Loading content
Modular, hierarchical workflow agents for the Vertex AI ecosystem. Architecture: Hierarchical workflow architecture, primarily for Vertex AI. Best suited: Enterprise workflow agents on Google Cloud / Vertex AI. Watch out: Most mature inside the Google ecosystem; less portable elsewhere.
Use this profile to understand the building block briefly, place it in the model, and switch to the 360° assessment when needed.
Technical building block: can be automated, integrated, or operated.
Concrete cog in the system that works inside larger relationships.
Google ADK is a modular framework for agentic workflows that helps teams build, control, and deploy production-oriented AI agents in the Vertex AI ecosystem.
Google ADK is Google's open-source agent development framework. The official documentation presents it as code-first and traces its evolution toward ADK 2.0 with graph workflows, collaborative agents, model routing, and deployment on Google Cloud. Its practical center of gravity is repeatable, controllable agent execution inside Vertex AI; portability decreases outside that stack.
ADK works like an orchestration layer for agents. An agent combines configuration, model calls, tools, and context. Simple tasks run as a fixed sequence; more complex ones run as a graph with branches, routing, and defined handoff points. Human approval can be inserted at clear checkpoints, while the runtime ties together execution, observability, and deployment.
A decision module dispatches requests to specialized targets such as agents, prompts, or tools.
Steps run in a fixed order, and each step uses the output of the previous one.
Humans review or confirm results and decisions at defined points.
Workflows are modeled as directed graphs with nodes, edges, and branches.
ADK fits when you need repeatable agent flows, tool use, controlled handoffs, and a clear path to Google Cloud operations. It is especially useful for teams close to Vertex AI that want deployment, observability, and governance in one stack. It is less attractive when strong platform independence or a deliberately neutral stack matters more.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.