All micro-internships
Micro-internship brief ≈2.5h in one sittingno-code

Prompt like a pro

Great AI output starts with a great prompt. Pick one real task and write five prompts that get progressively better answers — then explain what changed and why.

AI LiteracyPrompt Engineering

Posted by The AI Internships

The work brief

  1. 01Pick a task you actually care about (e.g. draft a cover letter, plan a trip, explain a topic).
  2. 02Write a first, lazy prompt and copy the AI’s answer.
  3. 03Improve the prompt four more times — add context, role, constraints, examples, format.
  4. 04For each version, note what you changed and why the answer got better.

What you’ll produce

3 deliverables

Submission standard

Submit all five prompt → answer pairs and your reflection. Be specific — generic answers won’t pass. Also paste a public 'Share' link to the actual chat so we can see the five prompts really happened in sequence.

  • The task you chose

    Short answerRequired

  • Your 5 prompts (worst → best), each with the AI’s answer

    Paste all five prompt → answer pairs exactly as they appear in the chat you share below — they must match.

    Written responseRequired

  • What changed between each prompt, and why the answer improved

    Written responseRequired

You’ll complete these inside your private workspace.

What you must submit as proof

This brief requires evidence an AI can’t fabricate.

  • Public 'Share' link to your ChatGPT/Gemini chat

    Must be YOUR live chat showing the real five-prompt back-and-forth, in order — not a re-typed copy.

    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.

Real iteration

25%

Five genuinely different prompts that build on each other.

Quality of reasoning

25%

Explains why each change helped.

Specificity & effort

13%

Concrete, personal, non-generic work.

Verifiable prompt trail

38%

Auto-fail if the link is missing, dead, not the student's own chat, or the shared prompts don't match the pasted ones (generic/invented).

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.