board-meeting

---
name: board-meeting
description: Use when running structured C-suite deliberation on a strategic question. 6-phase protocol: context, isolated independent analysis, critic review, synthesis, founder decision, extraction.
category: C-Level Advisory
version: 1.0.0
tools: []
---

# Board Meeting Protocol

Structured multi-agent deliberation that prevents groupthink, captures minority views, and produces clean, actionable decisions.

## The 6-phase protocol

### Phase 1: Context gathering
1. Load company context (from memory)
2. Load Layer 2 approved decisions (Layer 2 ONLY—never raw transcripts)
3. Reset session state—no bleed from previous conversations
4. Present agenda + activated roles; wait for founder confirmation

**Chief of Staff selects relevant roles based on topic.** Not all 14 every time. Standard routing: Market expansion (CEO, CMO, CFO, CRO, COO) | Product direction (CEO, CPO, CTO, CMO) | Hiring/org (CEO, CHRO, CFO, COO, VPE) | Pricing (CMO, CFO, CRO, CPO) | Technology (CTO, CPO, CFO, CISO) | Contracts/term sheets (GC, CEO, CFO) | Data strategy/AI (CDO, CAIO, GC, CISO).

### Phase 2: Independent contributions (ISOLATED)

**No cross-pollination. Each agent runs before seeing others' outputs.** Order: Research → CMO → CFO → CEO → CTO → COO → CHRO → CRO → CISO → CPO → GC → CDO → CAIO → CCO → VPE (activated roles only).

**Contribution format (max 5 key points, self-verified):**
- [Finding] — [VERIFIED/ASSUMED] — 🟢/🟡/🔴
- Recommendation: [clear position]
- Confidence: High / Medium / Low
- Source: [where data came from]
- What would change my mind: [specific condition]

### Phase 3: Critic analysis

Executive Mentor receives ALL Phase 2 outputs simultaneously. Adversarial role:
- Where did agents agree too easily? (suspicious consensus = red flag)
- What assumptions are shared but unvalidated?
- Who is missing from the room? (customer voice? front-line ops)
- What risk has nobody mentioned?
- Which agent operated outside their domain?

### Phase 4: Synthesis

Chief of Staff delivers:
- Decision required (one sentence)
- Perspectives (one line per contributing role)
- Where they agree / where they disagree
- Critic's view (the uncomfortable truth)
- Recommended decision + action items (owners, deadlines)
- Options if founder disagrees

### Phase 5: Founder review

**Full stop. Wait for the founder.**

Options: ✅ Approve | ✏️ Modify | ❌ Reject | ❓ Ask follow-up

Rules: User corrections OVERRIDE agent proposals. No pushback. 30-min inactivity = auto-close as "pending review".

### Phase 6: Decision extraction

After founder approval:
- Write full transcript → `decisions/raw/YYYY-MM-DD-<slug>.md`
- Write approved decision record → `decisions/approved/YYYY-MM-DD-<slug>.md`
- Append to index → `decisions/approved/decisions.md`
- Mark rejected proposals `[DO_NOT_RESURFACE]`

## Memory structure

Two-layer decision memory:
- Layer 1: Full transcripts (never auto-loaded)
- Layer 2: Founder-approved records ONLY (Phase 1 loads these)

This prevents hallucinated consensus.

## Failure-mode quick reference

| Failure | Fix |
|---------|-----|
| Groupthink (all agree) | Re-run Phase 2 isolated; force "strongest argument against" |
| Analysis paralysis | Cap at 5 points; force recommendation even with Low confidence |
| Bikeshedding | Log as async action item; return to main agenda |
| Role bleed | Critic flags; exclude from synthesis |