About the Book

Twenty chapters. One argument: the tools changed, the framework didn't, and now you can run both at once.

The AI Edge for Modern Investors starts four thousand years before AI existed, because sector rotation only works if you understand the cycle it's rotating through. Then it hands you the prompts to run that framework with tools that didn't exist five years ago.

Get the Book
Introduction
Introduction to Passive Investing: The Philosophy of Investment Legends
Opens not with a statistic but with a serious, respectful account of the pioneers of passive investing (Bogle, Buffett, Lynch, Graham, and Dalio) before making the turn: that as timeless as passive investing is, the tools available to investors keep evolving. Later in the chapter, the case for AI-assisted analysis is grounded in a 2024 Journal of Financial Economics study in which an AI model, trained only on public information, outperformed the average human analyst's 12-month price forecast in 55.9% of cases.
Chapter 1
My Investment Journey
A personal, memoir-style chapter recounting the mistakes that motivated the book, including a costly whole life insurance decision and a formative experience at Oxford, and presenting the author's own audited 2007–2009 track record as the book's founding credential.
Chapter 2
The Theory of Cyclicality: Patterns from Ancient Civilizations to Modern Financial Markets
A genuinely unusual chapter for this genre: cyclical thinking from Joseph's seven fat and lean years, through Jevons's sunspot theory and Kitchin's 3–5 year inventory cycle, to the 1946 work by Mitchell and Burns that still underlies how recessions are dated today.
Chapter 3
The Economic Cycle: A Foundation for Sector Rotation
Turns that history into the book's practical model: the four phases of the modern economic cycle and the indicators that define each one, the framework every later chapter builds on.
Chapter 4
Why Sector Rotation Matters
Introduces the 11 sectors of the S&P 500 as the "playing field" for rotation and makes the case that this movement is rooted in recurring economic rhythms, not random guesswork.
Chapter 5
Executing AI-Driven Sector Rotation
A practical operating manual: five steps for running an AI-enhanced rotation strategy: defining objectives, building a toolset, reading signals, executing allocations, and refining over time.
Chapter 6
Sector Rotation Through History
Tests the framework against four real periods: 1973–1975 (the oil shock and stagflation, when OPEC quadrupled oil prices), 1999–2002 (the dot-com bubble, when the NASDAQ Composite roughly quadrupled into its March 2000 peak and both technology and telecom lost more than 70% in the bust that followed), 2007–2009 (the financial crisis), and 2020–2022 (the pandemic recession and inflation rebound).
Chapter 7
The Best Tools for Implementing a Sector Rotation Strategy
A practical map of the AI and analysis platform landscape, explaining what each tool is actually built for, without the vendor pitch.
Chapter 8
Common Pitfalls in Sector Rotation
A candid look at where rotation strategies go wrong. Timing mistakes come first: mistiming a rotation, entering too early or exiting too late, is identified as one of the strategy's greatest challenges.
Chapter 9
How Artificial Intelligence Can Improve Portfolio Management
A deep dive into the specific mechanisms by which AI can improve portfolio management, building toward the named case study that follows.
Chapter 10
Case Study: Implementing AI-Driven Sector Rotation
The book's named real-world test: Allie D., a 38-year-old financial analyst who committed $1 million to an AI-driven sector rotation strategy in early 2023. Over the following two and a half years (navigating an expansion, a late-cycle peak, and a contraction) her strategy returned 14.77% annualized against the S&P 500's 10.1%.
Chapter 11
Mastering Prompt Engineering
Teaches the practical skill of writing effective prompts, including a worked example run against real Freddie Mac and Redfin housing data to stress-test a housing-sensitive portfolio, copy-paste ready, not a hypothetical.
Chapter 12
What Are the Best AI Tools Available to Optimize a Sector Rotation Strategy?
Evaluates the five dominant LLM families (GPT, Claude, Gemini, Llama, and Grok) against the same investing prompts, so you know which tool is actually suited to which task. Perplexity and QuantConnect appear alongside them as complementary tools (live-search citations and execution, respectively), not as additional model families.
Chapter 13
How AI Handles Unexpected Market Events
Addresses how AI tools help investors respond when geopolitical shocks, natural disasters, or sudden policy changes disrupt a carefully planned strategy.
Chapter 14
Outsmarting the Index: How AI Creates a New Edge for Investors
A genuinely counterintuitive chapter: argues that a simple S&P 500 index fund may offer less diversification than most investors assume, citing technology-related weighting near 30% of the index and the March 2023 Silicon Valley Bank failure as a real stress case, plus the DALBAR and Morningstar research on the behavior gap between what funds return and what investors actually earn.
Chapter 15
Blending Old Wisdom and New Tech
Argues that what is genuinely new about AI is not that it overturns durable investing principles, but that it does two things the old toolkit could not: puts institutional-grade capability in the hands of an ordinary investor, and executes the discipline investors already know they should follow. "Democratization and discipline," in the book's own words.
Chapter 16
Comparing Artificial Intelligence (AI) and Human Intuition
Draws the line between what a model should decide and what a person should, closing with four scenarios, explicitly labeled illustrative composites, in which that line mattered.
Chapter 17
How AI Can Help Mitigate Significant Risks
The book's signature practical tool: a five-scenario stress test (rates +100 bps, oil +$20, credit spreads +150 bps, VIX +15 points, the dollar +5%) that shows you which of your holdings would be hit hardest by each, and what to do about it before it happens, not after.
Chapter 18
Charting the Future: How AI Will Revolutionize Sector Rotation
A forward-looking chapter on where AI-driven rotation strategies are headed next.
Chapter 19
The Future Relationship Between AI and Quantum Computing
A grounded look at what quantum computing could eventually mean for markets, based on real, current hardware roadmaps from IBM, Google, and Quantinuum, not speculation.
Chapter 20
Mastering AI Terminology
A full glossary of the AI and investing vocabulary used throughout the book: a practical reference you'll return to, rather than a chapter meant to be read straight through.
The Part You'll Actually Use

Two appendices, built to be used the same day you read them.

Not a summary of the chapters: a working reference you'll return to long after you've finished the book.

Appendix A

The Expanded Economic Indicator Table

Every indicator referenced throughout the book, in one place: what it measures, where to find it updated, and how to read it against the four-phase framework.

  • Yield curve slope
  • PMI (manufacturing & services)
  • Credit spreads
  • Inflation trends (CPI/core)
Appendix B

Eight Ready-to-Use Prompt Templates

The exact wording this entire book is built on: sector ranking, signal confirmation, historical analog comparison, portfolio stress-testing, tax-loss harvesting, and more. Paste into any AI model today.

  • 1.1 Sector Ranking by Economic Phase
  • 1.2 Signal Confirmation Across Indicators
  • 1.7 Stress Testing Your Current Portfolio
  • + 5 more, covering the full workflow
Why This Book Is Different

Every claim comes with a way to check it.

Every AI tool is tested, not just described.
Five major model families, run against the same prompts, so you see what each is actually good at.
Every historical claim is sourced.
Endnotes run throughout the book, not just a bibliography tacked on at the back.
Every framework comes with a template.
Appendix B isn't a summary; it's eight ready-to-use prompts, the same ones referenced throughout the book.
Every tool ships with a stress test.
Chapter 17's five-scenario shock deck is the same methodology used to pressure-test institutional portfolios, written for a portfolio of any size.
Who This Book Is For

Capable people, underserved by what already exists.

Not a beginner's guide, and not a hobbyist's stock-tip newsletter, a book for readers who are good at something already and know they're missing a piece.

Reader 1

The Self-Directed Investor

Already manages their own portfolio. Already has an AI model open in another tab, but no idea how to point it at an actual decision. Appendix B's eight prompt templates and the Chapter 17 stress test exist for this reader specifically.

Reader 2

The Capable Professional

Excellent in a demanding field (engineering, medicine, the military, tech) who never got formal financial education and knows it. Smart, busy, and ready for a book that respects that instead of starting at square one.

Reader 3

The Advisor Building AI Fluency

Not shopping for stock ideas: shopping for a defensible, structured way to bring AI-assisted research into a practice or a team without cutting corners on rigor. The six-model comparison and the sourced citations are built for this reader.

Reader 4

The AI-Hype Skeptic

Already tried the shallow "AI + investing" content (thin sourcing, a vendor pitch dressed up as insight) and bounced off it. Not AI-skeptical. Unproven-claims-skeptical. The citation discipline is the whole reason this reader stays.

Who it's not for: anyone wanting AI to simply tell them what to buy. Principle III of The Discipline ("AI is a partner, not a prophet") rules that reader out on purpose.

Start with Chapter 1, or start with the free tools.

Either way, you'll be running the same framework by the end of the week.

Get the Book Try the Free Tools →