AI Prompting & Wall Street Stocks: From Financial Data to Analyst Discipline

This Week’s Focus: AI’s New Edge in Market Analysis

Markets entered November with cautious optimism. The Federal Reserve’s rate cut signaled a gradual shift toward easing, while Big Tech earnings underscored both the strength of AI-driven growth and the limits of current momentum. Geopolitical sentiment also improved after Presidents Trump and Xi confirmed that U.S. and Chinese negotiators had reached a “basic consensus” on a trade framework covering tariffs and rare-earth exports.

As investors recalibrate forecasts, two deeper shifts are redefining financial analysis. Real-time data connectivity through the Model Context Protocol (MCP), as discussed by Anthropic, is allowing models to access live, verified data. At the same time, structured prompting is teaching AI systems to reason more like analysts than text generators. Together, these innovations are reshaping how insight is created, verified and shared.

From Isolated Models to Connected Systems

Until recently, large language models (LLMs) relied on static training data that quickly became outdated. The Model Context Protocol, introduced by Anthropic in late 2024, created a common interface between AI systems and external data sources.

You can think of MCP for AI applications much like a USB-C port for hardware, a universal connector. OpenAI officially adopted MCP across its ChatGPT desktop app in March 2025, and  Google confirmed MCP support in upcoming Gemini models that April.

For analysts, this marks a quiet but profound shift. Models no longer operate as closed text generators but as data-aware research assistants. Several open-source tools now link AI models to platforms like Yahoo Finance via MCP, allowing retrieval of company financials, options activity and insider transactions without custom API work. A simple prompt such as “Retrieve Tesla’s last four quarters of operating income” now draws directly from verified filings instead of probabilistic guesses.

FactSet has also begun deploying MCP within its enterprise architecture. As the firm explained, the protocol provides "a control plane for AI capabilities where you implement rate limiting, access controls, audit logging, and dependency management." In other words, the focus is both on data access as well as governed, auditable workflows.

AI in Action: What Smart Promps Reveal This Earnings Season

📌 Prompt Example 1 — Meta Platforms Post-Earnings Story

Meta Platforms’ (META) Q3 2025 earnings underscored the market’s new discipline: growth alone isn’t enough. The company beat on both revenue and profit, but shares fell after it booked a $15.9 billion one-time tax charge linked to President Trump’s One Big Beautiful Bill Act. The charge was non-cash, yet it sharpened investor focus on Meta’s cost structure, particularly escalating AI infrastructure spending and ongoing Reality Labs losses. Capital intensity, not just competition or regulation, now defines Big Tech risk.

That’s where a structured prompt earns its value. Instead of asking, “Is Meta still a buy after earnings?”—a question that invites broad opinion—a disciplined prompt isolates the facts, then forces interpretation.

Example prompt:

By separating data retrieval from reasoning, this approach cuts through headlines and sentiment swings—revealing whether Meta’s AI-driven momentum rests on sustainable economics or increasingly expensive ambition.

📌 Prompt Example 2 — Walt Disney’s Upcoming Earnings

With Walt Disney’s (DIS) fiscal Q4 2025 results expected before market open on November 13, analysts are evaluating whether streaming profitability and park momentum can offset rising content costs. A structured prompt used ahead of results clarifies which performance drivers will matter most once the numbers are released.

Structured Pre-Earnings Prompt:

This AI prompting method defines success before earnings arrive, turning analysis from reaction into preparation. When results are published, it allows for a quick, disciplined comparison between expectations and reality. In practice, prompts like these help investors isolate the turning points that shape sentiment, such as whether streaming margins are improving faster than production costs.

How We Can Support Your Business 

We're a small team of investment professionals behind this newsletter focused on research, analysis and AI tools for finance. Drawing from decades of experience at funds, corporates and investment writing agencies in the U.S., U.K. and continental Europe, here's how we can support your business further:

• AI Prompting Training for Investment Professionals: We offer live, in-person or online, global learning & development sessions on AI prompting for investment research, analysis and writing.

• Investment Writing Services: Need high-quality content? We create fund commentary, investor letters, white papers and more, tailored to your voice and audience.

• Feature Your Business: Showcase your company, products or services to our audience of investment professionals and retail investors.

• LLM Training in the U.S., U.K. and Europe: Training the next-generation LLMs? We currently provide subject-matter consulting services to California-based LLMs (under NDA).

& Ways You Can Support Independent Research

• Click Our Sponsor Links: Each click from our sponsors helps fund our research. (Yes, even one click matters.)

• Share with your colleagues: If you like the content, please share it with your colleagues on social media platforms or at work.

• Support Our Work: Value our insights? You can contribute and support us with a coffee here: https://ko-fi.com/investingprompts  

• For collaborations, training or writing services: [email protected] 

From Analysis to Advantage

The real edge now belongs to analysts who pair live data access with structured reasoning. That means:
• Separating data retrieval from interpretation.
• Using repeatable prompt templates for earnings and sector reviews.
• Verifying outputs instead of taking them at face value.
• Recognizing each tool’s scope and limits.
• Refining prompt frameworks before the next earnings cycle.

As earnings season continues and Big Tech results fade into context, what matters most is not necessarily the volume of data but the clarity of interpretation. Structure turns information into insight, and disciplined prompting keeps that process consistent from one quarter to the next.

Thank you for reading AI in Investment Research & Finance. Here’s to spotting tomorrow’s market stories today.

Until next time