The Jony Ive
Framework
Reduction, Material Integrity & Detail
Jony Ive believed that form must answer to constraints: material, site, brief, budget. Jony Ive's design philosophy captures the specific questions they asked before drawing a single line, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The reduction, material integrity & detail framework distils Jony Ive'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 Jony Ive made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Jony Ive's distinctive patterns rather than a default model voice.
A glimpse of Jony Ive's thinking.
Design is not just what something looks like—design is how it works. Every element must earn its place through function, and every material must express its authentic nature. The most profound designs appear inevitable, as if they could not exist any other way.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would this look like if we started from nothing?"
4 more questions in Jony Ive'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 Jony Ive 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 Jony Ive'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 Jony Ive, 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
- →jony-ive.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →jony-ive-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 take it, not as described. A large, difficult client is a bundle of seams. Every special request, every exception to how you normally work, every escalation call is a joint where your company stops being one thing and becomes several things held together by your best people's goodwill. The revenue looks like strength. Usually it is the opposite: it pulls your team toward the client's shape and away from your own.
Ask what this client would remove from your company if it vanished tomorrow. If the answer is "a third of our revenue and nothing we'd miss doing," you are not buying a customer, you are renting out your attention at a premium. The difficulty is rarely the problem on its own. The problem is that it forces you to build things you would never build otherwise, and those things stay in the product long after the contract ends.
Here is the test I would apply: can you say in one sentence why this work belongs in your company? If the sentence is "because the invoice is large," the answer is no. If it is "because they need exactly what we are best at, and they are hard because the problem is hard," then take it.
Next move: this week, write the three conditions under which you would say yes: scope fixed, one decision-maker, no custom work outside your core offering. Send them to the client. Their reaction will tell you whether you are looking at a demanding partner or a very expensive distraction.
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 Jony Ive. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.