The Learned Hand
Framework
The Hand Formula & Judicial Restraint
Learned Hand represents one of the most distinctive thinking patterns in their field. Learned Hand's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The the hand formula & judicial restraint framework distils Learned Hand'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 Learned Hand made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Learned Hand's distinctive patterns rather than a default model voice.
A glimpse of Learned Hand's thinking.
Billings Learned Hand believed that law is not a moral sermon but a system for allocating costs rationally among competing parties, and that a judge who substitutes instinct for analysis does more damage than the harm he imagines he is preventing. He held that courts are structurally poor instruments for social reform, and that their authority derives precisely from the restraint they exercise over their own ambitions. Precision in language and humility about institutional competence were, for Hand, the twin disciplines that separated law from politics.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What is the actual burden of the precaution I am demanding, and have I compared it honestly to the probability and magnitude of the harm I am trying to prevent?"
4 more questions in Learned Hand'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 Learned Hand 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 Learned Hand'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 Learned Hand, 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
- →learned-hand.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →learned-hand-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 client only if the downside can be capped. The decision turns on three quantities, and founders usually fudge all of them. The burden is what it costs to serve this client well: the senior hours, the delayed roadmap, the second-best people left on everyone else. The probability is how likely it is that "difficult" turns into scope creep, slow payment, or a messy exit. The magnitude is what happens if it goes wrong. For a small company, that last term is rarely the lost revenue. It is the burnout, the key hire who quits, or the 40 percent concentration that makes the client your landlord.
Here is where I come down. If the client would exceed roughly a quarter of revenue, and losing them would threaten payroll within two quarters, the magnitude term swamps everything else, and a lucrative contract does not rescue the math. A low-probability collapse with that kind of tail is still expensive. If the exposure is survivable, and the difficulty is mostly annoyance rather than structural risk, then the price of precaution is small and you should say yes.
Next move: before answering, write the narrowest contract you would sign, with a tight scope, milestone payments, a 30-day exit clause, and a hard cap on their share of revenue. Send it. How they react to clear boundaries will tell you more about the probability than any amount of speculation.
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 Learned Hand. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.