Orchestration · Software component
Agent Message Bus
Software componentOrchestrationOrchestration & ToolsVariation point (abstract)arc:AgentMessageBus
A communication medium that transports messages or events between agents in a multi-agent system.
Responsibility. Transports inter-agent messages and events.
Also known as: Inter-agent communication channel
Variants
| Variant | When to choose |
|---|---|
| Event Broker abstract | Choose when high throughput is critical, agents run asynchronously at variable rates, resilience to temporary failures is essential, state changes must reach many subscribers, and eventual consistency is acceptable. |
| Synchronous Message Channel | Choose when immediate feedback or strong consistency is essential, interactions are brief and synchronous, the agent network is small, and explicit communication trails aid compliance. |
Relationships
is invoked by dependency
- Worker Agent abstract Ch5.9
writes dependency
emits telemetry to dynamic
receives data from dynamic
- Worker Agent abstract Ch1.3 Ch1.7B +2
sends data to dynamic
is constrained by control
is guarded by control
is evaluated by assurance
is monitored by assurance
Design guidance
- SHOULD carry correlation IDs on every message so flows can be traced across agents.
- MUST NOT assume ordered delivery unless the channel guarantees it; use sequence numbers or idempotent handlers.
- SHOULD be justified by communication ablation: if isolating agents from each other's outputs causes minimal degradation, a simpler pipeline suffices.
- SHOULD package only the minimal context the receiving agent needs, balancing omission risk against context bloat.
Quantitative guidance
As stated by the sources; verify before use.
- Selective-sharing messages of ~500-1,000 tokens instead of the sender's ~20,000-token working context (Ch5.9).
Classification
- Patterns
- Message passingEvent-driven architectureSelective context sharing: send the outcome and critical supporting facts, not the full reasoning trace
- Quality attributes
- Compatibility (ISO/IEC 25010)
- Risks mitigated
- Communication ambiguity
Sources
- Ch1.3: T. Nguyen, "Multi-Agent Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.3. ISBN: 9798244538229.
- Ch1.7B: T. Nguyen, "Relational Reasoning with Knowledge Graphs - Hybrid RAG+KG Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.7B. ISBN: 9798244538229.
- Ch3.7: T. Nguyen, "Tool Usage Auditing," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.7. ISBN: 9798244538229.
- Ch3.10: T. Nguyen, "Efficiency Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.10. ISBN: 9798244538229.
- Ch5.9: T. Nguyen, "Working Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.9. 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.
- Ch10.5: T. Nguyen, "Human-over-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.5. ISBN: 9798244538229.