10-K Risk Factor Triage
Separate boilerplate from material new risks in an annual report and rank them by likely impact on the investment case.
Prompt
ROLE: You are a forensic analyst who reads 10-K risk sections for what changed and what's genuinely material, ignoring legal boilerplate. CONTEXT: Company: [COMPANY_NAME] ([TICKER]). I'll paste the Risk Factors section, and if available, last year's for comparison. My thesis hinges on: [THESIS_DRIVER]. CURRENT RISK FACTORS: [PASTE_CURRENT] PRIOR-YEAR RISK FACTORS (optional): [PASTE_PRIOR] TASK: 1. Classify each risk as Boilerplate (generic), Standard-industry, or Company-specific & material. 2. Identify risks that are NEW or materially reworded versus the prior year — these signal what management is newly worried about. 3. For each material risk, estimate likelihood (Low/Med/High) and potential thesis impact (Low/Med/High). 4. Flag any risk that directly threatens my stated thesis driver. 5. Note conspicuous omissions — risks a competitor discloses that this company doesn't. OUTPUT FORMAT: A ranked table (risk / category / new? / likelihood / impact / thesis-relevance) sorted by impact, followed by a 3-bullet 'What This Tells Us' summary. CONSTRAINTS: Do not treat every risk as equally serious — that's the whole point. Quote the trigger phrase for any 'new/reworded' claim. If prior year isn't provided, say which judgments are limited without it.
How to use this prompt
- 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
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
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniquePins the response to a defined structure so it drops straight into your workflow.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueRecommended models
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
Equity Investment Thesis Builder
Construct a rigorous bull-and-bear investment thesis for a single stock with explicit variant perception and falsifiable assumptions.
DCF Valuation Walkthrough
Step through a transparent discounted-cash-flow model with stated assumptions, sensitivity, and a sanity check against multiples.
Earnings Call Transcript Decoder
Extract guidance changes, tone shifts, and evasive answers from an earnings call transcript into a structured signal sheet.
Portfolio Risk X-Ray
Diagnose hidden concentration, factor tilts, and correlation risk across a multi-position portfolio with concrete rebalancing options.