Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

Teams building enterprise AI on Google Cloud need to combine Gemini's long context window, native multimodal understanding and grounding capabilities with enterprise IAM, VPC Service Controls and predictable cost management. This programme covers the end-to-end Vertex AI and Gemini enterprise agent platform through hands-on practice.

Using the unified Google Gen AI SDK, processing text/image/audio/PDF inputs with Gemini, reducing cost with context caching and batch prediction, grounding on Vertex AI Search and BigQuery, function calling, code execution and the Vertex AI Evaluation Service are covered in labs. Participants produce a reusable Vertex AI reference application and production readiness checklist.

Who Should Attend?

  • Software and AI engineers building generative AI and agent applications on Google Cloud
  • Data engineers connecting BigQuery and enterprise document repositories to Gemini
  • Cloud architects responsible for AI security, networking and cost governance on GCP
  • Prerequisite: Python programming and basic familiarity with Google Cloud services

Key Takeaways

  • Build multimodal applications with the Google Gen AI SDK using structured output schemas and system instructions
  • Optimize cost and latency using Context Caching, Batch Prediction and Provisioned Throughput
  • Ground model responses on enterprise data via Vertex AI Search, custom RAG stores and Google Search grounding
  • Configure function calling, enterprise connectors and safety controls (Safety Settings, Model Armor)
  • Benchmark prompt and agent quality automatically using the Vertex AI Gen AI Evaluation Service

Curriculum

Vertex AI Platform Architecture and the Google Gen AI SDK
  • The Gemini model family (Pro, Flash, Flash-Lite), thinking budgets and the unified Google Gen AI SDK
  • Structured JSON schemas, native multimodal inputs (PDF, audio, video) and Context Caching
Enterprise Grounding: Vertex AI Search and RAG Engine
  • Building Vertex AI Search data stores over Cloud Storage, BigQuery, SharePoint and Jira
  • Vertex AI RAG Engine, semantic reranking, grounding metadata citations and document-level ACLs
Tool Calling, BigQuery Integration and the Enterprise Agent Ecosystem
  • Parallel and automatic function calling, built-in Code Execution and Apigee/Application Integration tools
  • Enterprise search and unified assistant architecture (Google Agentspace / Gemini Enterprise patterns)
Security, Model Armor and Enterprise Governance
  • Safety filters, system-instruction hardening and defending against prompt injection/PII leaks with Model Armor
  • VPC Service Controls, CMEK encryption, data residency and zero data retention configurations
Vertex AI Gen AI Evaluation Service and Operations
  • Pointwise and pairwise autoraters for groundedness, instruction following and tool-use accuracy
  • Cloud Logging/Trace observability, quota management and regression testing across model versions

Other Courses in This Category

  • Building Multi-Agent Applications with Google Agent Development Kit (ADK)

    Developing modular multi-agent systems with Google's open-source Agent Development Kit (ADK): LlmAgent, Sequential/Parallel/Loop workflow agents, MCP tools, local evaluation and deployment.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    5 modules
    View
  • Enterprise Agent Development with Google Cloud Vertex AI Agent Engine

    Learn hands-on how to design, deploy, and operate scalable, secure, and managed enterprise agent architectures using Google Cloud Vertex AI Agent Engine and Agent Development Kit (ADK).

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    4 modules
    View
  • Vertex AI Model Garden: Enterprise Model Selection and Endpoint Management

    Learn how to evaluate, customize, deploy as secure endpoints, and optimize cost-performance for Gemini, partner models, and open-weight models on Vertex AI Model Garden.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    4 modules
    View
  • Governance and Observability in Cloud-Based Agent Systems

    Learn how to design and implement end-to-end tracing, telemetry, automated evaluation, safety guardrails, and IAM-based access governance in enterprise cloud agent systems.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    4 modules
    View
  • Enterprise AI Lifecycle with the IBM watsonx Platform

    Learn how to build enterprise AI solutions, feed them with hybrid data architectures, and govern them for regulatory compliance using IBM watsonx.ai, watsonx.data, and watsonx.governance.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    4 modules
    View
  • Enterprise Digital Workers and Automation with IBM watsonx Orchestrate

    Learn hands-on how to design and manage digital assistants, custom skill catalogs, and multi-step workflow automations integrated with enterprise applications using IBM watsonx Orchestrate.

    Enterprise AI Platforms & Agent Cloud Ecosystem Corporate
    Live Course
    4 modules
    View

Get in touch