WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe - Virtual Stage • Jun 30, 2026 • Session details

Building and Deploying Multi-Agent Systems with ADK and Vertex AI

Saoussen Chaabnia

Monolithic prompts lead to fragile systems and context bloat. Discover how to build and deploy deterministic, debuggable multi-agent workflows using Google ADK and Vertex AI.

Pause
Mute Enter Fullscreen
#1 about 4 min

Workshop session outcomes and companion resource repository

The core outcomes of the session and where to find the companion workshop code.

#2 about 4 min

Defining AI agents and their autonomous capabilities

How AI agents perceive their environment, reason through decisions, and execute actions.

#3 about 5 min

Agent components, memory types, and execution loops

The fundamental building blocks of an agent including short-term context and long-term memory.

#4 about 5 min

Core capabilities of the Google ADK

How ADK enables deterministic control, agent communication, and model-agnostic execution in Python.

#5 about 6 min

Building specialized multi-agent hierarchies instead of monolithic prompts

The advantages of dividing complex workflows into organized trees of specialized agents.

#6 about 5 min

Workflow agents versus LLM reasoning agents in ADK

Choosing between dynamic reasoning capabilities and deterministic coordination patterns like sequential execution.

#7 about 4 min

Implementing logic hooks with ADK execution callbacks

How to inject operational logic like logging and authentication without modifying core behavior.

#8 about 3 min

Design patterns for child sub-agents and agent tools

When to pass full session scope to a child agent versus invoking it as a discrete functional tool.

#9 about 5 min

Bridging the gap from local development to production deployments

Resolving containerization, security, networking, and observability gaps before deploying agents to the cloud.

#10 about 7 min

Deploying applications directly to Gemini Enterprise Agent Runtime

How the managed runtime automatically handles scaling, context management, and tracing for workflows.

#11 about 2 min

Packaging ADK workflows with Python deployment scripts

Writing initialization logic to push code artifacts into registries and managed cloud endpoints.

#12 about 4 min

Connecting frontends via a FastAPI proxy backend layer

Using remote runners and server-sent events to safely proxy UI requests into deployed agent endpoints.

#13 about 5 min

Architecting a multi-agent content creation pipeline application

Mapping sequential, looping, and parallel agent responsibilities into a master orchestrator application.

#14 about 11 min

Live demonstration of the deployed multi-agent content application

Executing the content generation flow and reviewing workflow traces within the runtime console.

#15 about 4 min

Examining ADK Python configurations and sample class setups

Final walkthrough of the repository structure and sample Python class setups for custom tools.

Matching moments

46 sec

Introduction to distributed multi-agent systems

Saoussen Chaabnia Saoussen Chaabnia · Europe 2026 Virtual

1:29 min

Utilizing the ADK framework for agent logic

Saoussen Chaabnia Saoussen Chaabnia · Europe 2026 Virtual

2:43 min

Deploying a web application through an AI agent workflow

Mike Mike · World Congress 2025

4:37 min

Transitioning to a hybrid human and agent workforce

Thomas Dohmke Thomas Dohmke · World Congress 2025

4:05 min

Testing the completed multi-agent database workflow

Chris Heilmann Chris Heilmann +2 · LIVE

4:56 min

Architectural setup for the agentic AI live deployment demo

Daniel Oh Daniel Oh · World Congress 2026 Europe

More from World Congress 2026 Europe - Virtual Stage

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
3 months ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

From Black Box to Glass Box : Bedrock AgentCore Observability thumbnail
21:15
3 months ago

From Black Box to Glass Box : Bedrock AgentCore Observability

Yasemin Aktürk

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence thumbnail
30:41
3 months ago

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence

Julia Grosse

Better Together: Leveraging Your Observability Tools as a SIEM thumbnail
39:06
3 months ago

Better Together: Leveraging Your Observability Tools as a SIEM

Mathias Palmersheim

ChatGPT Apps: From Chat to Checkout thumbnail
30:29
3 months ago

ChatGPT Apps: From Chat to Checkout

Aaron Koivunen

Interior Decorating (TypeScript Decorators) thumbnail
29:22
3 months ago

Interior Decorating (TypeScript Decorators)

Michael Dowden

Related videos

AI Agents & Agentic AI thumbnail
26:53
Europe 2026 Virtual • 3 months ago

AI Agents & Agentic AI

Xavier Sala Presas

Designing and Deploying Distributed Multimodal Multi-Agent Systems with Google's AI Stac thumbnail
54:24
Europe 2026 Virtual • 3 months ago

Designing and Deploying Distributed Multimodal Multi-Agent Systems with Google's AI Stac

Saoussen Chaabnia

Beyond Chatbots: How to build Agentic AI systems thumbnail
24:22
World Congress 2025 • about 1 year ago

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

On a Secret Mission: Developing AI Agents thumbnail
29:03
World Congress 2025 • about 1 year ago

On a Secret Mission: Developing AI Agents

Jörg Neumann

Building Scalable Multi-Agentic AI Systems in Java: Orchestrating Agents with Event-Driven Approach thumbnail
52:40
Europe 2026 Virtual • 3 months ago

Building Scalable Multi-Agentic AI Systems in Java: Orchestrating Agents with Event-Driven Approach

Mary Grygleski

Building Blocks for Agentic Solutions in your Enterprise thumbnail
23:39
World Congress 2025 • about 1 year ago

Building Blocks for Agentic Solutions in your Enterprise

Dennis Zielke, Rene Pajta

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.