AI Round-Trip Transaction Detection Playbook

Your firm is engaged by a $280M manufacturer's audit committee after the external auditor flagged $4.2M in Q3 revenue that reversed in Q4. You have the general ledger export, sales journal, and accounts receivable aging. Three of the four transactions involve the same shipping intermediary registered in Delaware six months ago.

When to use this playbook

• Use this playbook when the decision looks like the situation above: Your firm is engaged by a $280M manufacturer's audit committee after the external auditor flagged $4.2M in Q3 revenue that reversed in Q4.
• It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Round-Trip Transaction Detection".
• Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

• General ledger export (Q2–Q4)
• Sales journal detail
• Accounts receivable aging report
• Entity registration records for the counterparty

Attachments: Multiple attachments (Spreadsheets, Documents)

You are a forensic accountant investigating potential round-trip revenue transactions at a $280M manufacturer. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. Identify all transactions that share the pattern: revenue recognized in one quarter, reversed or credited in the next, involving the same counterparty or payment routing.
2. For each flagged transaction, calculate the net economic impact and identify whether cash ever actually changed hands.
3. Assess whether the transaction structure indicates revenue inflation for covenant compliance, bonus triggers, or earnings management.
4. List the specific journal entries I should pull and the questions I should put to management.
5. Recommend whether this requires SAB 99 materiality analysis and what additional documents I need before I can conclude.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

• Multi-model consensus on transaction classification
• Divergent flags where models disagree on materiality
• Specific document requests ranked by evidentiary value
• Draft management inquiry questions

Review before you act

• Validate this output against source files before relying on it: Identify all transactions that share the pattern: revenue recognized in one quarter, reversed or credited in the next, involving the same counterparty or payment routing.
• Validate this output against source files before relying on it: For each flagged transaction, calculate the net economic impact and identify whether cash ever actually changed hands.
• Validate this output against source files before relying on it: Assess whether the transaction structure indicates revenue inflation for covenant compliance, bonus triggers, or earnings management.
• Validate this output against source files before relying on it: List the specific journal entries I should pull and the questions I should put to management.
• 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.