The Adam Grant
Framework
Original Thinking & Rethinking
Adam Grant built systems for compounding progress that outperformed more talented peers who relied on motivation. Adam Grant's approach to identity, habit, and output, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The original thinking & rethinking framework distils Adam Grant'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 Adam Grant made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Adam Grant's distinctive patterns rather than a default model voice.
A glimpse of Adam Grant's thinking.
Most people fail to think originally not because they lack creativity, but because they're trapped by false consensus and premature cognitive commitment. The highest performers actively cultivate doubt about their own ideas while creating psychological safety for others to challenge them. Authority comes not from being right, but from being willing to be wrong in service of finding better answers.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What evidence would change my mind about this?"
4 more questions in Adam Grant'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 Adam Grant 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 Adam Grant'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 Adam Grant, 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
- →adam-grant.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →adam-grant-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 lean: don't sign yet, but don't walk away either. The thing to distrust here is how good the deal feels. A large client lights up every founder instinct at once: revenue, credibility, proof you've arrived. When a decision is that emotionally one-sided, the first job is to build the strongest case against your own position and see whether it survives.
So argue the opposite. What if the difficulty isn't a cost of the deal but the deal itself? Large, demanding clients tend to bend a young company toward their needs: custom work, slow payment, a roadmap that quietly becomes theirs. The risk is rarely that you fail the client. It's that you succeed at the wrong business.
Look at it from your own team's side too. Your best people will absorb the friction first. If the two or three who would actually carry this account are lukewarm, that's evidence you shouldn't wave away because the revenue number is loud.
Then test the assumption underneath everything: that the difficulty is fixed. Much of it is negotiable before signing and miserable to renegotiate after. Scope limits, payment terms, a defined change process, a pilot with an exit.
Next move this week: ask your two most skeptical advisors, people who will tell you the truth, to name how this goes wrong in a year. Then take their answers to the client as contract terms. A client worth having will negotiate. If they refuse every guardrail, you've learned what the relationship will be.
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 Adam Grant. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.