Coming soon · Book Profile
Sources of Power How People Make Decisions
An exploration of how experienced professionals make rapid, effective decisions in high-stakes, time-pressured environments by leveraging intuition, mental simulation, and other sources of power beyond formal rational analysis.
A profile of this book is on the way.
What it’s about
Challenging the conventional wisdom that sound decision-making requires a slow, analytical comparison of options, 'Sources of Power' takes you into the real world of firefighters, military commanders, and ER nurses to reveal how experts make tough calls under extreme pressure. Gary Klein introduces the groundbreaking Recognition-Primed Decision (RPD) model, showing that intuition is not a mystical gut feeling but a highly developed form of pattern recognition built from deep experience. Through dozens of gripping stories and case studies, the book demystifies expert judgment and explores the essential sources of cognitive power—including mental simulation, storytelling, and metaphor—that enable people to size up complex situations in seconds and arrive at effective solutions. It's a must-read for anyone looking to understand, trust, and cultivate their own decision-making expertise.
The through-line
- Who it’s for
- A professional, leader, or specialist who must make high-stakes decisions in complex, time-pressured environments and wants to understand and improve their own intuitive judgment and that of their team.
- The problem
- The conventional methods for decision-making—weighing pros and cons, comparing multiple options—are too slow and cumbersome for the fast-paced, uncertain situations they actually face. They feel uncertain about trusting their 'gut feelings,' worry about making mistakes under pressure, and are frustrated that their hard-won experience is often devalued by formal processes that prize abstract analysis over practical wisdom.
- The plan
- Learn the Recognition-Primed Decision (RPD) model to understand how experts really make decisions.
- Discover the primary sources of decision-making power: intuition, mental simulation, storytelling, and metaphor.
- Apply these insights to develop your expertise, train others, and build more effective teams.
- The payoff
- The reader becomes a more confident and effective decision-maker, able to trust their trained intuition and rapidly assess complex situations. · They can lead their teams with greater clarity, fostering an environment where experience is valued and developed. · They can design better training programs and systems that support, rather than hinder, expert judgment.
See our guide
Related profiles we’ve built
- Time Series Forecasting Using Foundation Models →
- Understanding Deep Learning →
- The AI Marketing Canvas: A Five-Step AI Plan for Marketers →
- Artificial Intelligence →
- Artificial Intelligence - A Very Short Introduction →
- Effective Data Science Infrastructure →
- Human + Machine →
- Big Data_ A Very Short Introduction (Very Short Introductions) →
Additional reading
- OpenAI Prompt Engineering Guide · OpenAI
Official documentation from the model provider on how to craft effective prompts, recommended by the author.
- Anthropic's Prompt Engineering Guide · Anthropic
Official guide from another major LLM provider, offering best practices for prompt design.
- dair-ai/Prompt-Engineering-Guide · DAIR.AI Community
A comprehensive, community-maintained GitHub repository covering a wide range of prompt engineering techniques.
- GPT Researcher · assafelovic
An open-source project that inspired the book's research summarization engine, recommended for further exploration of building production-grade LLM applications.
- Building Effective AI Agents · Anthropic
An article recommended by the author for a deeper understanding of the distinction between agentic workflows and autonomous agents.
- Model Context Protocol (MCP) Official Website · Anthropic and Community
The primary source for the MCP specification, tutorials, and ecosystem resources, essential for building or consuming MCP servers.
- FastMCP 2 Documentation · jlowin and community
The official documentation for the recommended Python SDK for building MCP servers, used in the book's example.
- Knowledge Graph Enhanced RAG · Tomaž Bratanič and Oskar Hane
Recommended by the author for readers interested in diving deeper into combining knowledge graphs with RAG.
- Database Management Systems · Gehrke and Ramakrishnan
Referenced in Chapter 2 as a resource for readers unfamiliar with the basics of SQL and Relational Database Management Systems (RDBMSs), which are foundational for the structured data analysis chapters.
- Survey of Hallucination in Natural Language Generation · Ji, Z., Lee, N., Frieske, R., et al.
Cited in Chapter 2 to explain the concept of 'hallucinations' in LLMs and to underscore the importance of verifying information provided by models.