The Sherman Kent
Framework
Words of Estimative Probability
Sherman Kent won (or analysed) wars by thinking about force, terrain, and timing in ways their opponents did not. Sherman Kent's strategic thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The words of estimative probability framework distils Sherman Kent's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Sherman Kent made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Sherman Kent's distinctive patterns rather than a default model voice.
A glimpse of Sherman Kent's thinking.
Kent believed that intelligence analysis is a discipline, not an art form, and that its outputs must be held to the same standards of rigor as any empirical science. He argued that vague estimative language, words like "might," "could," or "possibly," without attached probability ranges, is not humility but negligence, because it allows the reader to project whatever confidence level they prefer onto the analyst's judgment. The analyst's job is to reduce the decision-maker's uncertainty by a measurable amount, and every word in an estimate either contributes to that reduction or undermines it.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What is the probability range you are actually asserting, and which word in our lexicon maps to that range?"
4 more questions in Sherman Kent's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Sherman Kent actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Sherman Kent's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Sherman Kent, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →sherman-kent.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →sherman-kent-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
My judgment: probably take it, but only on terms that cap the downside. I'd put it at roughly 60 percent that this client is net positive for the company over twelve months, and I'd rather say that number out loud than call it "a calculated risk," because that phrase lets you and your cofounder each hear a different bet.
The reasoning starts with separating what you know from what you were told. The client's size is a fact. The claim that they're "difficult" is probably a mix: one source may be a former vendor who burned out, another may be your own gut from two tense calls. Those are not equal evidence. A former vendor describing a payment dispute is far stronger than a sense that the buyer was curt in a meeting. Weigh them differently before they merge into one vague unease.
Then name the outcome that would prove you wrong. Here it is concrete: if the client refuses a scoped statement of work, or pushes back on payment terms before signing, the probability of a good outcome drops below 30 percent, and you walk. Difficult clients reveal themselves in the contract phase.
Next move: this week, ask a former vendor of theirs two direct questions: how late did they pay, and how many times did scope change after kickoff. Write the answers down before you decide. Those two numbers will tell you more than any amount of deliberating.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Sherman Kent. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.