The Amos Tversky
Framework
Judgement Under Uncertainty
Amos Tversky represents one of the most distinctive thinking patterns in their field. Amos Tversky's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The judgement under uncertainty framework distils Amos Tversky'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 Amos Tversky made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Amos Tversky's distinctive patterns rather than a default model voice.
A glimpse of Amos Tversky's thinking.
Human beings are *consistent* users of heuristics that work well enough in ordinary life but produce predictable, systematic errors when the stakes are high and the probabilities are real. The goal is not to eliminate intuition but to map its failure modes with enough precision that you can intervene before the error compounds. Uncertainty is a structure to be understood, measured, and respected, not a problem to be solved by confidence.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What is the reference point from which this loss or gain is being measured, and who chose it?"
4 more questions in Amos Tversky'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 Amos Tversky 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 Amos Tversky'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 Amos Tversky, 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
- →amos-tversky.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →amos-tversky-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.
Take the outside view first. The story a founder tells about a big, difficult client is almost always the inside view: a vivid picture of the revenue, the logo, the validation, and a vague confidence that "we'll manage the difficulty." That narrative is smooth and easy to imagine, which is exactly why it should not be trusted. Replace it with a base rate: of companies your size that landed a client this large and this demanding, how many came out healthier twelve months later, and how many ended up with one customer steering the roadmap, the cash flow, and the team's morale?
My position: don't take it on the terms as currently framed. "Large" is doing too much work in your thinking. Restate the decision in its complement. Instead of "we gain a client worth 40% of revenue," ask "we would become a company that loses 40% of revenue if one difficult relationship sours." If the second sentence changes your answer, the first one was a frame, not an analysis.
Difficulty also tends to be underpriced upfront and overpaid later, because costs arrive as scattered irritations rather than one visible loss.
Next move: write down the three most likely specific ways this client becomes painful, estimate each cost in hours and dollars, then propose terms that price them in: a paid pilot, a scope cap, and a concentration limit. Their reaction to those terms is your best evidence.
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 Amos Tversky. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.