thinking-first-principles

1# First Principles
2 
3Strip assumed constraints to independently supported primitives, then rebuild. Escape analogy when convention fails or looks artificially expensive.
4 
5## When to Use
6 
7- A constraint is treated as fixed ("too expensive," "impossible," "always done this way") without independent support.
8- Convention or analogy has failed, stalled, or only yields weak incremental variants.
9- Greenfield design where industry defaults may smuggle false requirements.
10- Cost or feasibility claims rest on pricing, precedent, or authority rather than physics, math, or measured need.
11 
12## When NOT to Use
13 
14- The constraint is verified physics, hard regulation, or measured capacity → accept it and optimize within it.
15- A proven standard library, protocol, or known-good pattern already fits → use it; do not re-derive.
16- Time-critical incidents → act on the most likely cause first; reserve first-principles rebuild for post-incident redesign.
17- Incremental polish of a working system with no false-constraint signal → skip.
18 
19## Procedure
20 
211. **State the problem and claimed constraints.** List every limit treated as fixed (cost, scale, stack, process, "must use X").
222. **Classify each constraint.** Tag as `physics/math`, `regulation/contract`, `measured fact`, or `convention/analogy/authority`. Keep only the first three as binding unless evidence upgrades a convention.
23…