An enterprise is designing an automated customer support solution using Python and the Agent Development Kit (ADK). The design must satisfy the following architectural requirements: Deploy the agent on a fully managed runtime with minimal operational overhead and built-in short-term session memory management. Ground model responses with internal enterprise documentation to eliminate hallucinations and provide accurate information. Execute actions against existing enterprise backend workflows using a least-privilege security model tied directly to the agent's runtime lifecycle. Which architecture should the cloud architect recommend?

Deploy the agent to Vertex AI Agent Engine with agent identity enabled, equip the agent with the Vertex AI Search tool for document grounding, and connect backend workflows using Application Integration tools.: What Vertex AI Agent Engine and Agent Builder Are Vertex AI Agent Builder and Vertex AI Agent Engine provide a comprehensive, fully managed suite for building, deploying, and governing agentic AI systems. Agent Engine acts as an opinionated, serverless runtime built to execute Python agent frameworks (such as ADK) with managed lifecycle features, built-in memory management, and native integration with enterprise tools. How It Meets the Requirements Fully Managed Runtime & Memory: Vertex AI Agent Engine provides a fully managed Python runtime with automatic instance scaling and built-in Sessions for short-term memory, eliminating the need to deploy and manage custom state databases or underlying compute infrastructure. Enterprise Grounding: Equipping the agent with the Vertex AI Search tool allows the model to perform retrieval-augmented generation (RAG) directly against indexed internal unstructured enterprise data, ensuring outputs are accurate and grounded. Least-Privilege Security: Enabling Agent Identity (AGENT_IDENTITY) auto-provisions a SPIFFE-based, read-only system-attested principal tied directly to the agent's lifecycle. This identity is granted specific IAM permissions to invoke Application Integration tools to trigger enterprise backend workflows safely without shared service accounts or static credentials. Key Advantages and Capabilities Managed Runtime: Automatic scaling powered by Cloud Run infrastructure under the hood, with zero server management. Integrated Grounding: Native tool support for Vertex AI Search and RAG Engine to connect enterprise data stores. Native Governance: Built-in agent identity for granular IAM allow and deny policies. Observability: Automatic telemetry with Cloud Logging, Cloud Monitoring, and Cloud Trace via OpenTelemetry. Why This Is Optimal This architecture leverages native Google Cloud agentic services to achieve full enterprise integration, managed memory, and strict identity governance with minimal operational complexity.

StudyCerts

Professional Cloud Architect

Intrigued by the art of cloud architecture? Discover how to design, develop, and manage robust, secure, scalable, and dynamic solutions on Google Cloud as you prepare for the Professional Cloud Architect exam!

Intermediate

Prepare and test your skills

Track Readiness

Set Exam Goal

Intermediate

Prepare and test your skills

Track Readiness

Set Exam Goal

Vertex Agent Builder Engine Grounding Tools

Section: Google Cloud AI and machine learning solutions (e.g., Gemini LLMs, Agent Builder, Model Garden, Gemini models, and AI Hypercomputer)

An enterprise is designing an automated customer support solution using Python and the Agent Development Kit (ADK). The design must satisfy the following architectural requirements:

Deploy the agent on a fully managed runtime with minimal operational overhead and built-in short-term session memory management.
Ground model responses with internal enterprise documentation to eliminate hallucinations and provide accurate information.
Execute actions against existing enterprise backend workflows using a least-privilege security model tied directly to the agent's runtime lifecycle.

Which architecture should the cloud architect recommend?

Build the agent in Vertex AI Agent Designer, store conversational history in Vertex AI Feature Store, and embed static API keys directly in the agent instructions to call backend APIs.

Deploy the agent on Cloud Run with Cloud Memorystore for session caching, and authenticate backend API tools using a single shared user-managed service account with Project Owner permissions.

Deploy the agent as a containerized service on Google Kubernetes Engine (GKE), deploy a Redis cluster for session memory, and use Grounding with Google Search for enterprise data retrieval.

Deploy the agent to Vertex AI Agent Engine with agent identity enabled, equip the agent with the Vertex AI Search tool for document grounding, and connect backend workflows using Application Integration tools.

Professional Cloud Architect

Intermediate

Prepare and test your skills

Track Readiness

Set Exam Goal

Intermediate

Prepare and test your skills

Track Readiness

Set Exam Goal

Vertex Agent Builder Engine Grounding Tools

Section: Google Cloud AI and machine learning solutions (e.g., Gemini LLMs, Agent Builder, Model Garden, Gemini models, and AI Hypercomputer)

An enterprise is designing an automated customer support solution using Python and the Agent Development Kit (ADK). The design must satisfy the following architectural requirements:

Deploy the agent on a fully managed runtime with minimal operational overhead and built-in short-term session memory management.
Ground model responses with internal enterprise documentation to eliminate hallucinations and provide accurate information.
Execute actions against existing enterprise backend workflows using a least-privilege security model tied directly to the agent's runtime lifecycle.

Which architecture should the cloud architect recommend?

Build the agent in Vertex AI Agent Designer, store conversational history in Vertex AI Feature Store, and embed static API keys directly in the agent instructions to call backend APIs.

Deploy the agent on Cloud Run with Cloud Memorystore for session caching, and authenticate backend API tools using a single shared user-managed service account with Project Owner permissions.

Deploy the agent as a containerized service on Google Kubernetes Engine (GKE), deploy a Redis cluster for session memory, and use Grounding with Google Search for enterprise data retrieval.

Explanations

What Vertex AI Agent Engine and Agent Builder Are

Vertex AI Agent Builder and Vertex AI Agent Engine provide a comprehensive, fully managed suite for building, deploying, and governing agentic AI systems. Agent Engine acts as an opinionated, serverless runtime built to execute Python agent frameworks (such as ADK) with managed lifecycle features, built-in memory management, and native integration with enterprise tools.

How It Meets the Requirements

Fully Managed Runtime & Memory: Vertex AI Agent Engine provides a fully managed Python runtime with automatic instance scaling and built-in Sessions for short-term memory, eliminating the need to deploy and manage custom state databases or underlying compute infrastructure.
Enterprise Grounding: Equipping the agent with the Vertex AI Search tool allows the model to perform retrieval-augmented generation (RAG) directly against indexed internal unstructured enterprise data, ensuring outputs are accurate and grounded.
Least-Privilege Security: Enabling Agent Identity (AGENT_IDENTITY) auto-provisions a SPIFFE-based, read-only system-attested principal tied directly to the agent's lifecycle. This identity is granted specific IAM permissions to invoke Application Integration tools to trigger enterprise backend workflows safely without shared service accounts or static credentials.

Key Advantages and Capabilities

Managed Runtime: Automatic scaling powered by Cloud Run infrastructure under the hood, with zero server management.
Integrated Grounding: Native tool support for Vertex AI Search and RAG Engine to connect enterprise data stores.
Native Governance: Built-in agent identity for granular IAM allow and deny policies.
Observability: Automatic telemetry with Cloud Logging, Cloud Monitoring, and Cloud Trace via OpenTelemetry.

Why This Is Optimal

This architecture leverages native Google Cloud agentic services to achieve full enterprise integration, managed memory, and strict identity governance with minimal operational complexity.

View source documentation

Professional Cloud Architect

Vertex Agent Builder Engine Grounding Tools

Professional Cloud Architect

Vertex Agent Builder Engine Grounding Tools

What Vertex AI Agent Engine and Agent Builder Are

How It Meets the Requirements

Key Advantages and Capabilities

Why This Is Optimal

Related questions