Podcast Summary – The Personal Finance Podcast
Episode: How to Use AI to Research Stocks (With Brian Feroldi)
Host: Andrew Giancola
Guest: Brian Feroldi
Date: November 3, 2025
Episode Overview
In this action-packed episode, host Andrew Giancola is joined by investing educator and author Brian Feroldi to dive deep into how individual investors can use AI as a research assistant for analyzing stocks. They discuss the mindset and process shifts needed to effectively leverage AI, walk through live demo prompts, and offer listeners practical techniques, frameworks, and resources for integrating AI into their investing workflows.
The episode emphasizes treating AI not as a decision-maker, but as a junior analyst—augmenting, structuring, and accelerating fundamental research while always maintaining your own judgment. Brian shares his top prompting strategies and even provides free access to his business analysis prompt.
Key Discussion Points & Insights
1. The Long-Term Investing Mindset (04:25–07:00)
- Andrew and Brian’s shared journey: Both tried day trading, penny stocks, and high-dividend strategies before settling on long-term investing inspired by Buffett, Munger, and Peter Lynch.
- Brian’s philosophy:
“Think of stocks not as tickers, but as businesses. Only invest in businesses that you understand and you think have good long term growth prospects.”
(Brian Feroldi, 05:25) - Key lesson: Avoid the temptations of short-term speculation; focus on business fundamentals.
2. Why AI is a Game-Changer for Investors (07:39–09:00)
- AI’s core advantage: Ingests and parses huge volumes of financial documents (e.g., 10-Ks, earnings calls) and delivers digestible summaries and explanations.
- Especially useful for new investors to “lower the skills you need to get started.”
- AI as tutor: Makes it easier to understand complex investing terms and processes.
-
“AI can act as a tutor slash buddy for figuring out what the terms mean — it is a godsend for new investors.”
(Brian Feroldi, 08:31)
3. AI as a Junior Analyst: Setting the Right Mindset (09:15–11:08)
- Don’t treat AI as an all-knowing oracle.
“Think of AI as a junior research assistant or think of them as an intern.”
(Brian, 09:15) - Give AI precise, step-by-step instructions—just like managing an intern.
- Vague prompts (e.g., “Is Amazon a buy?”) result in generic, unfocused, and potentially misleading outputs.
4. Guardrails: When to Rely on AI vs. Your Own Judgment (11:08–12:26)
- Ultimate responsibility stays with the investor.
“If the AI makes a mistake in the analysis, it's going to cost them nothing.”
(Brian, 11:32) - “Never outsource all of my decision making and thinking to AI... use it for what it’s best at: digesting information and presenting it back so I can make a more informed decision.”
5. Avoiding AI Hallucinations: Vetting Information (13:03–14:06)
- AI hallucinations ("made-up facts") are a major risk.
- Most important: Provide highly detailed and specific prompts and restrict the sources used.
-
“If you don’t constrain the AI into the instructions that you specifically want... it might go out and present you with information that's basically utterly useless.”
(Brian, 10:52)
6. The Power of Modular, Stepwise Prompts (14:21–15:51)
- Break down analysis into micro-tasks:
- What does the company do?
- What is its business model?
- Moats, financials, management, risks, valuation, etc.
- Verify each step before moving on to build a trustworthy, layered research process.
-
“Take big tasks, break them down into smaller micro tasks, verify the information... that will give you much more confidence in the final output.”
(Brian, 15:27)
7. Core Prompting Techniques for Reliable AI Analysis (20:28–24:57)
Brian’s 3 steps for prompting AI:
- Assign a role:
- E.g., “Act as Warren Buffett” or another notable investor. This conditions AI to focus on relevant investing frameworks and language.
-
“That one step alone will dramatically increase the quality of information you get back.”
(Brian, 22:18)
- Require citations & restrict sources:
- Only allow trusted sources (e.g., SEC filings, company sites, Morningstar Moat rating).
- Always require direct links to cited documents.
-
“When it's presenting me with information, I force it to put a citation with a link...”
(Brian, 23:42)
- Stepwise instructions:
- Lay out a checklist/order: “Do A, then B, then C...”
- Match the process you’d use as an analyst. If you have your own checklist, feed it into the AI.
8. Building a Prompt Library (26:27–27:13)
- Keep a database of your best prompts for reuse—don’t lose them in chat history.
-
“Put time into building out a series of prompts for yourself — that will save you hours upon hours of research down the road.”
(Brian, 47:01)
Notable Quotes
-
“AI won’t make investment decisions for you, but it can make researching businesses dramatically faster, cleaner, and way more structured.”
— Andrew Giancola (02:51) -
“Think of AI as a junior research assistant... You wouldn't just give that intern unlimited control.”
— Brian Feroldi (09:15) -
“You have to be the ultimate decision maker. This is your money that's on the line.”
— Brian Feroldi (11:32) -
“If you limit the places the AI can pull sources from, and you force it to give you a citation of where it came up... trust goes up dramatically.”
— Brian Feroldi (24:03)
Live Demo: Walkthrough of Brian’s Custom Prompt (27:13–45:52)
Walkthrough of Business Research Prompt (27:13–45:52)
Prompt Structure Highlights:
- Role assignment:
“You are an expert financial analyst specializing in business model analysis from SEC filings.” (Brian, 27:18)
- Stepwise instructions: Analyze most recent 10K, answer questions in order, verify, output with links.
- Source restriction: Only use original, trusted sources (SEC, company files, etc.)
Analyzing Iren Limited (29:11–36:22)
- Summary output included:
- What the company does (bitcoin mining, AI cloud/data centers, etc.)
- How it makes money (mining is dominant, but cloud services growing)
- Key customers, operational geography, business model dynamics, pricing power, recession resistance.
- Every bullet included direct source links.
Analyzing Apple (Company Everyone Knows) (37:56–45:07)
- Prompt produced:
- Up-to-date product/services breakdown
- Revenue split (products vs. services)
- Geographic sales breakdown
- Pricing power, customer types, recession analysis
- All numbers cross-verified with actual SEC filings
Key Takeaway:
“This prompt might even teach you something about the company that you’ve owned and think you know so well.”
(Brian, 45:07)
Practical Tips for Listeners
- Start simple: Use Brian’s business analysis prompt as a template (link below).
- Refine prompts: Add your own priorities, checklists, or preferred sources.
- Always verify: Click citations and review source documents for accuracy.
- Don’t skip judgment: Use AI as your accelerating “junior analyst” — never as boss.
Resource & Contact Information
- Brian’s Free Business Analysis Prompt:
Get a copy at longtermmindset.co/PFP (“for Personal Finance Podcast”) - Find Brian Feroldi on all major social media platforms and at longtermmindset.co
- Watch the full live screen-share demo at Andrew’s YouTube channel
Memorable Moments & Quotes with Timestamps
-
On the importance of clear roles for AI:
“If you give it that simple one sentence up front, ‘act as Warren Buffett’... it immediately prioritizes relevant information.”
(Brian, 21:44) -
On the perils of over-trusting AI:
“Never outsource all of my decision making and thinking to AI... this is my money that’s on the line.”
(Brian, 11:32) -
On the value of prompt libraries:
“If you develop processes... that’s going to change the information that gets spit out to you every time.”
(Andrew, 15:51)
Listener Actions
- Download Brian’s prompt and experiment with stepwise analysis on your favorite stock.
- Assign a role to AI (e.g., Warren Buffett), provide a checklist, and demand direct citations.
- Integrate—don’t outsource—AI into your investing process. Use as a research assistant, not a replacement for judgment.
Summary prepared for listeners of The Personal Finance Podcast: actionable, detailed, and ready to use in your research journey.