Google's agentic coding environment, driven by Gemini.

Pick this when

You're already in Google's model ecosystem and want its coding agent — the course treats it as a third option, not a first choice.

What makes it different

Gemini-native, so it inherits Google's long context

Used in BC4 to generate the example markdown and JSON files for the file-format lesson

What it does

Generates code and structured files from prompts

Runs as a local agentic coding environment alongside Cursor/Claude Code

What it does not do

Common wrong expectations

Doesn't have the course's track record — mentioned and used lightly, never compared head-to-head

Where it sits in a stack

The Google corner of the coding-agent shelf. Try it if Gemini is already your model of choice.

Shelf

Coding agents & editors

Our status · watch

No reason to add a third coding agent, but worth knowing it exists.

For your projects

Nothing pressing; note it if a future course session leans on Google tooling.

Freshness

current

Related tools

competes withCursorbuilds onGemini

cursor: grouped with Cursor and Claude Code as the local coding tools

gemini: runs on Gemini

Every moment the course touched it (10)

SessionCoverageMomentWhat happened
Basecamp 4: Introduction to n8n — IIdemonstrated1:07:31Used with Gemini to generate the example markdown and JSON files for the format lesson
Session 14: Claude Code — Advanced Workflowsdemonstrated0:15:26Google's VS Code-fork IDE, used only as a host for the Claude Code extension
Session 15: Loop, Harness & Graph Engineering (posted as 'Securing Vibe-Coded Apps')demonstrated0:58:25Bill-splitter built via instruction-loop ('work in a loop and don't stop until it's done') with self-written verification plan — loop behavior without /goal
AI Sprint: Claude Code with Antigravity — Day 1 (Taste as the Moat, the Muscle-and-Mirror Setup, and the Model Council Build)demonstratedEditor mode as mirror (hidden dot-folders) + agent manager as the proven backup during the Claude outage
AI Sprint: Claude Code with Antigravity — Day 2 (CLAUDE.md, the 50% Context Rule, and the Sketch-to-App Build)demonstratedMirror + warm standby again; 'whenever my Claude fails, I go to my memory and pick it forward'
AI Masterclass: Exploring Antigravity 2 — Four Products, Four Slash Commands, and Two Live BuildsdemonstratedAll four products toured; Antigravity 2 is the build surface: slash commands, skills, hooks, swarm, scheduler, browser
AI Sprint: Windsurf & Devin — Day 1 (Vibe to Agentic: GitHub as Pizza, the Four Spec Concerns, and the IDE Lineage)explainedOrigin story: built from Windsurf's acquired core team and IP snapshot
Basecamp 2: Vibe Codingmentioned1:35:08Grouped with Cursor/Claude Code as local coding tools; don't pay for multiple subscriptions at once
Session 11: Overview of Claude Code & Key Concepts (Installs, Modes, Context Files, Skills, Hooks & MCPs)mentioned0:04:35Listed among the tools of the 'top 10% of AI users'
AI Sprint: OpenClaw — Session 2 (Token Anatomy, Claude Code Inside the Server, Skills, and Multi-Agent Workspaces)mentionedSlido: usable in place of Claude Code only if it ships a CLI you can install server-side

← All tools by category