GCP300AOPS

Agent Operations on Google Cloud Training

In this course, you will use your knowledge of developing agents using the Agent Development Kit to operationalize agents using Agent Operations (AgentOps) on Google Cloud.

After reviewing the challenges of managing production agents and deployment targets, you will build CI/CD pipelines for agents and leverage a governed artifact management ecosystem. You will implement evaluation systems using the GenAI Evaluation Service and ADK and apply observability solutions for debugging with Cloud Logging and Cloud Trace. You will integrate security guardrails against agent-specific threats using Model Armor and Sensitive Data Protection. Finally, you will apply FinOps strategies to understand and manage agent costs.

Google Cloud
✓ Official training Google CloudLevel Advanced⏱️ 1 day (7h)

What you will learn

  • Optimize efficiency and consistency of agent deployments with CI/CD
  • Ensure agent quality by implementing and operating evaluation systems
  • Leverage observability solutions for debugging and continuous improvement
  • Establish guardrails against agent-specific threats
  • Build and use a governed artifact management ecosystem
  • Apply FinOps strategies to understand and manage agent costs

Prerequisites

  • Completion of "Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine" (GCP300ADKAE) or equivalent knowledge
  • Python
  • Prompt engineering
  • Agent Development Kit

Target audience

  • Application Developers, DevOps Engineers, ML Engineers, Anyone deploying agentic applications on Google Cloud

Training Program

6 modules to master the fundamentals

Objectives
  • Navigate the challenges of managing production agents
  • Define the core principles of AgentOps
  • Architect agent operations on Google Cloud
Topics covered
  • →Challenges of managing production agents
  • →Core principles of AgentOps
  • →AgentOps on Google Cloud
Objectives
  • Leverage CI/CD tooling and patterns for agentic solutions on Google Cloud
  • Select the deployment target for agents on Google Cloud
  • Build a complete CI/CD pipeline for an agent
Topics covered
  • →CI/CD review
  • →Agentic deployment targets
  • →CI/CD tooling and patterns on Google Cloud
  • →Cloud Build automation
Activities

Lab: CI/CD for Agents on Google Cloud

Objectives
  • Identify challenges addressed by observability
  • Instrument an ADK agent with structured logs
  • Enable OpenTelemetry tracing on Agent Engine and Cloud Run
  • Leverage BigQuery and Looker Studio for visualization
Topics covered
  • →Observability review
  • →Logging with agent callback logging
  • →Logging and tracing with OpenTelemetry
Activities

Lab: Instrument and Debug Agents with Cloud Logging and Cloud Trace

Objectives
  • Perform validation on model responses
  • Evaluate agent behavior, tool usage, and trajectory correctness
  • Create and manage evalsets using ADK Web UI
  • Evaluate evalsets with ADK UI, CLI, or code
  • Use the Vertex AI Generative AI Evaluation Service
Topics covered
  • →Testing generative AI model responses
  • →Evaluating model responses
Activities

Lab: Evaluating Agents with ADK

Objectives
  • Secure model inputs and outputs with Model Armor
  • Protect sensitive data using Sensitive Data Protection with Model Armor
  • Secure the connection between a user and an agent
Topics covered
  • →Model and context security
  • →Agent access
Activities

Lab: Enhancing AI Security with Model Armor and Sensitive Data Protection

Objectives
  • Identify the primary cost drivers of AI agents
  • Reduce token and model costs
  • Architect cost-efficient agent systems
  • Implement a measurable AI FinOps loop on Google Cloud
Topics covered
  • →Primary cost drivers for AI Agents
  • →Cost-efficient agentic systems
  • →FinOps on Google Cloud

Related Trainings

Google Cloud

Deploy multi-agent systems with Agent Development Kit and Agent Engine

In this course, you'll learn to use the Google Agent Development Kit to build complex, multi-agent systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You'll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.

1 d
Advanced
Google Cloud

Agentic AI Governance Essentials

This course provides learners with the essential skills to govern the design, deployment, and scaling of autonomous, Agentic AI systems. It focuses on enabling rapid innovation and accelerating speed-to-market while managing the unique risks presented by AI systems that can make decisions without constant human input. The course is structured around the practical application of the four-phase Agentic AI Governance Maturity Roadmap (Establish, Implement, Scale, Accelerate). It uses a blend of presentations, detailed case-study scenarios (Cymbal Health, Cymbal Insurance, etc.), group discussions, a tabletop exercise, and quizzes.

0.5 d
Intermediate

Upcoming sessions

No date suits you?

We regularly organize new sessions. Contact us to find out about upcoming dates or to schedule a session at a date of your choice.

Register for a custom date

Quality Process

SFEIR Institute's commitment: an excellence approach to ensure the quality and success of all our training programs. Learn more about our quality approach

Teaching Methods Used
  • Lectures / Theoretical Slides — Presentation of concepts using visual aids (PowerPoint, PDF).
  • Technical Demonstration (Demos) — The instructor performs a task or procedure while students observe.
  • Guided Labs — Guided practical exercises on software, hardware, or technical environments.
  • Quiz / MCQ — Quick knowledge check (paper-based or digital via tools like Kahoot/Klaxoon).
Evaluation and Monitoring System

The achievement of training objectives is evaluated at multiple levels to ensure quality:

  • Continuous Knowledge Assessment : Verification of knowledge throughout the training via participatory methods (quizzes, practical exercises, case studies) under instructor supervision.
  • Progress Measurement : Comparative self-assessment system including an initial diagnostic to determine the starting level, followed by a final evaluation to validate skills development.
  • Quality Evaluation : End-of-session satisfaction questionnaire to measure the relevance and effectiveness of the training as perceived by participants.

Frequently Asked Questions

You should have completed "Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine" (GCP300ADKAE) or have equivalent knowledge. You also need Python experience, prompt engineering skills, and familiarity with the Agent Development Kit.
It is designed for Application Developers, DevOps Engineers, ML Engineers, and anyone deploying agentic applications on Google Cloud who needs to operationalize and manage production agents.
The course includes 4 hands-on labs: CI/CD for Agents on Google Cloud, Instrument and Debug Agents with Cloud Logging and Cloud Trace, Evaluating Agents with ADK, and Enhancing AI Security with Model Armor and Sensitive Data Protection.
The training covers Vertex AI, Vertex AI Agent Engine, Vertex AI Agents, Cloud Build, Cloud Logging, Cloud Trace, BigQuery, Looker Studio, Model Armor, and Sensitive Data Protection.
AgentOps (Agent Operations) is the discipline of operationalizing AI agents in production. It covers CI/CD pipelines, observability, evaluation, security guardrails, artifact management, and cost optimization for agentic systems.
Our training organizations SFEIR SAS and SFEIR-Est are Qualiopi certified for training activities, which allows you to request funding from your OPCO. Funding approval remains at your OPCO's discretion. Contact us for a quote.

790€ excl. VAT

per learner