Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For React state that keeps drifting, make the first test produce evidence you can compare, not just something that looks complete.

Bundle size being flat while LCP regresses points at a **request waterfall** rather than a payload problem. In the app router the usual cause is an `await` sitting in a layout. Layouts render before the pages nested inside them. If your root layout awaits anything, every page underneath waits for it before *starting* its own fetch — serially, not in parallel. Check your `layout.tsx` files first, outermost in. You're looking for any `await` that isn't wrapped in a Suspense boundary.

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For React state that keeps drifting, I would start with these checks: - Reproduce the failure before changing code - Keep the patch smaller than the diagnosis - Write the rollback before deployment If you share real material, remove anything private first and replace bracketed fields with concrete details.