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

Online · Free

AI Agents and Automation Internship

8 short weeks. Free. Start any date.

Start free Plan my pace

By Wartens Ltd (UK), delivered through EDWartens.

A goal enters a loop of think, use a tool and observe, which repeats until the agent gives its answer.
  • Free
  • Online
  • Any start date
  • 1 to 8 weeks

Who it suits

Made for beginners.

You do not need to be a programmer. You start with what an agent is, then build simple workflows, then add a language model and tools one step at a time.
  • Students of computer science, IT, electronics, commerce and management.
  • Anyone who wants to automate repeat work and understand what an AI agent can and cannot do.
  • Read the notes on a phone, a tablet or a laptop.
Three boxes in a row: trigger, actions and output.

What you will learn

Eight weeks, one picture each

Every week is open from day one. Each lesson takes a few minutes.
  1. A goal enters a loop of think, use a tool and observe, which repeats until the agent gives its answer.

    Week 1

    What an AI agent is

    Explain the agent loop and its four parts, tell an automation from an agent, and map a manual task into trigger, steps, decision and output.

  2. Three boxes in a row: trigger, actions and output.

    Week 2

    Automation basics with n8n

    Describe a workflow as trigger, nodes and output, explain items and JSON, and build a small workflow in the free n8n community edition.

  3. A workflow of trigger, AI step, branch and action, with the AI step marked as the only uncertain part.

    Week 3

    Connecting an LLM to a workflow

    Add an AI step to a workflow, give it a prompt with a fixed output format, and test it on sample messages before trusting it.

  4. A sequence between the model, your app and a tool: the model asks, the app runs the tool, the result returns and the model answers.

    Week 4

    Tools and function calling

    Explain how a model uses a tool, write a clear tool description, and test that an assistant picks the right tool.

  5. Documents become chunks, embeddings and an index once; each question searches the index, finds top chunks and gets an answer with sources.

    Week 5

    Retrieval: agents that read your documents

    Explain how an assistant answers from your own documents, build a small document Q&A, and test that it names its sources and refuses when the answer is not there.

  6. A goal split into four steps, fetch, filter, summarise and draft, where each result is the input of the next step.

    Week 6

    Multi-step agents and human approval

    Break a goal into steps, limit how long an agent may run, handle failures, and place a human approval step before anything leaves the team.

  7. A test set table with an input, an expected action and a pass rule for each case, and a note that seven more rows make ten.

    Week 7

    Testing, costs, limits and safety

    Test an agent with ten cases, work out what a run costs, and set limits and guardrails so it stays safe.

  8. A five line brief: the team, what comes in, what the AI decides, what needs approval and what goes out.

    Week 8

    Build an agent end to end

    Build a small team agent in n8n with a trigger, an AI step, a tool, an approval and an output, test it and explain it in a one-page note.

Five steps in order: trigger, AI step, tool, approval and output, with approval highlighted.

Practice, if you like

Build a small workflow, then give it a brain.

Each week ends with a worked exercise, with a good result described. Skip them if you prefer.
  • Free tools: n8n community edition, a free chat assistant and Google Colab.
  • Small workflows you can run on your own computer with the free community edition.
  • A mini project in week 8: an agent built end to end, with a human approval step.
  • Best on a laptop or tablet. A phone works for reading.
A workflow of trigger, AI step, branch and action, with the AI step marked as the only uncertain part.
Documents become chunks, embeddings and an index once; each question searches the index, finds top chunks and gets an answer with sources.

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
A sequence between the model, your app and a tool: the model asks, the app runs the tool, the result returns and the model answers.

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.
A test set table with an input, an expected action and a pass rule for each case, and a note that seven more rows make ten.
How verification works

Questions

Quick answers

Is the AI Agents and Automation 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 tablet that can run n8n, a free AI assistant account and a free Google account for Colab. 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 a trigger that sends a message, a workflow that asks a model to summarise a text, or an agent that looks up a fact in your own document. In week 8 you build a small agent with a human approval step.

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?

Agents can act on wrong answers, so the course teaches approval steps, limits, logs and tests before anything is sent or changed. Never give an agent or a public chatbot personal, client or confidential data or keys you cannot afford to lose. Check what an agent did before you trust it.

Your first lesson is free.

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