A Primer of Practical AI Concepts. A decision-first guide featuring 22 key mathematical and statistical Quick Cases for students preparing for AI careers.

This collection serves as a quick-reference guide rather than a full course or textbook. Each Quick Case provides rapid conceptual orientation—enabling users to recognize when a mathematical idea applies, identify the relevant question, and select the appropriate next tool. Detailed derivations, proofs, and extensive practice are reserved for dedicated coursework; here, the focus is on recognition and fluency, not mastery of underlying techniques. The examples are intentionally simple, designed to make reasoning clear in one pass, rather than capturing the complexity of real data. This distinction is deliberate: a reference sheet's purpose is to foster pattern recognition for handling messier, real-world analysis, not to replicate that messiness. The 22 concepts included are deliberately selected, not exhaustive, reflecting common situations AI developers and related professionals face—such as skewed data, miscalibrated probabilities, unstable models, and correlated features—and requiring quick recognition of relevant reasoning tools. The goal is broad situational awareness rather than deep technical mastery. The material is geared toward Public Health students likely to design, oversee, or evaluate AI-based systems—like triage algorithms, resource distribution, or risk scores—rather than clinical practitioners. The target skill is applied AI literacy: knowing what questions to ask models or vendors and understanding common failure points. It does not aim to train students for medical practice.