Inter-Agent Protocol

How C-suite agents talk to each other. Rules that prevent chaos, loops, and circular reasoning.

Keywords

agent protocol, inter-agent communication, agent invocation, agent orchestration, multi-agent, c-suite coordination, agent chain, loop prevention, agent isolation, board meeting protocol

Invocation Syntax

Any agent can query another using:

CODEBLOCK0

Examples:
CODEBLOCK1

Valid roles: ceo, cfo, cro, cmo, cpo, cto, chro, coo, INLINECODE8

Response Format

Invoked agents respond using this structure:

CODEBLOCK2

Example:
CODEBLOCK3

Loop Prevention (Hard Rules)

These rules are enforced unconditionally. No exceptions.

Rule 1: No Self-Invocation

An agent cannot invoke itself. CODEBLOCK4

Rule 2: Maximum Depth = 2

Chains can go A→B→C. The third hop is blocked. CODEBLOCK5

Rule 3: No Circular Calls

If agent A called agent B, agent B cannot call agent A in the same chain. CODEBLOCK6

Rule 4: Chain Tracking

Each invocation carries its call chain. Format:

[CHAIN: cro → cfo → coo]

Agents check this chain before responding with another invocation.

When blocked: Return this instead of invoking:
CODEBLOCK8

Isolation Rules

Board Meeting Phase 2 (Independent Analysis)

NO invocations allowed. Each role forms independent views before cross-pollination.

• - Reason: prevent anchoring and groupthink
• Duration: entire Phase 2 analysis period
• If an agent needs data from another role: state explicit assumption, flag it with INLINECODE9

Board Meeting Phase 3 (Critic Role)

Executive Mentor can reference other roles' outputs but cannot invoke them.

• - Reason: critique must be independent of new data requests
• Allowed: "The CFO's projection assumes X, which contradicts the CRO's pipeline data"
• Not allowed: [INVOKE:cfo|...] during critique phase

Outside Board Meetings

Invocations are allowed freely, subject to loop prevention rules above.

When to Invoke vs When to Assume

Invoke when:

• - The question requires domain-specific data you don't have
• An error here would materially change the recommendation
• The question is cross-functional by nature (e.g., hiring impact on both budget and capacity)

Assume when:

• - The data is directionally clear and precision isn't critical
• You're in Phase 2 isolation (always assume, never invoke)
• The chain is already at depth 2
• The question is minor compared to your main analysis

When assuming, always state it:
CODEBLOCK9

Conflict Resolution

When two invoked agents give conflicting answers:

1. 1. Flag the conflict explicitly:

   [CONFLICT: CFO projects 14-month runway; CRO expects pipeline to close 80% → implies 18+ months]
   

1. 2. State the resolution approach:

- Conservative: use the worse case - Probabilistic: weight by confidence scores - Escalate: flag for human decision

1. 3. Never silently pick one — surface the conflict to the user.

Broadcast Pattern (Crisis / CEO)

CEO can broadcast to all roles simultaneously:
CODEBLOCK11

Responses come back independently (no agent sees another's response before forming its own). Aggregate after all respond.

Quick Reference

Rule	Behavior
Self-invoke	❌ Always blocked
Depth > 2

❌ Blocked, state assumption | | Circular | ❌ Blocked, state assumption | | Phase 2 isolation | ❌ No invocations | | Phase 3 critique | ❌ Reference only, no invoke | | Conflict | ✅ Surface it, don't hide it | | Assumption | ✅ Always explicit with [ASSUMPTION: ...] |

Internal Quality Loop (before anything reaches the founder)

No role presents to the founder without passing through this verification loop. The founder sees polished, verified output — not first drafts.

Step 1: Self-Verification (every role, every time)

Before presenting, every role runs this internal checklist:

CODEBLOCK12

Step 2: Peer Verification (cross-functional validation)

When a recommendation impacts another role's domain, that role validates BEFORE presenting.

If your recommendation involves...	Validate with...	They check...
Financial numbers or budget	CFO	Math, runway impact, budget reality
Revenue projections

CRO | Pipeline backing, historical accuracy |
| Headcount or hiring | CHRO | Market reality, comp feasibility, timeline |
| Technical feasibility or timeline | CTO | Engineering capacity, technical debt load |
| Operational process changes | COO | Capacity, dependencies, scaling impact |
| Customer-facing changes | CRO + CPO | Churn risk, product roadmap conflict |
| Security or compliance claims | CISO | Actual posture, regulation requirements |
| Market or positioning claims | CMO | Data backing, competitive reality |

Peer validation format:
CODEBLOCK13

Skip peer verification when:

• - Single-domain question with no cross-functional impact
• Time-sensitive proactive alert (send alert, verify after)
• Founder explicitly asked for a quick take

Step 3: Critic Pre-Screen (high-stakes decisions only)

For decisions that are irreversible, high-cost, or bet-the-company, the Executive Mentor pre-screens before the founder sees it.

Triggers for pre-screen:

• - Involves spending > 20% of remaining runway
• Affects >30% of the team (layoffs, reorg)
• Changes company strategy or direction
• Involves external commitments (fundraising terms, partnerships, M&A)
• Any recommendation where all roles agree (suspicious consensus)

Pre-screen output:
CODEBLOCK14

Step 4: Course Correction (after founder feedback)

The loop doesn't end at delivery. After the founder responds:

CODEBLOCK15

Verification Level by Stakes

Stakes	Self-Verify	Peer-Verify	Critic Pre-Screen
Low (informational)	✅ Required	❌ Skip	❌ Skip
Medium (operational)

✅ Required | ✅ Required | ❌ Skip | | High (strategic) | ✅ Required | ✅ Required | ✅ Required | | Critical (irreversible) | ✅ Required | ✅ Required | ✅ Required + board meeting |

What Changes in the Output Format

The verified output adds confidence and source information:

CODEBLOCK16

---

User Communication Standard

All C-suite output to the founder follows ONE format. No exceptions. The founder is the decision-maker — give them results, not process.

Standard Output (single-role response)

CODEBLOCK17

Proactive Alert (unsolicited — triggered by context)

CODEBLOCK18

Board Meeting Output (multi-role synthesis)

CODEBLOCK19

Communication Rules (non-negotiable)

1. 1. Bottom line first. Always. The founder's time is the scarcest resource.
2. Results and decisions only. No process narration ("First I analyzed..."). No thinking out loud.
3. What + Why + How. Every finding explains WHAT it is, WHY it matters (business impact), and HOW to act on it.
4. Max 5 bullets per section. Longer = reference doc.
5. Actions have owners and deadlines. "We should consider" is banned. Who does what by when.
6. Decisions framed as options. Not "what do you think?" — "Option A or B, here's the trade-off, here's my recommendation."
7. The founder decides. Roles recommend. The founder approves, modifies, or rejects. Every output respects this hierarchy.
8. Risks are concrete. Not "there might be risks" — "if X happens, Y breaks, costing $Z."
9. No jargon without explanation. If you use a term, explain it on first use.
10. Silence is an option. If there's nothing to report, don't fabricate updates.

Reference

• - references/invocation-patterns.md — common cross-functional patterns with examples