ReviewModerate riskComparison recommended

AI Related-Party Disclosure Gap Analysis Playbook

A pre-IPO SaaS company is preparing its S-1. The CFO has asked you to stress-test related-party disclosures before the SEC review. Revenue includes $6.8M from three customers whose principals have personal relationships with the CEO and two board members.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A pre-IPO SaaS company is preparing its S-1.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Related-Party Disclosure Gap Analysis".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Draft S-1 related-party section
  • Cap table and investor roster
  • Customer master file with principal contact names
  • Board and officer biographies
  • $6.8M in contracts from the three flagged customers

Attachments: Documents (Documents)

The Prompt

You are a forensic accountant conducting a related-party disclosure review for a pre-IPO SaaS company preparing its S-1. I am attaching:

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

Produce:
1. Map every disclosed and undisclosed connection between the company's officers, directors, investors, and its top 20 revenue customers.
2. Identify any revenue recognized from entities where a board member or officer holds an ownership stake, advisory role, or family connection—even if not disclosed.
3. Flag contracts where pricing deviates materially from arm's-length comparables in the customer file.
4. Draft the disclosure language the SEC will expect, and flag the disclosures currently in the S-1 that are insufficient.
5. Tell me which of these relationships require board independence reassessment before the roadshow.

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

What to expect

  • Relationship map across all parties
  • Gap list between current disclosures and SEC standard
  • Revised disclosure language by relationship
  • Independence risk flags

Review before you act

  • Validate this output against source files before relying on it: Map every disclosed and undisclosed connection between the company's officers, directors, investors, and its top 20 revenue customers.
  • Validate this output against source files before relying on it: Identify any revenue recognized from entities where a board member or officer holds an ownership stake, advisory role, or family connection—even if not disclosed.
  • Validate this output against source files before relying on it: Flag contracts where pricing deviates materially from arm's-length comparables in the customer file.
  • Validate this output against source files before relying on it: Draft the disclosure language the SEC will expect, and flag the disclosures currently in the S-1 that are insufficient.
  • 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 Related-Party Disclosure Gap 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 relationship map across all parties; gap list between current disclosures and sec standard; revised disclosure language by relationship; independence risk flags. Those are comparison artifacts — they only exist if more than one model runs. Models often split on qualitative materiality, intent versus error, and whether a newly formed counterparty is a red flag or a legitimate intermediary. Those splits are the review queue — not noise.

Forensic AccountingRelated-Party and Corruption RiskReviewModerateDocuments

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.