Team Design
How MARIA OS designs, composes, and governs multi-agent teams — from role architecture to graduated autonomy.
Why Team Design Matters
In autonomous systems, the team is the smallest unit of governance.
How you compose it determines what it can decide — and what it must escalate.
Judgment Cannot Be Parallelized
Execution scales linearly. Judgment does not. A team of 10 agents can process 10x the work, but the quality of a single decision depends on how responsibility is structured — not how many actors participate.
Composition Determines Capability
The mix of human, agent, and hybrid members defines the team's operational envelope. All-human teams preserve nuance but limit throughput. Agent-heavy teams maximize speed but require stronger governance rails.
Roles Before Actors
Design the responsibility structure first, then assign actors. A role defines what decisions can be made, what evidence must be produced, and who bears accountability. The actor — human or agent — is a runtime binding.
Trust Is Earned, Not Configured
Teams evolve through maturity stages. An agent earns expanded autonomy by demonstrating consistent, auditable performance within governed boundaries. Configuration sets the ceiling; behavior sets the floor.
Team design is not staffing. It is responsibility architecture.
Watch a Team
Evolve.
From all-human to agent-heavy — 4 tiers of team composition. Each tier activates more of the 8 standard agent roles as governance infrastructure matures.
Standard oversight
Eight standard roles. Four maturity tiers. Chief MARIA orchestrates them all.
8 Standard Roles x K1-K8 Skills
Every team draws from the same 8 standard agent roles. Each role maps to the K1-K8 skill model — the operational foundation shared across all universes.
Plan generation, dependency resolution, execution ordering
Design decisions, structure definition, interface governance
Implementation, optimization, deterministic execution
Test design, reproducibility verification, quality scoring
Boundary verification, permission checks, stop trigger management
Evidence collection, log organization, audit data generation
Health monitoring, fault detection, self-healing guidance
Safety policy enforcement, risk classification, defense design
K1-K8 Skill Model
Collect
Gather raw data and signals
Curate
Organize and prioritize data
Infer
Derive insights and predictions
Verify
Validate against ground truth
Plan
Sequence actions and allocate resources
Execute
Perform actions deterministically
Audit
Review and score quality
Govern
Enforce constraints and policies
Skills are fetched from the Skill Store or dynamically generated. See /architecture/skills for the full skill lifecycle.
Inter-Zone Coordination
Every cross-zone interaction passes through a governance gate. Chief MARIA orchestrates routing via the MARIA Coordinate System.
Hub-Spoke with Governance Gates
4 zones coordinated through Chief MARIA. Dashed lines = gate-governed paths.
5 Gate Types
Hub-Spoke
Chief MARIA routes tasks through governance gates to specialized zones. Low inter-zone dependency.
Best for: Independent work streams with shared quality standards.
Coordinate: G1.U1.P*.Z*.A*
Mesh
Direct peer-to-peer coordination between zones. Requires conflict resolution via Gatekeeper agents.
Best for: Tightly coupled domains where zones share state.
Coordinate: G1.U1.P1.Z*↔Z*
Cascade
Linear handoff: Zone A output becomes Zone B input. Each gate validates the handoff evidence bundle.
Best for: Sequential workflows like pipeline processing.
Coordinate: G1.U1.P1.Z1→Z2→Z3
Graduated Autonomy
Teams evolve through four maturity stages. Each stage unlocks greater autonomy by building the governance infrastructure required to support it.
Manual Oversight
Low risk, low throughput
Team Pattern
All-human teams, agents as tools only
Autonomy Level
None — agents execute explicit instructions
Governance
Human approval on every action
Assisted Execution
Moderate risk, 3-5x throughput
Team Pattern
Hybrid leads with human oversight
Autonomy Level
Tactical — agents propose, humans approve
Governance
Gate on decisions above threshold
Governed Autonomy
Managed risk, 10-20x throughput
Team Pattern
Agent-led with human quality gates
Autonomy Level
Operational — agents decide within bounds
Governance
Fail-closed gates + exception handling
Self-Governing Teams
Systematic risk management, 50x+ throughput
Team Pattern
Agent-heavy with governance infrastructure
Autonomy Level
Strategic — agents propose direction changes
Governance
Meta-governance: agents monitor governance health
More governance enables more autonomy. The ceiling rises with the floor.
Who Owns the Decision?
Responsibility flows upward through the MARIA Coordinate System: G.U.P.Z.A
Enterprise boundary — ultimate authority
Owns: Organizational values, ethics file, irreducible constraints
G1 = Bonginkan Corp
Business unit scope — strategic direction
Owns: Cross-planet policy, resource allocation, value alignment
G1.U2 = Sales Operations
Functional domain — operational governance
Owns: Domain-specific rules, team composition, workflow design
G1.U2.P3 = Contract Review
Operational unit — execution boundary
Owns: Task execution quality, SLA compliance, evidence production
G1.U2.P3.Z1 = Auto-Review Zone
Individual worker — task-level decisions
Owns: Action outcomes, execution traces within assigned parameters
G1.U2.P3.Z1.A5 = Contract Verifier
Core Principles
Responsibility Cannot Be Delegated
An agent executes on behalf of a human, but the human retains accountability. Delegation creates an execution chain, not a responsibility transfer.
Every Decision Has an Owner
No decision exists without a responsible party. If no owner is identifiable, the decision is escalated until one is found.
Evidence Is Mandatory
Every responsibility transition produces an evidence record. The absence of evidence is itself a governance violation.
Escalation Is Not Failure
Escalation is the system working correctly. A team that never escalates is either trivially scoped or dangerously overconfident.
Responsibility is architecture. If you cannot trace it, it does not exist.
How Teams Are Formed
9 steps — the same deterministic sequence used by the Universe Builder. Each step produces auditable output.
Goal
Define decision scope and business objective
Out: Decision boundary map
Scope
Map required roles and escalation paths
Team
Bind actors to roles (human/agent/hybrid)
Skills
Assign K1-K8 skill categories per role
Build
Configure zone graph and coordination topology
Gates
Set 5 quality gate types and thresholds
Validate
Run constraint checks and conflict detection
Test
Execute golden tests and reproducibility checks
Deploy
Team is live with telemetry and monitoring
Anti-Patterns
Ghost Accountability
No traceable owner for a decision class. Common when hybrid roles lack clear scope.
Premature Autonomy
Agent-heavy composition without governance infrastructure. Speed up, failures undetected.
Governance Theater
Gates exist but always pass. Evidence produced but never reviewed.
Escalation Avoidance
Teams suppress escalations to appear capable. Looks clean until systemic failure.
Same protocol. Same gates. Same evidence requirements. Every team is a governed universe.