playbook software in Treasure Contracts includes
All features on this page are live in the product.
Structured playbooks
Define criteria, targets and no-gos, set your party perspective and attach reference documents such as your standard template. Create custom contract types with their own playbook.
Traffic light per criterion
Each criterion is rated compliant, moderate or critical with a rationale, plus general AI risks, internal contradictions and deviations from your reference document.
Compliant wording suggestions
For every finding, Treasure proposes wording that fits your playbook. Reviewers can add their own risks and rate results, keeping a human in the loop.
Golden-set testing
Run a playbook against synthetic documents with known issues to check its quality before rollout and after every change.
Clause library alongside the playbook
Approved clauses live in a library with an editor and approval step, and are inserted live into templates. Clauses can also be managed via MCP (AI tool integration, €50/month, included from Professional).
Playbook routing by email
Plus addresses send forwarded contracts directly to a specific playbook, for example a dedicated NDA review inbox, protected by sender whitelists and DMARC/SPF checks.
How it works
From a Word playbook to an executable one
Demo on your own contract
Bring a contract and your key positions. In 30 minutes with the founders, we show Treasure reviewing it against them.
Derive the rules
We analyse 10–20 historical contracts and your guidelines, and turn them into criteria, targets and no-gos.
Confirm and test
Legal confirms every rule. Golden-set tests show whether the playbook flags what it should.
Run it live
In the Proof Sprint, two contract types are reviewed live with risk rating, redlines and audit trail, followed by formal acceptance.
Comparison
Word playbook, general AI prompt or Treasure Contracts?
Three ways to apply your contract positions — and how reliably each works.
| Criterion | Word or PDF playbook | Prompt in a general AI chat | Treasure Contracts |
|---|---|---|---|
| Applied to every contract | Only if someone reads it | Only if someone pastes it | Automatically, per playbook and contract type |
| Consistency | Depends on the reviewer | Depends on the prompt | Same criteria every time, confirmed by legal |
| Result | Comments in the margin | Free text | Traffic light per criterion with wording suggestion |
| Quality check | Manual spot checks | No golden-set testing like in Treasure | Golden-set tests with synthetic documents |
| Record | Document version history | Chat history; no per-contract audit trail like in Treasure | Audit trail for playbooks and reviews |
General orientation, depends on the tool and how it is used.
In detail
Legal playbook software: from written positions to executable rules
What goes into a good contract playbook
A contract playbook documents how your organisation handles recurring clauses: the preferred position, acceptable fallbacks and hard no-gos. In Treasure Contracts, legal playbook software goes one step further. Each criterion has a target and no-gos, the playbook knows whether you are buyer or seller, customer or supplier, and it can reference your own standard template. That perspective matters: an uncapped liability clause is a risk for one side and an advantage for the other.
Why playbooks matter more than the AI model
Treasure lets you choose the AI model per tenant and task, but the model is not what makes a review useful. A general model knows contract law in the abstract; it does not know your company's risk appetite. The playbook provides exactly that. Because every review runs against the same written criteria, results become comparable across reviewers, teams and months, and every rating can be traced back to the rule that produced it.
Using a playbook in negotiations
Negotiation playbooks usually define how far you can move on each point. Treasure applies those positions to every version the other side sends back: the review reruns automatically on each new version, the redline comparison shows what changed, and findings come with compliant wording you can propose in return. Treasure does not run negotiation rounds with the counterparty itself; it makes sure each draft you receive is checked against the same standard.
Testing and maintaining the playbook
A playbook is never finished. Laws change, business priorities shift, and new contract types appear. Golden-set tests let you run a playbook against synthetic documents with known issues, so you can see whether a change improves or weakens detection before it affects real contracts. Reviewer feedback on individual findings shows where rules need sharpening, and the audit trail records who changed what and when. That turns playbook maintenance into a controlled routine instead of an annual clean-up.
Your first step
Prove it first. Decide second.
You don't have to take our word for it. You see Treasure on your own contracts — first in a free 30-minute session, then in a 10-day Proof Sprint with measurable results.
For legal playbooks, that means: we turn your existing positions for two contract types into an executable playbook, test it with a golden set and show on your real contracts where it agrees with your lawyers.
1
Start free: your contract, reviewed live
30 minutes with the founding team. Bring a real contract and we show Treasure live on your clauses. No slides, 24-hour response guarantee — including a free AI Readiness Assessment.
Pick a time2
What you get in the 10-day Proof Sprint
- Baseline for cycle time, volume and legal effort
- Testable rules derived from your existing contracts and decisions
- Live test on 10–20 historical contracts with risk rating, redlines and audit trail
- Sign-off of the rules and jointly defined success criteria
- ROI analysis and a concrete 30-day plan for your first live process
€4,900 net, one-off · fully credited towards implementation if you sign within 30 days
Results guarantee: If Treasure misses the acceptance criteria agreed in writing up front, we keep working for up to 20 additional business days at no cost. If that is still not enough, we refund the sprint fee. This requires your timely cooperation; details are in the sprint offer.
Right of withdrawal: 4 weeks unconditional right of withdrawal with a full refund.
We run at most 3 Proof Sprints per month — we confirm the next available start date in the first call.
See pricing & Proof SprintFAQ
FAQ
What is the difference between a legal playbook and legal playbook software?
A legal playbook is the document with your positions. Legal playbook software applies it: Treasure stores criteria, targets, no-gos and your party perspective in a structured form and uses AI to check every contract against them, with a traffic light per criterion and compliant wording suggestions.
Do we need a finished playbook before we start?
No. Many teams have only scattered guidelines. In the Proof Sprint, we derive the playbook with you from 10–20 historical contracts and your existing rules. Legal confirms each criterion, and golden-set tests check the result before it goes live, so you start with rules that have already been measured.
Why not put our playbook into ChatGPT or Claude?
A prompt in a chat assistant is applied only when someone remembers to use it, results depend on the prompt, and there is no per-contract audit trail like in Treasure. Treasure applies the playbook to every contract and every version, tests it with golden sets and logs each review. Via MCP (AI tool integration, €50/month, included from Professional), you can still use Treasure from ChatGPT or Claude.
Where is our playbook and contract data stored?
On AWS in Frankfurt. AI processing takes place in EU regions, and your data is never used to train models. Tenants are separated at database schema level; two-factor authentication, Microsoft Entra ID SSO and an exportable audit trail are available. Information security is ISO 27001 certified.
What does legal playbook software from Treasure cost?
Plans start at €590 per month (Starter), with Professional at €1,790 and Business at €3,590, each billed annually and net; Enterprise on request. The 10-day Proof Sprint for €4,900 builds your first two playbooks and is fully credited towards implementation if you book within 30 days.
What happens if the playbook does not perform as expected?
Before the sprint, we agree on acceptance criteria in writing. If they are not met, we keep working for up to 20 additional working days at no extra cost, and otherwise refund the sprint price; your cooperation is required. The subscription also comes with a four-week unconditional right of withdrawal and a full refund.
Read next
Related solutions and features
Bring your next contract.
In 30 minutes you will know whether Treasure can apply your rules — on a real contract, with the founders.
Free · PDF guide
Implementing CLM with AI: A–Z
A practical workbook with ready-to-use prompts for requirements, vendor selection, rollout, adoption and ROI.
Double opt-in, unsubscribe anytime. No sales call, no spam.