refactor(findings): split ALL-FINDINGS.md into per-experiment files

Break the monolithic 3249-line findings file into 29 individual files,
one per experiment. Each file is named YYYY-MM-DD-NN-slug.md for easy
chronological sorting and discovery.

No content changes — purely structural reorganization.

findings/2026-04-26-07-emerging-role-assignments-pattern-not.md

@@ -0,0 +1,17 @@
+# Finding 7: Emerging role assignments (pattern, not conclusion)
+
+**Date:** 2026-04-26 (one day of intensive work — treat as hypothesis)
+
+- Opus (via Claude Code): complex generation needing deep project context.
+  Rich context: CLAUDE.md, full codebase access, design docs. Broad mandate.
+- Sonnet: parallel volume work (5 subagents drafting simultaneously).
+  Rich context per section, constrained output scope.
+- GPT-5: independent analytical review. Rich context (diff + files + issue).
+  Best when task is bounded and explicit.
+- GPT-4.1 Mini: focused narrow analysis (bias detection). Minimal context,
+  precise question. Cheap and fast.
+- **Takeaway:** The role assignment matters, but so does the context shape.
+  Opus gets broad context + broad mandate. Sonnet gets broad context +
+  narrow scope. GPT-5 gets rich context + explicit task. GPT-4.1 Mini gets
+  minimal context + laser question. We haven't tested swapping these
+  combinations — that's where the real learning will come from.