All micro-internships
Micro-internship brief ≈6h in one sittingbuilder

Ship a landing page with AI

Use an AI app builder to generate and deploy a real landing page — then prove you understand what it built. Share the live URL and the code.

AI Application DevelopmentUX DesignWeb Development

Posted by The AI Internships

The work brief

  1. 01Pick a product idea and generate a landing page (v0 / Bolt / Lovable, or code + AI).
  2. 02Read the AI’s code and change at least one thing yourself — copy, layout, colours — until you can explain every section.
  3. 03Deploy it so it has a public URL.
  4. 04Push the code to a public GitHub repo.

What you’ll produce

4 deliverables

Submission standard

Give us the live URL, the public repo, and a short write-up of what AI generated vs what you changed. We’ll fetch both. Also give us the direct link to the commit where you changed the AI's code yourself; your repo must show more than one commit.

  • Live URL of your deployed page

    Public linkRequired

  • Public GitHub repo

    Public GitHub repo — the commit history must show more than one commit, including the change you made yourself after reading the AI's code (not a single 'initial commit' dump). A one-commit paste fails the authenticity gate.

    Public linkRequired

  • What you built and how AI helped

    Written responseRequired

  • Screenshot of the live page

    Image uploadOptional

You’ll complete these inside your private workspace.

What you must submit as proof

This brief requires evidence an AI can’t fabricate.

  • Link to the specific commit (or PR) where YOU changed the AI's output

    A GitHub commit URL showing the edit you made after reading the generated code — proves you did more than paste.

    Public linkRequired

Submissions without this evidence cannot be submitted.

Protect other people in your proof. Blur faces, names, phone numbers and email addresses before you upload, and refer to anyone you worked with by role or number ("Listener 1", "the stall owner"). Your proof is only ever used to check your work — it is never published, never appears on your certificate, and is never shown in your public portfolio.

How your work is evaluated

The passing benchmark is 70/100.

Actually shipped

29%

The live URL loads a real, on-topic landing page.

Code present

14%

The repo contains the page’s code.

Craft & explanation

29%

The page is coherent and the write-up shows real judgement.

Built, not one-shot pasted

29%

If the live URL is dead, the repo has a single copy-paste commit, or the change-commit link is missing/empty, this fails regardless of how the page looks.

How we grade your AI usage

30% of your score

Using AI is the point — it’s the skill this certificate proves. You’ll answer three short questions about how you used it: what you asked, what was wrong with its first answer, and what you changed. Specific, honest answers score high. “I pasted the brief and submitted the answer” scores near zero.