Assign exactly one agent as accountable for each decision — consulted agents advise, but only one has final authority
When designing RACI-style accountability for cognitive agents, assign exactly one agent as 'accountable' (final decision authority) for each contested decision or resource, allowing other agents to be consulted or informed but not to hold veto power.
Why This Is a Rule
The RACI framework (Responsible, Accountable, Consulted, Informed) solves a fundamental organizational problem: when multiple parties have input on a decision, who makes the final call? Without a single accountable party, decisions either stall (everyone waits for someone else to decide) or fragment (multiple parties make contradictory partial decisions).
Applied to personal cognitive agents, the same problem manifests as internal conflict. Your "health agent" says eat the salad. Your "social agent" says join colleagues for pizza. Your "productivity agent" says skip lunch and keep working. Without a single accountable agent for the "what to eat at lunch" decision, you experience paralysis or default to whichever agent shouts loudest in the moment.
Assigning exactly one agent as accountable — not shared accountability, not committee decision — resolves the conflict architecturally. "Health agent is accountable for food decisions; social and productivity agents are consulted." The health agent hears input from social and productivity but makes the final call. No veto power for consulted agents means no deadlocks.
When This Fires
- When Define non-overlapping agent scopes — scope collisions are architecture problems, not willpower failures (non-overlapping scopes) can't fully eliminate agent overlap for a specific decision
- When the same decision triggers input from multiple agents with different preferences
- When designing the priority hierarchy (Resolve inter-agent conflicts with documented priority hierarchies — case-by-case deliberation defeats the purpose of automation) for contested decisions
- When internal conflict repeatedly arises around the same decision type
Common Failure Mode
Shared accountability: "Both my health agent and social agent get a vote on food decisions." Shared accountability is no accountability — it produces the same deliberation-at-decision-time that agents were designed to eliminate. One agent must own the decision. Others can provide input (consulted) or be notified (informed), but the accountable agent decides.
The Protocol
(1) For each decision type that triggers multiple agents, designate one agent as Accountable: this agent has final authority. (2) Designate other relevant agents as Consulted (provide input before the decision) or Informed (notified after the decision). (3) The accountable agent considers consulted agents' input but is not required to follow it. (4) Document the RACI assignment for each contested decision type. (5) When a contested decision arises, the accountability assignment resolves it without real-time deliberation: the accountable agent's recommendation wins. (6) Review assignments quarterly — the right accountable agent for food decisions at one life stage may not be the right one at another.