Vibe Coder · Unit 11: APIs · Project
Milestone 11 of 23
One AI feature
A feature in your app that calls a model, with its key kept safe.
One product, built one milestone at a time
Vibe Coder has one project. You pick an idea in Unit 1 and every unit adds a piece to it, until the last unit launches it. Every milestone ends with a push to your own GitHub repository. This is where your product starts to think. This milestone adds one feature that calls a model, returns an answer in a shape your app can rely on, and keeps its key out of sight.
- 1Your builder’s kitA one-line product idea, your role, and five working accounts.
- 2A fact-checked product briefOne page on your idea, tested against how the models really behave.
- 3Your product project in ClaudeA project with instructions and files, and your first real piece of work from it.
- 4A brand kit and research fileA name, images and market research for your product, with a second opinion.
- 5Your prompt libraryThe prompts you will reuse to build the product, each one tested.
- 6Your product specThe problem, the people, the first version and how you will measure it.
- 7A clickable prototypeA version people can click through, shown to three of them.
- 8A working first draftYour product generated from the brief, with sign-in and data, in your own GitHub repository.
- 9The first working versionYour app running on your computer, built with Claude Code.
- 10Your Claude Code setupProject instructions, a custom command and a skill made for your app.
- 11One AI featureA feature in your app that calls a model, with its key kept safe.
- 12A connected assistantClaude or ChatGPT connected to a tool you already use, with the right permissions.
- 13Sign-in and saved dataAccounts and a database behind your app.
- 14Your app, liveOnline at its own address, updating every time you save.
- 15Your product’s back officeThe automatic jobs behind your product, as tested workflows in GitHub.
- 16An agent that works for your productOne agent with narrow tools, limits, approval and a test set.
- 17A helper that answers from your documentsAnswers with sources, scored on your own questions.
- 18A product that can chargeEmail from your own domain and a tested checkout, in test mode.
- 19A model tuned for one jobA small experiment, measured against your best prompt.
- 20A brand image kitOn-brand images from one saved workflow, with your own LoRA.
- 21A launch videoThirty to sixty seconds, with voice, music and sound.
- 22A tested, locked-down appEvery flow checked, and each person able to see only their own data.
- 23Your launched productThe finished product, in front of people, with a page that shows your work.
You start with
Your Claude Code setup
Project instructions, a custom command and a skill made for your app.
Milestone 10Your product gains
One AI feature
That makes 11 of 23 pieces in place.
Your role
The steps change with your role. Choose yours to see your version of this milestone.
Start with this prompt
Paste it into Claude or ChatGPT, or into Claude Code once you are building. Fill in the parts in square brackets with your own product.
I want to add one AI feature to my app. Here is what it should do for the person using it: [describe it in one or two sentences] Before writing code, tell me: what goes into the model, what should come back and in what shape, where the API key will live so that it never reaches the browser, and roughly what one call will cost. Then build it in small steps, and show me how to test it with a good input and a bad one.
Build it step by step
8 steps, one from each lesson of the unit. Do each step after its lesson. A box you tick here is ticked in the lesson too.
Step 1 of 8 · from the lesson What an API is
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Choose your AI feature
Pick the one AI feature your product will have, and write it as a sentence: when the user does X, the app sends Y to a model and shows Z. Add it to your build brief.
Done when
You will build exactly this feature across the unit.
Step 2 of 8 · from the lesson Keeping keys secret
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Store your key safely
Create an API key, set a spending limit, and put the key in an environment file. Ask Claude Code to confirm the file is ignored by Git and that the key is only read on the server.
Done when
Do the same for every key you ever create.
Step 3 of 8 · from the lesson Calling Claude
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Add your AI feature
Have Claude Code build your AI feature with a server-side call to Claude, a loading state and an error message. Test it with three inputs and with the network off, then commit.
Done when
You will make its output dependable in the Structured output lesson.
Step 4 of 8 · from the lesson Calling OpenAI
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Make the provider switchable
Ask Claude Code to route the AI feature through one function with a setting for the provider. Run the same three inputs through both and note which you prefer and why.
Done when
Keep the comparison. You will revisit it when costs matter.
Step 5 of 8 · from the lesson Structured output
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Make your feature return data
Define the fields your AI feature should return and have Claude Code switch it to structured output with validation. Save the result to your list or table and display it.
Done when
These fields become database columns in Unit 12.
Step 6 of 8 · from the lesson What it costs
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Cost and cap your feature
Have Claude Code log token use, work out the average cost per use, and estimate a month at your success target. Set a provider cap and a per-user daily limit.
Done when
Your AI feature is built, structured, measured and capped.
Step 7 of 8 · from the lesson Fast models on Groq
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Try your AI feature on a fast model
Get a Groq API key. Point your AI feature at Groq by changing the address, key and model, and run your test inputs through both providers. Record speed and quality side by side.
Done when
Keep the provider and model in configuration, not scattered through the code.
Step 8 of 8 · from the lesson Models on your own computer
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepOne AI feature Run a model locally and call it
Install LM Studio and download a small model. Chat with it offline, ask it about an attached document, then start the local server and point your AI feature at it by changing only the address.
Done when
Switch your feature back to the hosted model before you deploy.
Publish it to GitHub
Your product repository
Commit the AI feature with its key in an environment variable. Add .env.example with the variable names only, and push.
A milestone is not finished until it is pushed. A public repository with a history is how other people, including employers, can see what you built. Never commit a key, a token or anyone’s private data.
When it is done
Every box above is ticked, the work is pushed to GitHub, and you can show the result to someone who has not seen it before. Then move on: milestone 12 is a connected assistant.