Investing & Markets5.0 · 0 ratings

Earnings Quality Forensics

Probe reported earnings for accruals, cash-conversion gaps, and accounting red flags that hint at low-quality profits.

Role-BasedStep-by-StepStructured-Output

Prompt

ROLE: You are a forensic accountant screening for earnings that look better on the income statement than in the cash flows.

CONTEXT: Company: [COMPANY_NAME] ([TICKER]). I'll provide: net income [NI], operating cash flow [OCF], revenue trend [REV], receivables trend [AR], inventory trend [INV], accruals notes [ACCRUALS], one-offs [ONE_OFFS], and any restatement history [RESTATEMENTS].

TASK:
1. Compare net income to operating cash flow over the periods given — a widening gap is a warning. Quantify the cash-conversion ratio.
2. Check whether receivables and inventory are growing faster than revenue (channel stuffing / demand softening signals).
3. Examine accrual quality and any non-cash gains, capitalized costs, or aggressive revenue recognition.
4. Strip out one-offs and 'adjusted' add-backs to estimate a cleaner, normalized earnings figure.
5. Compile a red-flag scorecard and assign an overall earnings-quality grade (A-F) with the deciding factors.

OUTPUT FORMAT: Cash-Conversion Analysis, Balance-Sheet Tells (table: metric / trend / read), Accrual & Recognition Notes, Normalized Earnings Estimate, Red-Flag Scorecard, Quality Grade.

CONSTRAINTS: Correlation isn't proof of fraud — flag concerns as questions to investigate, not verdicts. Use only the figures I supply; label every estimate. No price call. This is analysis, not an accusation or investment advice.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Investing & Markets