Subagents, Scheduled Tasks, and Managed Agents in Google Antigravity

Run parallel Google Antigravity agents without losing work to git conflicts. This Google AI course teaches developers to build and coordinate multi-agent Antigravity workflows in production —...

Read More
8781  Reviews star_rate star_rate star_rate star_rate star_half
Duration 1 day
Course Code AIC-3102
Available Formats Classroom

Overview

Course Description

Run parallel Google Antigravity agents without losing work to git conflicts. This Google AI course teaches developers to build and coordinate multi-agent Antigravity workflows in production — configuring subagents, Skills, and Plugins from the CLI (agy), spawning parallel subagents with opt-in Git worktree isolation, scheduling background tasks that provision their own isolated worktree, and deploying custom agents through the Antigravity SDK as Managed Agents. Hands-on labs produce a CLI-configured subagent verified with agy inspect, a scheduled task proven collision-free across parallel runs, and an SDK-built Managed Agent deployed and polled end to end. The course is designed for software developers, AI engineers, and DevOps engineers who already use Google Antigravity for daily work.

Skills Gained

By the end of this course, participants will be able to:

  • Configure custom Antigravity subagents, Skills, and Plugins through the CLI with scoped tool access
  • Spawn dynamic and parallel subagents with opt-in Git worktree isolation, coordinated through the /agents panel
  • Schedule background tasks that provision their own isolated worktree automatically
  • Validate subagent actions with pre- and post-tool-use hooks
  • Build and deploy a custom agent with the Antigravity SDK as a Managed Agent through the Gemini API’s Interactions API

Who Can Benefit

This course is designed for:

  • Software Developers
  • AI Engineers & Architects
  • DevOps Engineers

Prerequisites

Participants should enter this course with:

Organizational Objectives

This course assists organizations to:

  • Prevent lost work from git staging collisions by enabling worktree isolation for scheduled tasks and ad hoc parallel runs
  • Accelerate concurrent development work through dynamic and parallel subagent spawning
  • Reduce the blast radius of production agents by deploying them as Managed Agents with per-invocation sandbox isolation through the Gemini API
  • Build a working knowledge of Google Antigravity’s advanced multi-agent surface in one day

Software

All attendees must have a modern web browser and an Internet connection.

Course Details

Course Details

Module 1 - Creating and Configuring Custom Subagents

By the end of this module, you will be able to create and configure Antigravity agents from the CLI (agy) outside the desktop app, define custom subagents and Skills as markdown blueprints, package them into Plugins with scoped tool access, inspect loaded configuration with agy inspect, and invoke agents headlessly for scripted and CI workflows.

  • Antigravity CLI (agy) architecture and its shared agent harness with the desktop app
  • Custom subagent definitions and Skills as markdown blueprints, staged globally or per workspace
  • Packaging Skills, subagents, hooks, and MCP servers into Plugins with a plugin.json manifest
  • Scoping tool access for a custom subagent and managing installed Plugins from the CLI
  • Inspecting loaded configuration, Skills, Plugins, and MCP servers with agy inspect
  • Headless and scripted invocation for CI pipelines
  • Hands-on Lab: Configure a custom subagent through the Antigravity CLI with scoped tool access, verify it with agy inspect, and invoke it headlessly against a sample repository.

Module 2 - Advanced Parallel Agent Patterns

By the end of this module, you will be able to spawn dynamic and parallel subagents for concurrent work, monitor and approve their actions from the /agents panel, enable Git worktree isolation for individual agent tasks, schedule background tasks that provision their own isolated worktree automatically, configure toolPermission modes and sandboxing in settings.json, and validate subagent actions with pre- and post-tool-use hooks.

  • Dynamic and parallel subagent spawning, monitored from the /agents panel
  • Reviewing and approving subagent actions with Ctrl+J and Ctrl+K
  • Opt-in Git worktree isolation for individual ad hoc agent tasks
  • Scheduling background tasks with /schedule that provision their own isolated worktree automatically
  • toolPermission modes (always-proceed, request-review, strict, proceed-in-sandbox) and the enableTerminalSandbox toggle in settings.json
  • Pre- and post-tool-use hooks defined in hooks.json for conditional validation
  • Hands-on Lab: Spawn two parallel subagents with worktree isolation enabled, schedule a background task that provisions its own isolated worktree, and verify no staging collisions occur across the concurrent runs.

Module 3 - Building and Deploying Managed Agents with the Antigravity SDK

By the end of this module, you will be able to construct a custom agent programmatically with the Antigravity SDK and deploy it as a Managed Agent running in an isolated, ephemeral Linux sandbox through the Gemini API’s Interactions API. You will run it in the foreground or as a background interaction polled by ID, define custom instructions and Skills through AGENTS.md and SKILL.md, and apply production safety practices before invoking it end to end.

  • The Antigravity SDK for defining custom agent behavior as code, deployable to your own infrastructure
  • Managed Agents in the Gemini API: a single Interactions API call for an isolated, ephemeral Linux sandbox
  • Defining custom agent instructions and Skills through AGENTS.md and SKILL.md
  • Foreground requests versus background execution polled by interaction ID
  • Persistent state and context compaction across multi-turn Managed Agent sessions
  • Production safety practices: no production credentials in the sandbox, domain allow lists, and reviewing agent output before deploying
  • Hands-on Lab: Build a custom agent with the Antigravity SDK, deploy it as a Managed Agent through the Gemini API’s Interactions API, and verify its sandboxed, isolated execution by polling the interaction to completion.

Schedule

FAQ

Does the course schedule include a Lunchbreak?

Classes typically include a 1-hour lunch break around midday. However, the exact break times and duration can vary depending on the specific class. Your instructor will provide detailed information at the start of the course.

What languages are used to deliver training?

Most courses are conducted in English, unless otherwise specified. Some courses will have the word "FRENCH" marked in red beside the scheduled date(s) indicating the language of instruction.

What does GTR stand for?

GTR stands for Guaranteed to Run; if you see a course with this status, it means this event is confirmed to run. View our GTR page to see our full list of Guaranteed to Run courses.

Does Ascendient Learning deliver group training?

Yes, we provide training for groups, individuals and private on sites. View our group training page for more information.

What does vendor-authorized training mean?

As a vendor-authorized training partner, we offer a curriculum that our partners have vetted. We use the same course materials and facilitate the same labs as our vendor-delivered training. These courses are considered the gold standard and, as such, are priced accordingly.

Is the training too basic, or will you go deep into technology?

It depends on your requirements, your role in your company, and your depth of knowledge. The good news about many of our learning paths, you can start from the fundamentals to highly specialized training.

How up-to-date are your courses and support materials?

We continuously work with our vendors to evaluate and refresh course material to reflect the latest training courses and best practices.

Are your instructors seasoned trainers who have deep knowledge of the training topic?

Ascendient Learning instructors have an average of 27 years of practical IT experience and have also served as consultants for an average of 15 years. To stay current, instructors spend at least 25 percent of their time learning new, emerging technologies and courses.

Do you provide hands-on training and exercises in an actual lab environment?

Lab access is dependent on the vendor and the type of training you sign up for. However, many of our top vendors will provide lab access to students to test and practice. The course description will specify lab access.

Will you customize the training for our company’s specific needs and goals?

We will work with you to identify training needs and areas of growth.  We offer a variety of training methods, such as private group training, on-site of your choice, and virtually. We provide courses and certifications that are aligned with your business goals.

How do I get started with certification?

Getting started on a certification pathway depends on your goals and the vendor you choose to get certified in. Many vendors offer entry-level IT certification to advanced IT certification that can boost your career. To get access to certification vouchers and discounts, please contact info@ascendientlearning.com.

Will I get access to content after I complete a course?

You will get access to the PDF of course books and guides, but access to the recording and slides will depend on the vendor and type of training you receive.

How do I request a W9 for Ascendient Learning?

View our filing status and how to request a W9.

Reviews

had a good time with the course, however some topics were left out due to the compact amount of time for training.

Great oppportunity for me to get training on the software during my work day.

I was very satisfied about how the course was organized. Sean Did a very good work

Simply great training provider that I can go for updating/acquiring my skill sets.

Quick to sign-up to course, and was able to garner some information from the course.