NewEDWartens Lab is open: 18 free machines (opens in a new tab)

Online · Free

Generative AI and Prompt Engineering Internship

8 short weeks. Free. Start any date.

Start free Plan my pace

By Wartens Ltd (UK), delivered through EDWartens.

Three nested boxes: generative AI inside machine learning inside artificial intelligence.
  • Free
  • Online
  • Any start date
  • 1 to 8 weeks

Who it suits

Made for beginners.

You do not need to code. If you have asked a chat assistant a question, you can start, and you learn why it answers the way it does and how to ask better.
  • Students of any branch who want to use AI well in study and work.
  • Anyone who wants to write clear prompts, check the answers and avoid the common traps.
  • Read the notes on a phone, a tablet or a laptop.
A sentence and a long word each cut into small pieces called tokens.

What you will learn

Eight weeks, one picture each

Every week is open from day one. Each lesson takes a few minutes.
  1. Three nested boxes: generative AI inside machine learning inside artificial intelligence.

    Week 1

    What generative AI is and is not

    Say what generative AI does well, where it goes wrong, and how it differs from a search engine.

  2. A sentence and a long word each cut into small pieces called tokens.

    Week 2

    How LLMs work

    Explain tokens, the context window, next-token prediction and temperature in plain words.

  3. Five parts of a good prompt: role, context, task, format and limits, each with a short example.

    Week 3

    Prompting fundamentals

    Turn a vague request into a clear prompt with a role, context, task, format and limits, and improve it one change at a time.

  4. Two example pairs of input and label, then a new input for the assistant to label in the same way.

    Week 4

    Advanced prompting

    Use examples, structured output, step-by-step reasoning, prompt chains and a self-check to get answers that are easier to trust and reuse.

  5. Four steps: a question, a search of your documents, the best passages added to the prompt, and an answer with quotes.

    Week 5

    Grounding and RAG in plain words

    Explain how an assistant answers from your own documents, ask for answers that quote the text, and spot when it should have said it does not know.

  6. Random noise becomes a clearer picture over several steps, guided by the words of the prompt, ending in a finished image.

    Week 6

    Images and multimodal AI

    Explain how an image is generated from a text prompt, write a clear image prompt, and check what a vision-capable assistant gets wrong when it reads a picture.

  7. Four steps to check an AI answer: pick the claims, find a trusted source, open the sources and fix or delete what you cannot confirm.

    Week 7

    Risks: hallucination, bias, privacy, prompt injection

    Spot a made-up fact, a biased answer and a privacy leak, explain prompt injection, and check an AI output before you use it.

  8. A prompt library table with five columns: purpose, prompt, example output, checks and owner, and two filled rows.

    Week 8

    A prompt library for a real team (mini project)

    Build, test and share a small library of prompts for one team, with an owner and a review loop that keeps it good.

One prompt tested on three inputs, a typical one, an awkward one and an odd one, each marked pass or needs a fix.

Practice, if you like

Try a prompt, then improve it.

Each week ends with a worked exercise to try with a free chat assistant, with a good result described. Skip them if you prefer.
  • Free tools: a free chat assistant (ChatGPT, Gemini, Claude or Copilot free tiers) and Ollama.
  • Short exercises you can repeat with your own topics.
  • A mini project in week 8: a prompt library for a real team.
  • Best on a laptop or tablet. A phone works for reading.
Five parts of a good prompt: role, context, task, format and limits, each with a short example.
Four steps: a question, a search of your documents, the best passages added to the prompt, and an answer with quotes.

Your pace

Choose a start date and a length.

We show your weekly plan. You can change it later.

Any length from 1 to 8 weeks. Start on any date from today. Retry the weekly checks and the final quiz as often as you like.

Plan my internship
Two example pairs of input and label, then a new input for the assistant to label in the same way.

Certificate and documents

Want proof? Add it later.

Free learners keep full access. A verifiable certificate of completion is an optional paid document, issued by Wartens Ltd (UK). Anyone can check it with the QR code or number.
Four steps to check an AI answer: pick the claims, find a trusted source, open the sources and fix or delete what you cannot confirm.
How verification works

Questions

Quick answers

Is the Generative AI and Prompt Engineering Internship really free?

Yes. Joining is free and so are all eight weeks, the weekly checks and the final quiz. You pay only if you choose an optional add-on.

How long can I take?

This internship runs for 1 to 8 weeks. You pick a start date and can change your plan later. All eight weeks are open from day one, so a short plan moves fast and a long one gives you room.

What do I need?

A laptop or phone and a free AI assistant account. Ollama is optional if you want to try a model on your own computer. Every tool used is free or has a free tier, so there is nothing to buy. The notes also read well on a phone.

What will I actually do?

You read short notes with diagrams, watch a few videos and take an easy check each week. Each week ends with a worked exercise, such as rewriting a vague prompt, giving an example, asking for a structured answer or spotting a made-up fact. In week 8 you build a small prompt library a team could use.

What do I get at the end?

A certificate of completion is an optional paid document, issued by Wartens Ltd (UK). It has a QR code and a number, so anyone can verify it at edwartens.com/verification. The lessons stay free, and you can finish without buying anything.

Is this a paid position?

No. It is training, not employment. Nothing is paid to you, and nothing here promises work with any company.

Who wrote the course?

OFORO, the Wartens AI company, wrote the notes and exercises. OFORO builds the AI behind Wartens' engineering and training work. The internship is run by Wartens Ltd (UK) and delivered through EDWartens.

What about privacy and wrong answers?

Generative AI can invent facts, repeat bias and be tricked by hidden instructions, and the course teaches you to check every answer. Never paste personal, client or confidential data into a public chatbot: privacy law applies wherever you live. Keep AI as a drafting aid and let a qualified person decide.

Your first lesson is free.

Start free
  • No card to start
  • Start any date
  • Verify with a QR code
Start free