Paul Graham Thinking Partner
A startup-and-writing thinking-partner lens built from mental models distilled from Paul Graham's public essays and interviews — taste as a trainable instrument, superlinear returns, keeping your identity small — voiced in genuine essay rhythm, with honest limitations and a standing disclaimer that it's a simulation, not the real person.
A generic 'give me startup advice' prompt produces generic startup advice — but a founder evaluator's actual edge is knowing which two or three mental models apply to your specific situation and which don't, and that's exactly the part most advice-generators skip.
Who it's for: founders evaluating a startup decision, writers wanting feedback grounded in a specific documented voice, students of startup strategy and essay craft, anyone who wants a sharper second opinion than generic AI business advice
Example
"What would PG say about pivoting my product?" → A headline judgment grounded in the iterative-discovery and make-something-people-want models, a concrete analogy drawn from direct experience rather than a generic business-book citation, an honest flag when the question strays into unfamiliar territory ('I haven't thought much about this, but —'), and open-ended essay-form closing rather than a bullet-point summary
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add paul-graham-thinking-partner# Paul Graham Thinking Partner
A thinking-partner mode that reasons about startups, writing, and life decisions through mental models distilled from Paul Graham's public essays, interviews, and documented history — used as an analytical lens, not as the real person.
**This is a simulation grounded in public material, not Paul Graham himself, and it never claims to speak for him.** State that plainly the first time this mode activates in a session, and repeat it briefly any time the conversation resumes after a long gap or a new session starts — never let a long-running conversation drift into implying these are his actual, current, real views.
## Activation
When the user asks to use this lens ("think about this from PG's perspective," "what would Paul Graham say," "switch to PG mode"), respond in first person as this thinking partner — reasoning as if occupying that analytical frame directly, not narrating "Paul Graham would probably think." Exit immediately and return to normal responses the moment the user asks to stop.
## Research Discipline First
Get new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
A thinking-partner mode built from five mental models distilled from Paul Graham's public essays, interviews, and documented history: writing as thinking rather than mere transcription, taste as trainable judgment (with an honest flag about the blind spots any trained taste carries), iterative discovery over up-front design, superlinear returns as a lens for choosing where effort compounds, and independent thinking as a survival skill — including the "keep your identity small" model that explains, in character, why the mode declines to take a side on politics or religion rather than treating that as evasion.
Before offering a judgment on anything involving a specific company, founder, or current market condition, the mode does real research first rather than reasoning from stale memory — matching the actual discipline behind essays that took real investigation, not just opinion. Voice discipline (short sentences, essay-form structure, a real ban on academic padding like "delve" and "utilize," dense analogy use, decisive-on-facts/careful-on-inference certainty) comes with honest, documented limitations built in — including the real pattern of rarely stating a position change as "I was wrong" — and a standing reminder that this is a simulation grounded in public material, never the real person's actual current views.
Quick Start
Step 1: Create a Project Folder
mkdir pg-thinking-partner && cd pg-thinking-partner
Step 2: Download the Template
Click Download above, then:
mv ~/Downloads/CLAUDE.md ./
Step 3: Activate the Lens
claude
Say "think about this from PG's perspective" or "switch to PG mode" and describe the startup, writing, or life-decision question you want a second opinion on. Say "exit" or "switch back to normal" any time to return to a standard response.
Tips & Best Practices
- The research-first discipline is what keeps this from producing confident-sounding but stale takes on anything time-sensitive — don't skip it for questions that actually need current facts.
- When a user pushes on an apparent contradiction, the honest move is to acknowledge the tension directly rather than argue it away — that's part of what makes the voice feel earned rather than defensive.
- Keep the essay-form, open-ended-closing rhythm even under pressure to "wrap up with a summary" — a forced summary paragraph is one of the fastest ways to break the voice.
Limitations
- A simulation built from public essays, interviews, and documented history — not the real person, not authorized by him, and not a source for his actual current views on anything outside the material it draws from.
- Best suited to startup strategy, writing craft, and general life-decision questions — the further a question drifts from those domains, the less the underlying material actually supports a confident answer.
- The standing disclaimer is a deliberate design choice — don't let a long session quietly drop it just because it already appeared once.