⌂ All Courses 12 modules • beginner friendly • ~10 hours
GOOGLE AI · IDE TRACK

Gemini Code Assist:
AI Pair Programming in Your IDE

From your first ghost-text suggestion to a deployed, AI-reviewed service. Twelve hands-on modules covering every feature: completion, chat, context files, agent mode, MCP, Gemini CLI, GitHub PR reviews, Google Cloud, and enterprise controls.

🔍 Search the Course  ·  💬 Ask the Course (works offline)

12
Modules
11
Hands-on Labs
5
Capstone Projects
~70%
Lab Time
⚠️ Heads-up (June 2026): Google is migrating the free Individuals tier of Gemini Code Assist and Gemini CLI to the Antigravity platform on June 18, 2026. Standard and Enterprise editions continue unchanged — this course teaches the full Standard/Enterprise feature set, and module G00 explains exactly what the transition means for you.
🍲

One project, start to finish: Recipe Box

From G02 onward every lab builds the same small Flask API — you generate its storage layer from comments, debug it in chat, test it, extend it with agents, get it reviewed on GitHub, and deploy it to Cloud Run. The capstone then has you build a second service, Meal Planner, entirely on your own using every skill.

Part 1 · Foundations
G00 · ORIENTATION

What Is Gemini Code Assist?

The feature map, the three editions and pricing, the June 2026 Antigravity transition, and how the 12 modules fit together. No code.

⏰ 25-35 min · concept module
G01 · SETUP

Setup & Your First Suggestion

Install in VS Code and JetBrains, sign in, trigger and verify your first AI-generated function. Plus the Standard/Enterprise admin flow.

⏰ 35-45 min · lab
G02 · COMPLETION

Code Completion & Generation

How completion really works ("your file is the prompt"), the spec-comment formula, partial accepts — and Recipe Box's storage layer built from comments.

⏰ 45-60 min · lab
Part 2 · Daily Driving
G03 · CHAT

Chat, Smart Commands & Actions

The code-aware chat panel, /fix /explain /doc /simplify /generate, right-click smart actions, source citations — and a 3-bug debugging lab.

⏰ 45-60 min · lab
G04 · QUALITY

Refactoring, Tests & Debugging

Natural-language code transformations, unit test generation, and why failing generated tests are good news (your design just got reviewed).

⏰ 50-60 min · lab
G05 · CONTEXT

Context Mastery: GEMINI.md & .aiexclude

Whole-codebase awareness, standing rules that visibly change output (proven by experiment), and mechanical secret-exclusion.

⏰ 45-55 min · lab
Part 3 · Agents & Automation
G06 · AGENT I

Agent Mode: Multi-File Delegation

The plan → diff → approve loop, checkpoints, command gates — and a coordinated 5-file tagging feature shipped through them.

⏰ 50-65 min · lab
G07 · AGENT II

MCP Servers & Power Tools

Connect agents to GitHub via MCP, restrict built-in tools, the honest truth about auto-approve — and an agent that fixes a real GitHub issue.

⏰ 50-65 min · lab
G08 · TERMINAL

Gemini CLI

The same brain in your shell: @files, !commands, headless mode as a Unix tool — generating READMEs and changelogs from pipes.

⏰ 40-50 min · lab
Part 4 · Ship It
G09 · REVIEWS

AI Code Reviews on GitHub

The PR-review app: summaries, severity-labeled findings, /gemini commands, config.yaml and styleguide.md — tuned on your own repo.

⏰ 45-55 min · lab
G10 · CLOUD

Google Cloud Integrations

Deploy Recipe Box to Cloud Run from chat (/deploy), plus the Gemini surfaces in BigQuery, Firebase, and beyond. Includes a no-cloud fallback.

⏰ 50-60 min · cloud lab
G11 · CAPSTONE

Enterprise, Security & Capstone

Code customization, data governance, IP indemnification — then build, test, review, and deploy the Meal Planner service using everything, graded against a 7-point rubric.

⏰ 90-120 min · capstone project
Domain Capstones · pick your specialty after G11
🏆

Real-industry projects, full workflow

Four standalone capstones anchored in real domains — each runs the complete Gemini Code Assist workflow (rules-first GEMINI.md, comment-driven generation, generated tests, an agent-mode feature, AI PR review) against problems with genuine industry stakes. Do the one matching your career track, or all four for a full-stack portfolio.

CAPSTONE · DATA ENGINEERING

LienSight: UCC Lien Risk Pipeline

Public-records lien filings → lender-ready risk data. Medallion architecture (bronze/silver/gold), entity resolution, amendment state tracking, quarantine-based data quality.

⏰ 3-5 hrs · Python + pandas + SQLite
CAPSTONE · API

TrackFlow: B2B Order Tracking API

Purchase-order lifecycle with an enforced, audited state machine; pluggable carrier adapters; business-day SLA breach detection. Exhaustive 64-pair transition testing.

⏰ 3-5 hrs · Flask + SQLite
CAPSTONE · BACKEND

PriorAuth: Healthcare Pre-Authorization

A policy-as-data clinical rules engine: CPT/ICD criteria in versioned JSON, explainable decisions with reason codes, immutable audit trails, PHI-safe logging discipline.

⏰ 4-6 hrs · Flask + rules engine
CAPSTONE · FRONTEND

TrackFlow Ops Dashboard

A zero-build vanilla JS operations dashboard: live order board, SLA banner, accessible detail drawer, honest loading/error/empty states, headlessly tested logic, dual themes.

⏰ 3-5 hrs · HTML/CSS/JS · pairs with the API capstone
Related Courses