AI Playbook for Working Capital Normalization
A PE acquisition target has a proposed working capital target of $8.4M in the purchase agreement. The target's trailing 12-month average working capital is $11.2M. The seller's investment bank claims the higher average reflects normal seasonality. The buyer believes the target has been building working capital before closing. Closing is in 14 days.
When to use this playbook
- Use this playbook when the decision looks like the situation above: A PE acquisition target has a proposed working capital target of $8.4M in the purchase agreement.
- It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Working Capital Normalization".
- Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.
What you'll need
- Monthly working capital data (past 24 months: AR, AP, inventory, accruals)
- Purchase agreement working capital definition and target
- Seasonality analysis from the seller's IB
- Detailed AR aging by customer (current and 60 days prior)
- Inventory roll-forward and current inventory count
Attachments: Multiple attachments (Spreadsheets, Documents)
The Prompt
You are a financial advisor resolving a working capital dispute in a PE acquisition. I am attaching: Work only from the attached source files. If a conclusion is not supported, say so. Produce: 1. Calculate normalized working capital using a methodology that excludes seasonal peaks and transaction-related build: what is the true representative working capital? 2. Identify any pre-closing working capital manipulation: was AR accelerated (early billing), AP stretched, or inventory built beyond normal patterns in the 90 days before closing? 3. Assess the seller's seasonality argument: is the $11.2M 12-month average driven by genuine seasonality or by pre-closing activity? 4. Calculate the expected post-closing working capital adjustment if the target is set at $8.4M vs. normalized levels. 5. Tell me the negotiation position: what target to propose, what methodology to defend it, and what the true purchase price adjustment is. Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.
What to expect
- Normalized working capital calculation
- Pre-closing manipulation analysis
- Seasonality argument assessment
- Post-closing adjustment calculation at different targets
- Negotiation position with methodology and purchase price impact
Review before you act
- Validate this output against source files before relying on it: Calculate normalized working capital using a methodology that excludes seasonal peaks and transaction-related build: what is the true representative working capital?.
- Validate this output against source files before relying on it: Identify any pre-closing working capital manipulation: was AR accelerated (early billing), AP stretched, or inventory built beyond normal patterns in the 90 days before closing?.
- Validate this output against source files before relying on it: Assess the seller's seasonality argument: is the $11.2M 12-month average driven by genuine seasonality or by pre-closing activity?.
- Validate this output against source files before relying on it: Calculate the expected post-closing working capital adjustment if the target is set at $8.4M vs. normalized levels.
- 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 Working Capital Normalization, 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 normalized working capital calculation; pre-closing manipulation analysis; seasonality argument assessment; post-closing adjustment calculation at different targets. 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.

