Agent Dependency Graph

Data artifactOrchestrationOrchestration & Toolsarc:AgentDependencyGraph

A declared directed acyclic graph of which agents consume which other agents' outputs in a workflow, from which topologically sorted execution phases are derived.

Responsibility. Records inter-agent dependencies for validation and ordered execution.

Also known as: Explicit dependency graph, Dependency DAG, Workflow dependency declarations

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

Dependency-Ordered Executor abstract Ch8.2A

is read by dependency

is guarded by control

Dependency Cycle Validator Ch8.2A

Design guidance

MUST declare inter-agent dependencies explicitly; agents SHOULD NOT be trusted to self-coordinate on data availability under concurrent execution.

Quantitative guidance

As stated by the sources; verify before use.

Research workflow phases: [Planner, Researcher] -> [Analyst] -> [Writer, Reviewer] (Ch8.2A).

Classification

Patterns: Topological sortExecution phases
Quality attributes: Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)Maintainability (ISO/IEC 25010)
Risks mitigated: Out-of-order agent executionImplicit agent self-coordination

Sources

Ch8.2A: T. Nguyen, "Error Rates and Reliability," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.2A. ISBN: 9798244538229.
Ch10.4: T. Nguyen, "Human-in-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.4. ISBN: 9798244538229.