AI words, in plain English.

An AI model operating autonomously across multiple steps: it plans, acts, checks its own work, and loops until the job is done. Can be built on Claude, GPT, Gemini, or any capable model.

In practiceThe jump from 'answer my question' to 'go handle this.' Agents are where AI stops being a search engine and starts being a coworker.

Software trained on massive text to predict the most useful next word. At scale, that becomes conversation.

In practiceThis is the engine. Everything else here is a setting, a guardrail, or a feature built on top of it.

A defined set of rules for how one program requests data or an action from another, and what it sends back. Think of it as a menu: the exact things a service lets you ask for, and how to ask.

In practiceYour booking form does not reach inside your email tool. It sends a request the tool's API allows, in the format the tool expects, and a new lead appears.

The private credential that lets one tool use Claude on your behalf. Anyone holding it can spend on your account.

In practiceTreat it like a credit card number. Never paste it in a public file, a screenshot, or a chat message.

Apple's channel for delivering push notifications to iPhones and iPads.

In practiceThe Apple side of mobile notifications. FCM handles Android and the web the same way.

Tuning your App Store listing so more people who see it actually install it.

In practiceThe App Store version of SEO. Worth real effort once you know people convert; a distraction before that.

Proving a user is who they say they are before letting them in, usually a login.

In practiceEmail and password, or 'sign in with Google,' is authentication deciding whether to open the door.

Making a task run itself on a trigger or a schedule, with no human hand on the keyboard.

In practiceThe whole point. Once you understand automation, every repetitive task becomes a candidate for elimination.

The part of your app that runs on a server, out of sight: logic, data, and the rules the frontend cannot be trusted with.

In practiceCharging a card or saving a booking happens in the backend, where a user cannot tamper with it.

The step that turns your source code into the optimized files a browser or app store actually runs.

In practice'npm run build' packages everything for production. If the build fails, nothing ships.

A network of servers that keeps copies of your site around the world so it loads fast wherever the visitor is.

In practiceMost hosts include one. It is also why a fresh deploy can take a moment to reach everyone.

The rate at which paying users cancel or stop coming back.

In practiceSign up 100 users a month but lose 100, and your growth is zero. Keeping the users you have beats chasing new ones.

A plain text file in your project folder that Claude reads automatically every session as its instructions.

In practiceYour persistent memory for Claude Code. Write it once, stop repeating yourself forever.

The two sides of a web app: the client is the user's browser, the server is the machine you control.

In practiceValidate on both. The client can be tampered with, so the server gets the final say.

A saved checkpoint of your code in version control, with a short note on what changed.

In practiceCommit often. Each one is a point you can safely return to when the next change breaks something.

Claude summarizing older conversation history to make room when the context window fills up.

In practiceKeeps long sessions functional. Early details get compressed, so check that nothing critical got dropped.

A reusable building block of your interface, like a button or a card, defined once and used everywhere.

In practiceBuild the button as a component once, and every page gets the same button, fixed in one place.

The maximum amount of text Claude can hold in one conversation. Go past it and the earliest parts start disappearing.

In practiceLong sessions drift. If Claude forgets an instruction from an hour ago, you have hit the window: start fresh or compact.

Software for tracking your contacts and customer conversations in one place.

In practiceOverkill at launch. A spreadsheet and your inbox do the job until relationships, not features, become the main work.

The standard tool for running a task on a fixed clock schedule: every night, every hour, every Monday.

In practiceSet it once and it runs without you. The standard way to automate recurring jobs like a nightly sync or weekly digest.

A free nine-digit ID that verifies your business exists to Apple when you enroll a company developer account.

In practiceRequest it the week you decide to enroll as a company. It can take days to weeks, and you cannot open the account without it.

The organized store where your app keeps its data: users, bookings, orders, anything that has to persist.

In practiceClose the tab and reopen it, and your data is still there. That is the database remembering.

Outside code your app relies on to work, installed rather than written by you.

In practiceEvery dependency is one more thing to trust and update. Do not add new ones without a reason.

Pushing your app live so the world can reach it, moving it from your machine to a host.

In practiceDeployment is the moment your change leaves your laptop and shows up at your real URL.

The exact lines a change adds or removes, shown side by side so you can see what really changed.

In practiceRead the diff before you accept Claude's work. It is the difference between approving and hoping.

Converting text into a list of numbers that encode its meaning, so computers can compare ideas mathematically.

In practiceThe engine behind smart search. Without embeddings, search is keyword matching. With them, it is meaning matching.

A single address on your backend that does one job when something sends it a request.

In practiceYour booking form posts to an endpoint that saves the booking. One door, one purpose.

The on/off flag in your payment system that unlocks paid features once a purchase succeeds.

In practiceThe "purchased but nothing unlocked" bug is almost always a product that was never attached to its entitlement. Check that link first.

Settings and secrets stored outside your code, so keys and passwords never live in the files you share.

In practiceYour Stripe key goes in an environment variable, not pasted into a file that could end up public.

Google's free service for sending push notifications to Android devices and the web.

In practiceThe Android side of mobile notifications. APNs handles Apple; you likely need both if you target multiple platforms.

Showing Claude two or three worked examples before your real request so it matches your format and tone.

In practiceThe highest-leverage prompting technique. One good example beats a paragraph of instructions.

Retraining a model on your own data to permanently shift its default behavior.

In practiceMore powerful than prompting, and far more expensive. Worth it when you have thousands of consistent examples and prompting hits a ceiling.

The part of your app that runs in the browser and the user sees: buttons, forms, layout, everything on screen.

In practiceWhen someone taps a button on your booking page, that is the frontend doing its job.

When an AI states something false with full confidence: invented facts, fake citations, wrong numbers.

In practiceThe most dangerous thing to miss. Always verify factual claims, and never cite a source without checking it.

A US law governing how protected health information must be handled, triggered by medical data, not by a wellness theme.

In practiceDeciding in writing that your app is a lifestyle tool, not a medical product, keeps you out of HIPAA's scope.

A spot where your own code runs automatically when a specific event fires, like a check that runs just before every file edit.

In practiceThe guardrail layer. Hooks catch mistakes before they ship without you needing to remember to check.

Integrated Development Environment: the app where you write, run, and fix your code, a live visual preview of what you're building alongside it, and every AI-proposed change shown next to your current code, line by line, so you can see exactly what would change before you accept it.

In practiceVS Code and Cursor are the two you will hear about most, not the only ones out there. Claude proposes an edit, you see the exact before-and-after side by side, and you accept only what you have read. The IDE is your cockpit: nothing changes without passing your eyes first.

Checking that data coming in is what you expect before you trust it or store it.

In practiceValidating that an email field actually holds an email stops junk, and some attacks, at the door.

A one-time sign-in link emailed to the user: click it and you are logged in, no password required.

In practiceLovely until an email scanner clicks the link before your user does and burns it. Always send a six-digit code alongside as the reliable fallback.

The standard way Claude plugs into external tools like Notion, your database, or your calendar.

In practiceWhat separates Claude as chatbot from Claude as operator. MCP is the power source for autonomous work.

A specific trained version of an AI. Different models have different speeds, costs, and reasoning depth.

In practiceYou pick the model like a tool: the cheap fast one for sorting emails, the heavy one for legal review.

In a payment tool like RevenueCat, the bundle of products displayed on your paywall at a given moment: prices, plans, and trial options.

In practiceThe display layer above entitlements. A product unlocks an entitlement; an offering decides which products show on the paywall right now.

Settings that control how much Claude can act on its own versus how often it pauses to ask you first.

In practiceStart restrictive. Loosen as you build trust with a workflow. Never go full auto on something you have not tested.

A setting that makes Claude lay out its entire plan before taking any action. You approve, then it proceeds.

In practiceNon-negotiable for high-stakes tasks. Catches wrong assumptions before they become wrong actions.

The instruction or question you give the AI.

In practiceThe quality of your output is almost entirely decided here. The clearer your instruction, the better the result.

An attack where hidden instructions inside external content (a doc, a webpage) try to hijack Claude.

In practiceWhen Claude reads untrusted content, that content can try to make it misbehave. Awareness is the first defense.

A website a user can add to her home screen so it behaves like an installed app, no App Store required.

In practiceThe fast path to "it feels like an app" without Apple's review queue. A manifest file and HTTPS make any site installable. A service worker is recommended, for offline support, not required.

The part of a URL after the question mark that passes small bits of data, like ?id=42.

In practiceNever put private data in a query string. URLs get logged, shared, and saved in history.

Claude searches your own documents for the relevant chunk, then answers from it.

In practiceKeeps answers grounded in your material. The difference between 'I think' and 'here is the source.'

Capping how many requests something can make in a window of time, so one user or bot cannot flood you.

In practiceRate limiting is what stops a script from hitting your login a thousand times a second.

A database rule that lets each user read and change only her own rows, enforced by the database before your code runs.

In practiceThe wall between one person's private data and everyone else's. Turn it on for every user table, then still filter every query by user id.

A scheduled task Claude runs automatically: weekly digest, daily summary, nightly cleanup.

In practiceThe difference between 'I have to remember to do this' and 'it is already done when I wake up.'

An isolated environment where code or an agent runs without being able to touch the rest of your system.

In practiceThe difference between a mistake that costs seconds and one that corrupts files. Know whether your tools run sandboxed.

Private credentials your app needs but no one should see: API keys, passwords, tokens.

In practiceA leaked secret is like a lost house key. Keep them in environment variables, never in your code.

Backend code that runs on demand without you managing a server, spinning up only when called.

In practiceYour contact form can run on a serverless function: no server to babysit, you pay only when it runs.

Supabase's server-only credential that bypasses row-level security entirely, meant for trusted server code only, never the browser. Supabase's current dashboard calls it the Secret key, under Settings, API Keys; you may still see the older "service_role" name in code and docs.

In practiceA query run with it returns every user's rows. Keep it server-side and still filter by user id.

A script that runs in the background independently of your page, powering offline mode and push notifications alongside your manifest.

In practiceIt doesn't make your PWA installable, a manifest and HTTPS already do that, but it's what makes the installed app work offline. Add one once your core features work.

Developer shorthand for getting your app out where people can use it, whether that is publishing it to the web or launching it in the App Store.

In practiceYou will hear it everywhere in building. In this course we mostly say publish or launch instead, but "ship it" and the "Ship Map" mean the same thing: get it real and out in the world.

A reusable set of instructions that teaches Claude to do one task your way, defined once and used on demand.

In practiceYour intellectual property as a Claude user. Build it once, save hours every week.

A quick check that the real path works end to end, not just that the code looks right.

In practiceBefore calling a feature done, smoke-test it: actually book the appointment, do not just read the code.

A hard dollar ceiling on an API key. When hit, the key stops working rather than running up an unlimited bill.

In practiceSet this before anything else with the API. A loop bug at 3am can generate a four-figure bill without it.

The set of tools your app is built on: the language, the framework, the database, the host.

In practiceNaming your stack once in CLAUDE.md means Claude stops guessing and writes code that fits what you use.

Your rules for how work should be done, written down in a file the AI reads every time rather than held in your head or repeated each session.

In practiceYour voice, your quality bar, your do-not-do list, written once in a file like CLAUDE.md. You stop re-explaining yourself, and every session starts already knowing how you want things done.

A focused copy of Claude assigned one specific job inside a larger task, reporting back when done.

In practiceEnables parallel work. Three subagents reviewing a contract at once beat one doing it in sequence.

The standing instruction sent before your message that frames Claude's role, tone, and rules for the whole session.

In practiceYour lever for consistent behavior. A good system prompt is worth ten repeated instructions.

A dial controlling randomness: low is predictable, high is creative and varied.

In practiceLow for structured outputs like JSON and summaries. High for brainstorming. The wrong setting is a common silent failure.

Apple's tool for installing your real app on a real phone before it goes live, for you and invited testers.

In practiceTest as the reviewer will: install via TestFlight, complete a sandbox purchase, and use a fresh Apple ID before you submit.

The unit AI usage is billed in, roughly a word fragment of about four characters. Input and output both cost tokens.

In practiceEvery API call has a token cost. Understanding tokens stops bill surprises when you paste a 50-page doc.

The text the model learned from during training. It shapes everything the model knows, assumes, and gets wrong.

In practiceExplains why Claude has a knowledge cutoff, and why it can reflect biases baked into the internet.

A single database write that updates the row if it exists or inserts it if it does not.

In practiceThe clean fix for sync code that runs twice. Keyed on a unique column, an upsert lands on the right row instead of creating duplicates.

A long random ID used as a row's primary key instead of a guessable sequential number.

In practiceSafer than 1, 2, 3: a user cannot reach someone else's record by changing a number in the URL, because the next id is unguessable.

A database built to store embeddings and search by meaning rather than exact keywords.

In practiceEnables RAG at scale. Thousands of notes, and Claude finds the right one instantly.

A URL in your app that an outside service calls automatically when something happens: a payment, a cancellation, a bounce.

In practiceThe reverse of an API call. Your app does not ask for news; the service tells you.