Decision DAG
How MARIA OS transforms organizational judgment into a Directed Acyclic Graph — the mathematical foundation for traceable, reproducible decision-making.
Not Just a Workflow. A Responsibility-Aware DAG.
Traditional workflows route tasks. MARIA OS routes decisions — each node carries ownership, evidence requirements, and gate conditions that enforce accountability at every step.
Each node carries Risk Level, Owner, and Gate Status — no implicit dependencies
Directed
Every edge has direction. Responsibility flows forward.
Acyclic
No circular dependencies. No infinite loops.
Evidence-Linked
Every connection carries verifiable evidence.
Workflows describe what happens. DAGs describe who is responsible.
Deterministic Execution Engine
Topological sorting ensures every decision node executes only after its dependencies are satisfied. No race conditions. No skipped gates.
A node becomes ready only when ALL dependencies are complete
Graph Model
V: Decision / Execution Nodes
E: Evidence-based dependencies
Topological Scheduler
O(V + E) linear time
Dependency order guaranteed
Parallel Execution
Ready nodes run concurrently
Failures trigger local re-execution
Topological sort guarantees dependency order
Ready nodes are safely parallelized
Failures trigger local re-execution only
All transitions are immutably logged
Execute in order. Never skip a gate.
Automation Without Losing Responsibility
Every decision node carries a Human/Agent allocation ratio. Higher risk nodes require more human involvement. The ratio evolves as evidence accumulates.
Responsibility allocation per node. h = human, a = agent.
Gate Policy enforces minimum human involvement by risk.
Responsibility Phase
HUMAN by default for high-risk decisions
Execution Phase
AGENT where safe and efficient
Even as total human ratio decreases, responsibility phase integrity is preserved
Risk scores drive allocation. Not intuition — equations.
Fail-Closed Governance Engine
Every critical path passes through a Gate. Gates enforce evidence requirements, approval chains, and constraint validation. When conditions are not met, the system stops — it never proceeds by default.
READY(v) ∧ PolicySatisfied(v) ∧ ApprovalSatisfied(v) ∧ EvidenceComplete(v)
Safety-1
High-risk nodes never complete without human approval
Safety-2
Nodes never execute without required evidence
Auditability
All completed nodes produce trace records
When in doubt, stop. Never proceed by default.
Formal Verification Properties
The DAG structure provides mathematical guarantees: completeness (all decisions reachable), soundness (no invalid transitions), and termination (all paths end).
V: Decision/Execution Nodes, E: Evidence-based dependency edges
No node can reach itself through any directed path
Execute only when all predecessors complete
Required evidence must be supplied by predecessors
Higher risk demands more human involvement
High-risk nodes never complete without human approval
Not aspirational. Mathematically guaranteed.
Every Decision Is Replayable
The DAG preserves the complete execution trace: inputs, outputs, gate evaluations, and timing. Any decision can be replayed with its original context.
Each transition generates a TraceEvent
Time-travel to any point via Trace
Same graph + Same trace + Same policy = Same final state
Full Causality Chain
Every state change traces back to its cause
Human Approval Bound
Approval signatures are cryptographically linked to nodes
Policy Versioning
Every decision records which policy version was active
Evidence Immutability
Evidence bundles are hash-verified and tamper-proof
If you cannot replay it, you cannot audit it.
Scope Cannot Drift
Execution boundaries are fixed at design time. New requirements create new nodes — they never mutate existing specifications. The Architect enforces structural integrity.
Action Gateway is the sole execution surface — agents have no direct write permission
Agents have no direct write permission.
All side effects pass through Action Gateway.
Even if monitoring fails, no side effect can occur without a valid ticket.
Scope drift is a governance failure. The DAG prevents it by construction.
DAG as the Universal Coordination Layer
The Decision DAG is not a visualization. It is the execution substrate — the single source of truth for what decisions exist, who owns them, and what evidence they require.
Knowledge & Memory Layer
Evidence Control Layer
risk ≥ 3 → primary source required
Responsibility-Aware Decision DAG
READY(v) ∧ EvidenceComplete(v) ∧ PolicySatisfied(v) ∧ ApprovalSatisfied(v)
Trace & Replay Engine
Replay(G, Trace, t) → Same State
Data is separated from Decisions.
Decisions are separated from Responsibility.
Responsibility is enforced by Gate.
Everything is replayable.
The DAG is not a diagram. It is the architecture.