Fermi Estimation

Use when the user needs a defensible quantitative estimate of something with no data at hand, and wants a reasoned order-of-magnitude answer rather than a blind guess or a refusal. Runs Fermi estimation: defines the target quantity precisely, decomposes it in parallel into a chain of sub-factors each estimable to within an order of magnitude, estimates each factor as a range with its basis, multiplies the chain and propagates the uncertainty, then cross-checks the result against independent decompositions and known bounds and names the factor that dominates the error. Triggers include "Fermi estimate", "back of the envelope", "order of magnitude", "ballpark", "how many / how much / how big roughly", "estimate the market size", "we don't have data but need a number".

l4ci Updated 6 repo stars

File contents

l4ci/latticework commit 80cbf8720e

Frequently asked questions

npx get-skill add l4ci/fermi-estimation