Tool or Technology
TT0159

Google Antigravity in Action

Orchestrate AI Agents & Build Software Smarter

Antigravity
Duration
16 Hours
Level
Intermediate
Delivery
Instructor-Led
Format
Capability Training

Programme Objectives

  • Develop functional proficiency in using Google Antigravity to plan, execute, review, and manage complex AI-assisted software-development tasks.
  • Use agent-driven workflows for repository understanding, feature development, debugging, testing, research, browser interaction, and implementation verification.
  • Orchestrate multiple specialized agents and subagents while maintaining controlled project context, permissions, tools, and isolated Git workspaces.
  • Build reusable agent capabilities using Custom Agents, Skills, Rules, Workflows, MCP integrations, and execution hooks.
  • Apply human review, artifact-based verification, permissions, security controls, testing, and governance practices to reliable agentic-development workflows.

Technology covered

Google Antigravity 2.0Antigravity CLIAntigravity IDE ExtensionsAI AgentsProjectsTasksArtifactsImplementation PlansTerminal ToolsBrowser ToolsGit WorktreesSubagentsCustom AgentsSkillsMCP ServersRules & WorkflowsHooksScheduled Tasks

Who should attend

  • Software Developers
  • Software Engineers
  • Frontend Developers
  • Backend Developers
  • Full-Stack Developers
  • DevOps & Platform Engineers
  • QA & Test Automation Engineers
  • Application Support Engineers
  • AI Application Developers
  • Technical Leads
  • Solution Architects
  • Engineering & Digital Transformation Teams

Prerequisites & Participant Readiness

  • Working knowledge of at least one programming language
  • Familiarity with source-code repositories and application-development concepts
  • Basic knowledge of Git and version-control workflows
  • Familiarity with command-line or terminal usage is recommended
  • Basic understanding of debugging and software-testing practices
  • Familiarity with Generative AI and prompting is beneficial
  • Basic understanding of APIs and developer tools is helpful for MCP activities
  • Appropriate Google Antigravity access and an approved development repository should be available for hands-on exercises
  • No completion of shorter Antigravity programmes is required

TOC Modules

Concepts
  • Understanding Google Antigravity as an agent-first development and knowledge-work platform
  • Understanding Antigravity 2.0, CLI, IDE, and IDE Extension surfaces
  • Understanding AI agents, tools, tasks, artifacts, knowledge, and reasoning
  • Understanding synchronous versus asynchronous agent execution
  • Differentiating conversational coding from autonomous agent-driven execution
Practical activities
  • Navigating the Antigravity 2.0 environment
  • Starting an Agent conversation for a development requirement
  • Asking an Agent to inspect and explain an existing project
  • Comparing manual, conversational, and agent-driven development approaches

Scenarios

Product Requirement to Verified Software Feature

Product Requirement → Project Context → Implementation Plan → Main Agent → Development Subagent → Test Subagent → Git Worktrees → Browser Verification → Code Diff → Human Review → Integration

Participants use Antigravity to turn a realistic product requirement into a tested feature while coordinating planning, parallel development, automated verification, and human approval.

Production Defect to Multi-Agent Resolution

Production Issue → Logs & Repository Analysis → Root-Cause Agent → Implementation Agent → Test Agent → Terminal Validation → Browser Verification → Artifact Review → Approved Resolution

Participants coordinate multiple specialized Agents to investigate a software issue, identify its root cause, implement a controlled correction, verify the fix, and prepare the change for safe integration.

Related programmes

Continue with programmes from the same capability area.

Take the next step

Ready to make this programme work for your team?

Customise modules, duration and business scenarios for your team.

Instructor-ledVirtualHybrid

Designed around your roles, tools and real workflows.