Identify New Opportunities: Stocks with a High Probability of Experiencing a Multiple Re-rating or De-rating
using sophisticated context engineering
Last updated: 16 December 2025
Objective:
The largest share price opportunities come from situations where investor’s identify impactful changes to a stock’s operating environment early. This leads to a period where the key value drives of a company either accelerate or decelerate, changing the market’s view, and drive large changes (re-rating or de-rating) in a company’s valuation multiple and resultant share price. This prompt workflow uses detailed Context Engineering by way of 40 synthesized historic examples to feed the AI model with sufficient context to use its pattern recognition capabilities to identify similar situations across the market.
Explanation:
This prompt is designed to function as a high-level pattern-matching engine, using context engineering (specifically “many-shot prompting”) to train the AI to mimic the reasoning of a fundamental equity analyst.
By providing a diverse set of detailed historical examples—such as Oracle’s shift to AI cloud infrastructure or Celsius’s distribution deal—the prompt moves beyond simple instruction and instead demonstrates the precise causal chain it seeks: an external catalyst (operating environment change) triggering an acceleration in internal value drivers (revenue/margins), which inevitably forces the market to assign a higher valuation multiple to the stock. This effectively calibrates the model to ignore generic “cheap” stocks and instead hunt for structural discontinuities—specific moments where a company’s future earnings power is decoupling from its historical trend, creating a temporary pricing inefficiency that the market has not yet recognized.
For investors, these opportunities are the “holy grail” because they offer asymmetric returns driven by a multiplier effect: the share price rises not only because earnings grow, but because the market decides to pay more for every dollar of those earnings (multiple expansion). The AI spots these by synthesizing qualitative data—such as backlog acceleration, regulatory approvals, or strategic pivots—with quantitative disconnects, looking for situations where a stock is priced like a low-growth legacy business (e.g., an auto parts supplier) but is silently transitioning into a high-growth vertical (e.g., AI data center cooling). This approach allows the model to identify “coiled spring” setups where the current valuation fails to reflect the imminent change in the company’s economic reality.
Important Note: This prompt is designed as an initial stock screen - not to produce investment recommendations and is subject to our Disclaimer (accessible from top menu). As always, be aware that models can make mistakes. At each step, examine the response and challenge information or conclusions that appear erroneous before proceeding to any subsequent steps. If in doubt use a second model with the same prompt to verify the information and generate challenge questions and answers (CoVe process) to correct interpretations of data.
Link to blog post explanation:
N/A
Preferred Model(s):
· Gemini 3 + Deep Research
Important Execution Notes:
Input the geographic and market cap focus range where indicated.
Ensure Deep Research is selected.
Sample Output:
Copy/Paste Prompt Set:
Important note: Subscribers can use this prompt set for their own analysis. However, the prompt is copyrighted by The Inferential Investor, paywalled, and must not be shared without permission.