── ── Startups
Do Things That Don't Scale
Paul Graham's counterintuitive rule: early on, the unscalable is exactly what you should do. Startups don't take off by themselves — founders recruit users manually, deliver an over-the-top experience by hand, and learn things automation would hide. Worrying about scale too early is a form of avoidance; the manual phase is where you earn insight and love that later become…
Run Do Things That Don't Scale on a real problem
Bring something you're actually deciding — free, in the browser.
How it works
1. Recruit the first users by hand — go to them individually; don't wait for a funnel. Gate: "it won't scale" used to avoid direct outreach = you're hiding from the work that matters now. 2. Deliver a delightfully unscalable experience — concierge/white-glove; do manually what the product will later automate. 3. Insert yourself into the value delivery — the friction you feel is the product spec. 4. Learn from doing, not dashboards — hand-delivery surfaces needs analytics miss. 5. Use the unscalable to create early love — a small number of users who love you beats many who are indifferent. 6. Systemize only what's validated — automate a step after manual delivery proves it matters. Gate: automating before validation locks in the wrong process (and becomes an agent doing the wrong thing well).
When to use it
- an early founder is over-automating or waiting for growth to be 'efficient'
- 'this won't scale', recruiting first users, delivering early service manually
- concierge/white-glove starts
When not to use it
the motion is already validated and the task is genuinely to scale it (then systemize/automate).
Worked example
Do Things That Don't Scale
Paul Graham's counterintuitive rule: early on, the unscalable is exactly what you should do. Startups don't take off by themselves — founders recruit users manually, deliver an over-the-top experience by hand, and learn things automation would hide. Worrying about scale too early is a form of avoidance; the manual phase is where you earn insight and love that later become…
Install this skill (free, MIT)
npx skills add deciqAI/knowledge-skillsUseful? Star the repo — stars help other builders find it.
Related mental models
Two questions decide most repeated bets: is this bet good?
A system has a feedback loop when its output circles back as input to the next cycle.
Before product-market fit, the founder must run sales personally — not because it scales, but because it's the fastest, highest-fidelity discovery loop and the only way…
Herzberg's 1959 Pittsburgh study found satisfaction and dissatisfaction are two independent axes.