AI Customer Contract Risk Analysis Playbook
A strategic acquirer is buying a $70M revenue B2B services company. The target has 240 customer contracts. Legal due diligence has flagged that 38 contracts have change of control provisions that may require customer consent or allow early termination without penalty. These 38 contracts represent $31M in annual revenue.
When to use this playbook
- Use this playbook when the decision looks like the situation above: A strategic acquirer is buying a $70M revenue B2B services company.
- It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Customer Contract Risk Analysis".
- Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.
What you'll need
- 38 flagged customer contracts with change of control provisions
- Annual revenue and contract term for each flagged customer
- Customer relationship notes from management
- Acquirer's proposed transaction structure (asset purchase vs. stock purchase)
- Comparable deal consent solicitation precedents
Attachments: Documents (Documents)
The Prompt
You are an M&A attorney analyzing customer contract risk for a strategic acquisition. I am attaching: Work only from the attached source files. If a conclusion is not supported, say so. Produce: 1. Classify each of the 38 contracts: (a) requires written consent, (b) allows termination if not consented, (c) provides for fee adjustment, or (d) deemed consent with notice. 2. Identify the contracts where non-consent risk is highest based on relationship health, contract value, and competitive alternatives for the customer. 3. Assess whether a stock purchase structure (no technical assignment) eliminates the change of control trigger in any of these contracts. 4. Calculate the revenue at risk if the highest-risk contracts exercise termination rights and the purchase price adjustment this warrants. 5. Tell me the consent solicitation strategy: which customers to approach before signing, which after, and what concessions to offer to secure consent. Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.
What to expect
- Contract classification matrix (consent/termination/adjustment/notice)
- High-risk contract identification
- Stock purchase structure trigger analysis
- Revenue at risk and purchase price adjustment
- Consent solicitation strategy with concession framework
Review before you act
- Validate this output against source files before relying on it: Classify each of the 38 contracts: (a) requires written consent, (b) allows termination if not consented, (c) provides for fee adjustment, or (d) deemed consent with notice.
- Validate this output against source files before relying on it: Identify the contracts where non-consent risk is highest based on relationship health, contract value, and competitive alternatives for the customer.
- Validate this output against source files before relying on it: Assess whether a stock purchase structure (no technical assignment) eliminates the change of control trigger in any of these contracts.
- Validate this output against source files before relying on it: Calculate the revenue at risk if the highest-risk contracts exercise termination rights and the purchase price adjustment this warrants.
- Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
- Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
- Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.
Why compare models on this
For Customer Contract Risk Analysis, running the same attachments across independent models is useful because the hard part is classification and completeness, not fluency. The workflow is already designed to surface contract classification matrix (consent/termination/adjustment/notice); high-risk contract identification; stock purchase structure trigger analysis; revenue at risk and purchase price adjustment. Those are comparison artifacts — they only exist if more than one model runs. Models disagree on whether revenue is pull-forward, whether a contract is terminable, and how much working capital to normalize. Those fights are the diligence memo.
See governed multi-model AI on your own prompt
Compare GPT-5, Claude, and Gemini side by side, with human review and a decision record built in.

