Agentic AI Reference Architecture

Tools & Integration · Software component

Tool Call Dispatcher

Software componentTools & IntegrationOrchestration & ToolsVariation point (abstract)arc:ToolCallDispatcher

An abstract execution component that schedules multiple model-proposed tool calls, either in dependency order or concurrently, and collects their results for the agent.

Responsibility. Determines the execution order and concurrency of a set of tool calls requested by the model.

Also known as: Tool execution strategy, Multi-tool execution

is invoked byinvokesinvokesis specialized byis specialized byis specialized byAgent Controller: is invoked byAgent ControllerTool Executor: invokesTool ExecutorExternal Service API: invokesExternal Service APISequential Tool Dispatcher: is specialized bySequential Tool DispatcherParallel Tool Dispatcher: is specialized byParallel Tool DispatcherAsynchronous Tool Dispatcher: is specialized byAsynchronous Tool Dispat…
Direct neighbourhood (hover for relationship types)

Variants

VariantWhen to choose
Asynchronous Tool DispatcherChoose when profiling shows GPU idle gaps during I/O-bound tool calls in multi-step agent loops (e.g., ReAct) under concurrent load.
Parallel Tool DispatcherChoose for independent data fetching from multiple sources where latency matters and tools share no mutable state and have no coordination requirements.
Sequential Tool DispatcherChoose when tools have dependencies (Step N+1 needs Step N's output), when guaranteed execution ordering is needed, when tools modify shared data, or when orchestration logic depends on seeing results sequentially.

Relationships

invokes dependency

is invoked by dependency

Design guidance

Classification

Patterns
Tool chainingParallel function calling
Technologies
LangChain AgentExecutorLangGraph
Quality attributes
Performance efficiency (ISO/IEC 25010)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Cascading tool failures

Sources

  1. Ch2.6: T. Nguyen, "Tool Integration and Function Calling," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.6. ISBN: 9798244538229.
  2. Ch7.3: T. Nguyen, "NeMo Agent Toolkit Profiling," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.3. ISBN: 9798244538229.