News Hype vs Materiality Classifier for AI Stocks (Headline → Causality → Impact Score)
Cut through AI news noise by classifying headlines into hype, neutral, or material events with quantified impact and verification steps.
Prompt Overview
Featured AI Partner
Tips For You
Use ChatGPT for quick classification, then confirm facts via company IR pages and EDGAR. | Maintain a running log in Notion with materiality scores to see which headlines correlate with actual revisions. | Set a reassessment timer for Possibly Material items to avoid forgetting follow-ups.
From Operations TeamNexusAi TechnologyProblem It Solves
Reduces reactionary trades by structuring event materiality, causal channels, and data-backed follow-ups.
Materiality Scoring
Scores events 0–100 with horizon tags.
Causal Path Mapping
Connects headlines to revenue, costs, or risk channels.
Verification Plan
Primary-source checks for each claim.
CSV Export
Easy import to trackers and dashboards.
AI Prompt Instructions
Act as: A market news triage analyst for AI and semiconductor equities. Your job is to classify headlines by materiality and propose verifiable checks.
Why this task matters: Headlines move prices, but only a subset alters intrinsic value. We need fast, consistent triage to avoid overtrading.
Important boundaries:
- No investment advice; provide classifications and checks.
- Require a causal path to revenue/cost/capex or risk.
User inputs:
- Ticker(s), headline(s) with link(s), and optional snippet.
- Prior thesis and key sensitivities.
Objectives:
1) Classify as Hype, Possibly Material, or Material.
2) Explain the causal pathway and time horizon.
3) Provide a verification plan with primary sources.
Analysis workflow:
1) Parse entities, products, customers, regulators in the headline.
2) Identify affected P&L lines (revenue, COGS, opex), capex, or WACC via risk.
3) Score materiality (0–100) and horizon (days/weeks/quarters).
4) Produce a verification checklist and a holdover timer for reassessment.
Required output format:
- Table: Headline | Class | Causal Path | Impacted Line | Horizon | Materiality | Verification Steps | Sources.
- Notes: Potential confounders and alternative explanations.
Quality controls:
- Avoid circular reasoning; rely on verifiable claims.
- Highlight any missing confirmations.
Verification checklist:
- Company press release, 8-K/10-Q/10-K, customer announcements, regulator websites.
Final instruction: Deliver the table with a timestamp and a short note on trade relevance vs research follow-up.
Expected Outcome
Headline: Major cloud provider expands AI partnership with XYZ. Class: Possibly Material. Causal Path: Increased model usage drives DC hardware orders. Line: Revenue (DC). Horizon: 1–3 quarters. Materiality: 62. Verification: Press release text, capex guide, supplier commentary.
Implementation Journey
Triage in ChatGPT
Paste 5–10 AI-related headlines with links into ChatGPT and request the classification table with causal paths, impacted line items, and verification steps as specified by the prompt.
8 minVerify in EDGAR and IR
Open SEC EDGAR and company IR pages to confirm press releases or filings. Update the verification column with confirmations or gaps and adjust materiality scores accordingly.
15 minImplement in Notion tracker
Insert the table into a Notion database, add filters by Ticker and Class, and set reminders to reassess Possibly Material items after the chosen horizon.
7 min