🏆SFEIR is the Google Cloud EMEA Training Partner of the Year 2025🤝New partnership: Official GitLab Training🤖New training: AI-Augmented Developer
🏆SFEIR is the Google Cloud EMEA Training Partner of the Year 2025🤝New partnership: Official GitLab Training🤖New training: AI-Augmented Developer
GCP300ANTIGRAVITYCLI

Building Agents with Antigravity and Agents CLI Training

In this course, you will learn how to create enterprise agents on the Gemini Enterprise Agent Platform. You will discover why real-world business tasks require autonomous agents and how to leverage Antigravity, and the Agent CLI to transform and automate your ADK development workflow.

You will learn how to manage agents, examining how the platform splits into a control plane that defines agents and a data plane that runs them on the Managed Agents API. Through conceptual lessons and a hands-on lab building an agent from scratch, you will learn how to assemble agent components, execute resilient reason-act loops, manage persistent multi-turn state, and ensure scalability across your enterprise AI projects.

Google Cloud
✓ Official training Google CloudLevel Advanced⏱️ 0.5 day (3.5h)

What you will learn

  • Utilize Antigravity and the Agent CLI to automate and accelerate the development of enterprise-grade agents.
  • Explain how the Agent Development Kit (ADK) and Agents API simplify the creation of autonomous enterprise agents.
  • Build managed, secure, isolated agents leveraging Google infrastructure using the Agents API.
  • Interact with the Agents API to manage the control plane and with the Interactions API to work with the data plane.
  • Extend agents with mounted data, skills, tools and MCP servers.
  • Run agents using background interactions, a streamed reason-act loop, resilient typed results, and multi-turn state.
  • Apply the security model and operational practices that secure an agent for production.

Prerequisites

  • Familiarity with Google Cloud Platform

Target audience

  • Software Developers & Engineers, Platform & DevOps Engineers, Technical Architects / Solutions Architects, Automation Specialists

Training Program

9 modules to master the fundamentals

Objectives
  • Explain the developer's shift from manual implementation to high-level orchestration by outlining the phases of design intent, delegation, and verification within the Vibe Coding model
  • Construct a formal agent specification using Gherkin syntax to explicitly define correct behaviors, failure states, and edge cases prior to writing any prompts
  • Evaluate an agent's generated output directly against a stable specification to ensure precision and prevent compounding errors during the interactive build process
Topics covered
  • →The Vibe Coding Model
  • →Spec-Driven Development and Gherkin Syntax
  • →Architectural Prompting and Output Verification
Objectives
  • Differentiate between Agent Studio, the Managed Agents API, and Antigravity to select the most appropriate agent-building solution based on specific development needs and infrastructure control requirements
  • Utilize the Artifacts panel within the Antigravity 2.0 Desktop app to inspect, run, and reference generated outputs
  • Operate the Antigravity CLI to execute agentic coding tasks and terminal commands, maintaining a unified workspace and context across both command-line and graphical interfaces.
Topics covered
  • →The Antigravity Ecosystem
  • →Antigravity 2.0 Desktop and Artifact Management
  • →Antigravity CLI and Enterprise Setup
Objectives
  • Explain how the Agents CLI bridges the context gap by mounting domain-specific skills that align a coding agent's output with the current ADK 2.0 surface
  • Apply the seven core Agents CLI skills to effectively navigate distinct phases of the agent development loop
  • Manage the development session by explicitly loading relevant skills to maintain a focused context
Topics covered
  • →Bridging the Agent Context Gap
  • →The Seven Core Lifecycle Skills
  • →Context Management and Version Control
Objectives
  • Construct a foundational agent project structure rapidly by executing the agents-cli scaffold create command to bypass interactive configuration dialogs
  • Implement additional workspace capabilities, such as new deployment targets and package dependencies, utilizing command-line scaffolding tools
  • Design a customized workspace declaratively by providing Antigravity with a clear natural-language intent of the agent's goals
Topics covered
  • →Rapid Project Generation
  • →Package Management and Deployment Enhancements
  • →Intent-Driven Scaffolding
Objectives
  • Outline the end-to-end ADK development lifecycle and identify the specific purpose of key files and directories generated during project scaffolding
  • Execute local code validation and interactive testing workflows utilizing the agents-cli lint and playground
  • Design the primary agent module to correctly bind models, instructions, and tools within a standardized application wrapper.
Topics covered
  • →The Development Lifecycle and Project Structure
  • →Core Agent Configuration
  • →Local Code Validation and Testing
Objectives
  • Execute the evaluation workflow using the Agents CLI to generate execution traces and systematically grade agent performance using LLM-as-judge metrics
  • Formulate comprehensive evaluation datasets and metric configurations that rigorously test agent behaviors
  • Analyze evaluation scores to identify common failure modes, iteratively refining the agent's logic or the metric descriptions
Topics covered
  • →Evaluation Structure and Workflow
  • →Evaluation Configurations and Datasets
  • →Evaluation Best Practices and Iteration
Objectives
  • Differentiate between code-first and infrastructure-first deployment strategies to select the appropriate foundation for enterprise agent applications
  • Configure a secure execution environment by defining network allowlists and external data mounts to strictly control the agent's data access and network reach
  • Execute agent operations by defining durable agent resources on the control plane and launching ephemeral interactions on the data plane
Topics covered
  • →Infrastructure-First vs. Code-First Approaches
  • →The Sandbox Environment and Security Boundaries
  • →Control Plane vs. Data Plane Operations
Activities

Lab: Build, Run, and Harden Agents with Managed Agents API

Objectives
  • Differentiate between executable tools and instructional skills to effectively equip an autonomous agent for complex, real-world tasks
  • Explain the Model Context Protocol (MCP) architecture and how it leverages standardized communication to decouple agent logic from external tool execution
  • Assemble an agent configuration on the control plane by integrating built-in tools, MCP server connections, mounted data, and published skills
Topics covered
  • →Tools vs. Skills
  • →Model Context Protocol (MCP) Architecture
  • →Agent Assembly and Skill Publication
Objectives
  • Implement robust production execution patterns by utilizing asynchronous long-running tasks, SSE streaming, and fallback polling mechanisms to handle connection drops
  • Analyze agent execution traces and granular token telemetry to monitor operational costs and identify inefficient reasoning loops
  • Manage context persistence across multiple conversation turns by explicitly defining interaction and environment scopes, ensuring operations remain within strict data security boundaries
Topics covered
  • →Execution and Reconnection Patterns
  • →The ReAct Loop and Cost Telemetry
  • →State Management and Data Security

Related Trainings

Google Cloud

Build Agents with the Agent Development Kit

In this course, you'll learn to use the Agent Development Kit (ADK) to build systems where multiple AI agents collaborate on complex tasks. You'll start with the ADK agent model: how ADK represents agents, tools, and runners, and how a single agent is configured and run. You'll then make tools the model can call, persist session state across agents, and instrument the execution lifecycle with callbacks and plugins. Next, you'll orchestrate multiple agents using ADK's template workflow agents and graph-based workflows, and ground them in enterprise data through multi-source retrieval and MCP integrations. Finally, you'll deploy a multi-agent system to Agent Runtime as a managed service and register and share it through Gemini Enterprise so users across an organization can reach it.

1 d
Advanced
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

Antigravity for Enterprise Series

This comprehensive 6-module series explores Google Antigravity, an agent-first development platform designed to consolidate fragmented developer workflows into a unified server-side harness. Learners will journey from foundational architecture and multi-team scale to advanced enterprise guardrails, responsible vibe coding for non-technical teams, and deterministic compliance reporting for regulated industries. Note for Spark Sessions: Participants can choose any 3 modules to make up a 3-hour Spark session, or complete two 3-hour sessions (all 6 modules) to cover the entire series.

1 d
Intermediate
View all trainings →

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.
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

Software developers and engineers, platform and DevOps engineers, technical and solutions architects, and automation specialists.
Familiarity with Google Cloud Platform.
You will use Antigravity and the Agent CLI to automate and accelerate the development of enterprise-grade agents, build managed, secure and isolated agents with the Agents API, extend agents with mounted data, skills, tools and MCP servers, and apply the security model and operational practices that secure an agent for production.
Nine modules: vibe coding and spec-driven development, Antigravity, the Agents CLI, project scaffolding, the ADK project structure, evaluation, the Managed Agents API, tools and skills including the Model Context Protocol (MCP), and running and operating the agent.
The course lasts 3.5 hours and is delivered in an instructor-led format by SFEIR Institute. It combines conceptual lessons with a hands-on lab: "Build, Run, and Harden Agents with Managed Agents API".
Yes. This is an official Google Cloud course delivered by SFEIR Institute, a certified Google Cloud Training Partner.

395€ excl. VAT

per learner

ReserveQuote