Learn it → Apply it → Save as Skill
State the answer first, then prove it. Group your supporting reasons into a small number of non-overlapping clusters, order each cluster logically, and back every claim with evidence underneath — the structure most readers and listeners actually expect, even though most writers default to the opposite order.
The Dr. Wallace's Favorite Mental Models is designed to turn useful ways of thinking into reusable tools. Each model gives you a fast visual overview, deeper interactive learning, practical application exercises and an AI-ready Markdown skill you can save for future use.
Instead of merely reading about mental models, you can gradually build your own AI skills library: a collection of portable reasoning skills that can help ChatGPT, Claude, Grok and other AI assistants apply the mental models you value.
Most communication is built chronologically: background, method, findings, and only then — buried at the end — the point. The Pyramid Principle inverts that order. Lead with the governing thought, support it with a handful of grouped arguments, and back each argument with the underlying data.
Important: your real structure might need two arguments or five. The pyramid shape is a reminder of top-down order and grouped support — not a rule that every answer needs exactly three reasons.
The model is most useful when a reader or listener needs to reach a conclusion quickly and may stop paying attention before they reach the end of a chronological account.
The pyramid is built from the top down even though it is usually researched from the bottom up.
State the single governing thought — your recommendation, conclusion or main message — in the first sentence, not the last.
Cluster your supporting reasons into a small number of groups that are mutually exclusive and collectively exhaustive (MECE): no overlap, no gaps.
Arrange each group deductively (premise, premise, conclusion) or inductively (similar items leading to one implication) — never a loose list.
Back every argument with the facts, analysis or evidence beneath it. A reader should be able to stop reading at any level and still have a true, complete picture.
A reader skimming only the titles of a strong deck should already know the full argument. A reader skimming only the titles of a weak deck only knows the subject matter.
Open a use case to see what the model changes.
Move the request or recommendation to the first sentence. Group the context, risk and timeline underneath as three short supporting points, each with its own short evidence line.
State the recommendation on the first slide's title, not just the topic. Use the body slides to prove each supporting argument with one chart or data point apiece.
Open with the decision you are asking the group to make, then walk through the two or three reasons, each supported by what you found. Save background for questions.
Replace "First we did X, then Y, then Z" with the finding itself, then regroup the method and results as evidence for that finding rather than a timeline of activity.
Lead with the overall recommendation (hire, promote, hold), then group the evidence into two or three themes such as skill, collaboration and growth trajectory.
Ask the assistant to state its answer or recommendation in the first line, then list its reasoning as grouped, labeled support underneath — the same structure you would demand from a person.
This is an illustrative example designed to teach the method, built around the classic Situation–Complication–Question–Answer (SCQA) opening.
Expand for the origin of the framework and the honest limits of its central discipline, MECE.
Barbara Minto earned an MBA from Harvard Business School in 1963 — one of only eight women in a class of roughly 600 — and joined McKinsey & Company that year as the firm's first female MBA hire. After working in Cleveland and then London from 1966 to 1973, she left during the layoffs that followed the 1973 oil crisis and built a training business around the executive-communication techniques she had developed coaching McKinsey consultants on how to write recommendations. She published "The Pyramid Principle: Logic in Writing and Thinking" in 1985, followed by a revised and expanded edition, "The Minto Pyramid Principle: Logic in Writing, Thinking and Problem Solving," in 1996.
Minto formalized the MECE discipline — grouping ideas so they are Mutually Exclusive and Collectively Exhaustive — at McKinsey in the late 1960s as the structural engine beneath the pyramid. She has credited the underlying logic to Aristotle's work on categories rather than claiming to have invented the idea of clean, non-overlapping classification from scratch. MECE went on to become one of the most widely taught structuring heuristics in management consulting.
MECE guarantees that a set of categories does not overlap and covers the stated scope — it does not guarantee that the categories chosen are the right or most useful ones, and a technically MECE breakdown can still omit something that matters if the scope itself was drawn too narrowly. Critics also note the discipline can be overly rigid: forcing strict mutual exclusivity sometimes hides genuinely useful overlap, and some real situations call for a small amount of deliberate redundancy for clarity rather than none at all. Treat MECE as a quality check on structure, not a guarantee that the structure is substantively correct.
Writing in the order the work happened — background, then method, then finding — rather than leading with the finding and using the rest as support.
A heading like "Market Analysis" labels a subject. A heading like "the market is growing but our share is shrinking" states a finding a skimming reader can actually use.
Treating "three arguments" as a rule rather than a frequent outcome. Let the logic of the problem decide the number of groups, not a template.
Grouping reasons so that one data point could support two different arguments at once undermines the reader's confidence in the whole structure.
Switching mid-group between "because A, and because A implies B, therefore C" and "these three similar things suggest C" without signaling the shift confuses readers following the argument.
Applying a rigid answer-first structure to an exploratory update or a document meant for careful, independent reading, where it reads as presumptuous or strips out needed nuance.
you are sharing interim, unfinished findings and do not yet have a recommendation to put at the top.
the reader will study the material alone, needs full nuance and caveats, and benefits from a slower, fuller narrative than a slide headline allows.
the content is a procedure, a safety instruction or a compliance record where the actual sequence of steps is the point, not an argument.
This browser tool structures your thinking. It does not send your information anywhere or perform AI analysis.
Save as Skill converts the model into portable Markdown instructions that teach an AI when and how to apply the Pyramid Principle, what questions to ask, what evidence to seek, what mistakes to avoid and how to structure its own answers.
Save the skills you find useful and organize them into your own reusable library. The Markdown is intentionally model-neutral, so it can be used wherever an AI system accepts uploaded files, project knowledge, custom instructions or reusable text context. Platform capabilities differ, so this is a portable skill file rather than a claim of one-click installation.
No. The same answer-first, grouped-support logic repeats recursively: the top-level answer is supported by grouped arguments, and each of those arguments can itself be the "answer" to a smaller pyramid of its own supporting data one level down.
Situation–Complication–Question–Answer is Minto's recommended opening for the introduction above the pyramid: establish what the reader already agrees is true (Situation), the change or tension that creates a problem (Complication), the question that tension raises (Question), and then the governing answer that becomes the top of the pyramid (Answer).
They share the answer-first instinct, but BLUF (used widely in military and government writing) is mainly a one-line convention for where the conclusion sits. The Pyramid Principle goes further, prescribing how the supporting arguments underneath that conclusion should be grouped, ordered and backed with evidence.