Mastering Multi-Agent Orchestration using ADK
Cloud - Edmonton
Suvaditya Mukherjee
ML GDE | Magnopus | USC
@halcyonrayes
Cloud - Edmonton
$whoami
Google Developer Expert - Machine Learning & Cloud
ML Engineer @ Magnopus
Master’s - Computer Science (Artificial Intelligence) @ USC
Agents
Chapter One
The proliferation of agents and why you need them
Generative AI vs. Agentic AI: Moving from static text generation to dynamic, goal-oriented execution.
The Core Loop: Perceive (Observation) -> Think (Reasoning) -> Act (Execution).
Autonomy: The ability to iteratively plan and execute sub-tasks without continuous human prompting.
Moving beyond Chat
Interactivity
Systems need to interact with external environments (databases, APIs, local file systems).
Complexity
Real-world workflows require multi-step reasoning that exceeds single-prompt capabilities.
Resilience
Agents can self-correct, catch exceptions, and retry execution paths when initial attempts fail.
Why Agents?
Chapter Two
Are they any different?
LLMs v/s Agents
Large Language Models
Stateless prediction engines mapping inputs to probability distributions.
Agents
Stateful systems that use the LLM as a reasoning engine to drive external actions.
Engine v/s Vehicle
Architectural Differences
LLMs generally are standalone, whereas Agents will have other non-LLM tools or software components attached to it.
Chapter Three
One for all, all for one
Single-Agent Systems
Monolithic Agents
A single agent equipped with a massive system prompt and access to all available tools.
Use Case: Excellent for narrow, well-defined tasks (e.g., a simple code generation assistant).
Implementation: Often relies heavily on the ReAct (Reason + Act) prompting framework.
Context Window Pollution: Keeping track of tool outputs, past reasoning, and system instructions degrades performance over time.
Persona Conflict: Forcing one LLM to act as a planner, executor, and critic simultaneously leads to poor task execution.
Error Cascading: A single hallucination early in the loop can derail the entire execution pipeline.
Context Collapse
Chapter Four
Why have one when you can have multiple?
Multi-Agent Systems
Decomposing complex workflows into specialized, narrow-scope agents.
Divide and Conquer
Each agent is executed in a predetermined order. This is the simplest form of a multi-agent pattern.
Multi-Agent Patterns
Sequential
Multi-Agent Patterns
Multiple agents can run parallel to each other. They can be independent to each other.
Parallel
Multi-Agent Patterns
Agents are triggered at intermediate steps based on results of previous steps. Can also trigger multiple agents.
Decision
Multi-Agent Patterns
Agents run a loop until a certain condition is met, at which point it exits the loop.
Loop
The Agentic Stack
Google ADK
Chapter Five
A toolset for 0-to-100 builders
Edges
The routing logic that determines the flow of execution.
Nodes
The individual agents or functional blocks in your graph.
State
The shared memory object passed between nodes.
Agents Galore
Multi-Agent Systems as State Machines
Each node receives the current state, performs its task, mutates the state, and passes it along.
Predictability as a feature
Ensures predictable execution paths and simplifies debugging complex Python workflows.
State-driven Orchestration
5 Core ADK Skills
01
Scaffolding
Initializes projects via agent-starter-pack with 50+ validated templates.
02
Dev Guide
Development lifecycle, coding guidelines, and operational rules.
03
Cheatsheet
API quick reference: patterns, tool definitions, and state management.
04
Evaluation
Testing, benchmarking, and quality validation using adk eval.
05
Deployment
Packaging, production rollout, and observability on Agent Engine.
Chapter Six
Giving your agents access to the world
ADK Tools
Familiar API surfaces
Binding Python functions (e.g., executing a PyTorch script, querying a local database, or running shell commands) to the agent.
Hands for the Agent
Tools are the interfaces between the LLMs’ reasoning and external execution.
Easy to integrate across apps
ADK handles the JSON schema generation and argument parsing automatically.
Connecting Agents to Reality
Source: ADK Documentation
Manage issues, search pages, and update team content
Connect with BigQuery to retrieve data and perform analysis
Atlassian
BigQuery
Store and retrieve information using semantic vector search
ChromaDB
Access models, datasets, research papers, and AI tools
Generate speech, localize voices, and create audio content
Hugging Face
Cartesia
Manage payments, send invoices, and handle subscriptions
PayPal
And many more!
Chapter Seven
Create to understand
Build with ADK
Chapter Eight
Where to go from here
Advanced Patterns
Human-in-the-Loop (HITL)
Designing graphs that pause execution before taking irreversible actions (e.g., merging code to main, executing a transaction).
The system waits for explicit human validation or modification of the state before proceeding via a defined edge.
Parallelization and Optimization
Running independent agent branches concurrently (e.g., dispatching three different "Research" agents simultaneously).
Merging the parallel states back together via a "Reducer" node, optimizing latency and token usage in heavy workflows.
Thank You!
Merci beaucoup!
Cloud - Edmonton
Suvaditya Mukherjee
ML GDE | Magnopus | USC
@halcyonrayes