Building in the AI Age
A vocabulary/orientation module for building whole apps across the stack — frontend for backend devs and vice-versa, shipping to a live URL, and directing AI coding tools. Know what every piece is called so you know what to tell the AI.
- chapters
- 8
- objectives
- 47
- core
- 36
- est. time
- 3h 34m
- 01 7.1 Anatomy of a modern app ★ core
Every web app is the same handful of parts — client, server, API, database, and the pipe from your repo to a live URL. Learn the map once and every framework slots into it.
- 02 7.2 Frontend for backend devs ★ core
The browser-side vocabulary a server dev needs to direct an AI to build good UI — components, state, rendering, styling — without becoming a frontend specialist. (Module 5 is the interview-depth version.)
- 03 7.3 Backend for frontend devs ★ core
The server-side vocabulary a UI dev needs to direct an AI to build a real backend — runtimes, endpoints, data, auth, jobs — and where each piece lives.
- 04 7.4 TypeScript, just enough ★ core
The whole stack is TypeScript. Learn what static types are, the bugs they catch before you run the code, and how they make both you and the AI faster.
- 05 7.5 From code to a live URL ★ core
How localhost becomes a real website — git/GitHub, a host, a domain, DNS, HTTPS, production env vars, and preview deploys. (Module 6 is the interview-depth version.)
- 06 7.6 The AI coding toolbox ★ core
A taxonomy of AI coding tools — autocomplete, chat, terminal agent, AI IDE, app-builder — so you reach for the right one, plus a non-stale way to think about model tiers.
- 07 7.7 Working with AI agents ★ core
The workflow and vocabulary for getting good output from a coding agent — context, prompting, plan-then-code, the edit-test-review loop, and the safety rails.
- 08 7.8 Building AI features into your app ★ core
Putting AI inside the product, not just using it to write code — calling an LLM API, prompts-as-code, structured output, and the embeddings → vector store → RAG pipeline.
Section assessment
Harder, multi-concept questions drawn from across the module. Aim for 75%.
- 01medium
Code that must keep a secret (e.g. a payment key) should run…
- 02medium
React is a UI library; Next.js / Astro are…
- 03medium
A strong frontend prompt to an AI should name… (select all)
- 04medium
Authentication vs authorization:
- 05medium
A validation check in the frontend is enough to keep an endpoint secure.
- 06medium
Why do types make an AI assistant more accurate?
- 07medium
A signature like total(o: Order): number is best described as…
- 08medium
A preview deploy is…
- 09medium
For a hands-off task that spans many files in a repo (edit, run, test, loop), reach for…
- 10medium
The most capable model is always the right choice for every task.
- 11medium
The “context window” is…
- 12medium
A strong task prompt for an agent includes… (select all)