The Ferran Adrià
Framework
Experimentation & Deconstruction
Ferran Adrià built a reputation not on one dish but on a distinctive approach to ingredients, technique, and taste. Ferran Adrià's culinary philosophy is captured in this framework, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The experimentation & deconstruction framework distils Ferran Adrià'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 Ferran Adrià made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Ferran Adrià's distinctive patterns rather than a default model voice.
A glimpse of Ferran Adrià's thinking.
Every established technique is just one answer to a question nobody remembers asking. True innovation comes from isolating the essential function of something, then rebuilding it from scratch using completely different methods. The goal isn't improvement—it's transformation into something unrecognizable yet fundamentally better.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What would this look like if I had to achieve the same result using completely different physics?
4 more questions in Ferran Adrià'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 Ferran Adrià 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 Ferran Adrià'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 Ferran Adrià, 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
- →ferran-adria.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →ferran-adria-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.
Don't decide yet. Take the client apart first.
Right now you're staring at one fused object: "big difficult client." Founders treat it as a yes/no gamble, but it's actually several separate things welded together: revenue, reference value, operational strain, and whatever makes them difficult. Each one behaves differently once you isolate it.
So deconstruct the difficulty itself. Is it scope that keeps shifting? Slow payment? A demanding contact who rewrites everything at 11 p.m.? Each of those is a different physics problem. Shifting scope can be engineered away with a fixed-price phase and a change-order mechanism. Slow payment can be solved with deposits. A volatile person might be a ceiling on the relationship, not a fixable defect. Most founders skip this step and lump all three under "difficult," then either flinch or leap blindly.
My position: lean toward yes, but only in a shape you've deliberately rebuilt. Revenue that large teaches you things a comfortable client never will, and the hard parts are information, not just cost.
Next move this week: write down every specific friction you expect, then propose a paid pilot of 60 to 90 days with the terms redesigned around those frictions. Watch what happens when you hand them the new structure. If they refuse reasonable terms, you've learned the difficulty is structural and you walk away cheaply. If they accept, you've bought a real experiment instead of a bet.
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 Ferran Adrià. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.