diff --git a/.planning/phases/23-brainstormer-flow/23-VALIDATION.md b/.planning/phases/23-brainstormer-flow/23-VALIDATION.md
new file mode 100644
index 00000000..d7ab6730
--- /dev/null
+++ b/.planning/phases/23-brainstormer-flow/23-VALIDATION.md
@@ -0,0 +1,76 @@
+---
+phase: 23
+slug: brainstormer-flow
+status: draft
+nyquist_compliant: false
+wave_0_complete: false
+created: 2026-04-01
+---
+
+# Phase 23 — Validation Strategy
+
+> Per-phase validation contract for feedback sampling during execution.
+
+---
+
+## Test Infrastructure
+
+| Property | Value |
+|----------|-------|
+| **Framework** | vitest ^3.0.5 |
+| **Quick run command** | `pnpm --filter @paperclipai/ui vitest run --reporter=verbose` |
+| **Full suite command** | `pnpm vitest run` |
+| **Estimated runtime** | ~20 seconds |
+
+---
+
+## Sampling Rate
+
+- **After every task commit:** Run relevant test file(s) per task verify command
+- **After every plan wave:** Run `pnpm vitest run`
+- **Before `/gsd:verify-work`:** Full suite must be green
+- **Max feedback latency:** 20 seconds
+
+---
+
+## Per-Task Verification Map
+
+| Task ID | Plan | Wave | Requirement | Test Type | Automated Command | File Exists | Status |
+|---------|------|------|-------------|-----------|-------------------|-------------|--------|
+| 23-00-01 | 00 | 0 | (scaffolds) | stub | `pnpm vitest run` | Created in W0 | pending |
+| 23-01-01 | 01 | 1 | AGENT-01, AGENT-02 | unit | vitest | Wave 0 | pending |
+| 23-02-01 | 02 | 1 | CHAT-09, AGENT-03 | unit | vitest | Wave 0 | pending |
+| 23-03-01 | 03 | 2 | AGENT-05, AGENT-06 | unit | vitest | Wave 0 | pending |
+| 23-04-01 | 04 | 3 | AGENT-07 | unit+manual | vitest + human verify | Wave 0 | pending |
+
+*Status: pending / green / red / flaky*
+
+---
+
+## Wave 0 Requirements
+
+- [ ] Test stubs for brainstormer-specific components and hooks
+- [ ] DB migration for message_type column
+
+---
+
+## Manual-Only Verifications
+
+| Behavior | Requirement | Why Manual | Test Instructions |
+|----------|-------------|------------|-------------------|
+| Structured questioning flow | AGENT-01 | Requires LLM interaction | Start brainstormer conversation, verify structured questions appear |
+| Spec card renders as structured card | AGENT-03 | Visual rendering | Send spec message, verify card layout |
+| Task creation via handoff | AGENT-06 | Integration with issue API | Approve spec, verify tasks appear in dashboard |
+
+---
+
+## Validation Sign-Off
+
+- [ ] All tasks have `<automated>` verify or Wave 0 dependencies
+- [ ] Sampling continuity
+- [ ] Wave 0 covers all MISSING references
+- [ ] No watch-mode flags
+- [ ] Feedback latency < 20s
+- [ ] `nyquist_compliant: true` set in frontmatter
+
+**Approval:** pending