0. Welcome & How to Use This Guide

What this guide is

This wiki is a practical “from zero → expert” path for building real software faster by iterating with Google AI Studio. The model does a lot of typing and first-pass implementation; you stay responsible for architecture, correctness, and shipping decisions.

• Project-forward: you’ll repeatedly turn prompts into runnable code, then harden it into something you trust.
• Tool-aware: you’ll learn when to rely on the model’s text vs when to use tools (tests, linters, logs, evals) to verify reality.
• Production-minded: speed is the goal, but reliability, security, and maintainability are the constraint set.

How to use it (fast + deep)

If you want results fast

• Pick a project section and follow it end-to-end.
• Copy prompts, run the code, and only then iterate (avoid “big prompt, big rewrite”).
• Keep a tiny changelog: what you asked, what changed, what broke, what you fixed.

If you want deep understanding

• Read the foundations first, then re-run the projects with stricter constraints and more tests.
• Rewrite prompts as specs: clear inputs, outputs, edge cases, and acceptance criteria.
• Practice “model escalation”: use faster models for scaffolding, stronger models for hard refactors.

How it’s organized

The guide is split into parts that build on each other. You can read it linearly, but it’s designed for jumping around without losing the plot.

• Foundations: mental models and the core workflow, so you can spot failure modes early.
• AI Studio: how to prototype safely and move from playground outputs into real repos.
• Beginner → Intermediate → Expert: the same skills, but with increasingly strict quality bars.
• Testing / Security / Performance: the “adult supervision layer” that turns prototypes into products.

Conventions (projects, checkpoints, ship points)

This wiki uses a few recurring concepts to keep you shipping instead of looping forever:

• Projects: full mini-products that force you to connect prompting, code, and real-world constraints.
• Checkpoints: moments where you stop adding features and clean up: run the app, fix the rough edges, and stabilize.
• Ship points: a “good enough to publish” line. You ship something small, then iterate from a working baseline.

Where to go next

Start with these pages to calibrate expectations and set up your workflow:

• 0.1 What “vibe coding” means (and what it doesn’t)
• 0.2 Who this guide is for (beginner → expert tracks)
• 0.3 How to follow along (projects, checkpoints, and “ship points”)
• 0.4 Required vs optional tools (AI Studio, editor, Git, runtime)
• 0.5 A note on UI changes & product naming
• Part I — Foundations