Skip to content
EDWartens UK

Free course · AI and machine learning

AI Coding for Engineers: Claude Code, Cursor and Copilot

Use AI coding agents the way an engineer should: set up Claude Code, Cursor and GitHub Copilot, write the spec before the prompt, review every diff, let tests and Git catch the mistakes, connect tools with MCP, keep secrets out, build a Python Modbus and OPC UA logger, and generate PLC Structured Text that is checked and simulated before it goes near a machine.

See the modules

Free to learn. Verifiable certificate £19 when you pass the final exam (optional, VAT included).

Level
Beginner
Modules
13
Video
15 hours
Price
Free

Outcome

What you will be able to do

Explain what a coding agent does and where it fits in engineering work; install and configure Claude Code, Cursor and GitHub Copilot with project instructions and safe permission modes; write a spec and acceptance tests before prompting; review AI code with a checklist; use pytest and Git so any agent change can be proved or undone; connect tools through MCP and keep plant-facing tools read only; keep credentials out of prompts and repositories and check what an agent installs; build a tested Python Modbus and OPC UA data logger; and review and simulate AI-generated IEC 61131-3 Structured Text before it goes near a machine.

  • Explain what a coding agent does and which engineering tasks to give it
  • Install and configure Claude Code, Cursor and GitHub Copilot with safe permission modes
  • Write a one-page spec with acceptance tests before prompting
  • Review AI code with a checklist and catch invented functions and swallowed errors
  • Use pytest and Git so every agent change can be proved or undone
  • Connect tools through MCP and keep plant-facing tools read only
  • Keep credentials out of prompts and repositories and check every new dependency
  • Build a tested Python Modbus and OPC UA logger and review AI-written Structured Text in a simulator

Software

VS Code, Python 3.10 or later, Git, and at least one of Claude Code, Cursor or GitHub Copilot. Cursor and Copilot have free plans; Claude Code needs a paid Claude plan or a Console account. A PLC simulator (PLCSIM, CODESYS or OpenPLC) for the Structured Text module.

Hardware

A computer that runs VS Code. No PLC or plant equipment: every exercise runs against simulators.

Syllabus

13 modules

Each module has video lessons, notes and a short quiz. The final exam closes the course.

  1. 1What agentic coding is, and what it is not2 lessons
  2. 2Setting up Claude Code2 lessons
  3. 3Setting up Cursor2 lessons
  4. 4Setting up GitHub Copilot4 lessons
  5. 5Spec first: prompting an agent for code3 lessons
  6. 6Reading and reviewing AI code3 lessonsLab
  7. 7Tests as guardrails2 lessons
  8. 8Git and safe rollbacks2 lessons
  9. 9MCP and tool use2 lessons
  10. 10Security, secrets and sandboxing4 lessonsLab
  11. 11Worked build: a Python Modbus and OPC UA data logger2 lessons
  12. 12Structured Text with AI: check every line, simulate before the machine4 lessons
  13. 13Final Assessment1 lesson

How it works

How this course works

  1. Watch the video lessonsOne module at a time, at your own pace.
  2. Take the module quizA short quiz at the end of each module shows what stuck.
  3. Keep your notesWrite in My notes beside each module and ask the trainer if you are stuck.
  4. Practise in the labOptionalTry a task from the module in the EDWartens Lab, in your browser.
  5. Sit the final examPass it once you have been through the modules.
  6. Certificate, if you want oneOptionalPaid, and only after you pass. Anyone can check it online.

EDWartens Lab

Practise this in the EDWartens Lab

Practise the habits that keep AI-assisted work safe in the AI Workbench: checking an AI's claims against the source and keeping an agent from obeying planted text.

Works alongside AI Coding for Engineers: Claude Code, Cursor and Copilot. The Lab is ai for industry practice in your browser: no install, no hardware, free to use. Sign in as a learner and it opens with your account.

Open the free lab See the Lab
AI for industry: Build AI models.

Levels to try with this course

Optional. Skip it whenever you like: it never blocks your progress or your certificate.

Why practise in a lab

Technical work is judged on what you can do: wiring, commissioning, finding a fault. Doing a task yourself teaches more than watching it a second time, and a lab lets you try it safely before you meet real equipment. It does not replace working on real hardware.

  • Practise safely, so a mistake costs nothing.
  • The lab checks your work like a site test, so you know when it is right.
  • Free, in your browser, with nothing to install.

Certificate

An optional certificate when you pass

Learning is free. Pass the final exam and you can have a certificate for £19, including VAT, with a number employers can check online. It records that you completed a free online course; it is not a regulated qualification or a CPD certificate.

  • Your name, the course, its study time and your final exam score
  • A unique certificate number and a QR code to its verification page
  • Issued by Wartens Ltd; add it to your LinkedIn profile in one click
  • Pay now or after you pass: it is issued the moment you pass the final

How the certificate works

Sample certificate for AI Coding for Engineers: Claude Code, Cursor and Copilot

Credits

Who made the lessons

The video lessons belong to their creators. EDWartens wrote the study plan, notes, quizzes and the final exam.

  • Anthropic

    the talk on the future of agentic coding with Claude Code, and Mastering Claude Code in 30 minutes

  • Tech With Tim

    the full beginner tutorials for Claude Code and Cursor 3.0, and the pytest tutorial on writing tests in Python

  • freeCodeCamp.org

    the Claude Code full course on VS Code setup, autonomous goals, MCP servers and GitHub

  • Cursor

    ten working tips for Cursor's Agent

  • Visual Studio Code

    getting started with Copilot Free, the agent mode tutorial with MCP and custom agents, and local, background and cloud agents

  • GitHub

    when to use Copilot's cloud (coding) agent versus agent mode, and automating code review and testing with Copilot

  • IBM Technology

    the explainers on agentic coding, spec-driven development, agentic engineering versus vibe coding, AI in code review, and MCP

  • Microsoft Developer

    the session on planning, specifying and implementing with GitHub Spec Kit

  • Owain Lewis

    the lessons on coding with AI agents from a spec and on test-driven development with Claude Code

  • John Kim

    the lesson on how an experienced engineer reviews AI-written code

  • Corey Schafer

    the Git command-line fundamentals and the lesson on fixing mistakes and undoing bad commits

  • Snyk

    the lesson on securing AI-generated code

  • SiteGround.com

    the security checklist for vibe-coded projects

  • Nate Herk | AI Automation

    the lesson on using Claude Code's safer permission modes instead of bypassing permissions

  • Fuzz Puppy

    running Claude Code safely inside a VS Code dev container

  • APMonitor.com

    reading and writing Modbus from Python

  • Fusion Automate

    a basic Modbus data logger in Python with SQLite

  • Siemens Knowledge Hub

    the introduction to the Industrial Copilot for engineering

  • Jakob Sagatowski

    the TwinCAT specialist's test of ChatGPT for PLC programming

  • Automatedo

    the guide from prompt to PLC code with AI

  • LEARNACON

    generating PLC code with AI for TIA Portal

Questions

About this course

Who is this course for?
Engineers who write scripts or want to: PLC and SCADA engineers, instrumentation and maintenance engineers, data and AI learners, and engineering students. You should be able to read a short Python program.
Do I need to pay for Claude Code, Cursor or Copilot?
No. One tool is enough to do every exercise, and Cursor and GitHub Copilot both have free plans. Claude Code needs a paid Claude plan or a Console account, so every exercise can be done in Cursor or Copilot instead. EDWartens is not affiliated with Anthropic, Cursor, GitHub or Microsoft.
Will this course go out of date?
These tools change every month. The course was checked against each tool's official documentation on 30 September 2026, the notes say so, and they point you to the official pages to check the current steps. The engineering habits it teaches, specs, tests, review and Git, do not change.
Can AI write PLC programs for my machine?
It can draft Structured Text, and the course shows how convincing and how wrong the drafts can be. Every line must be reviewed against a control narrative and tested in a simulator such as PLCSIM, CODESYS or OpenPLC before it goes near a machine, and safety functions stay in safety-rated systems.
Is this the same as the prompt engineering or Python courses?
No. Prompt Engineering for Engineers teaches writing prompts, and Python for AI and Engineering Data teaches Python itself. This course teaches working with coding agents: setup, specs, review, tests, Git, MCP and security, applied to automation work.
Is the course really free?
Yes. Every module, the notes, the project and the final assessment. The only paid item is the certificate, if you want it.
What certificate do I get?
An EDWartens Certificate of Completion, issued when you pass the final assessment, with a number anyone can verify on our site. It is not a certification from Anthropic, Cursor, GitHub or Microsoft.
How long does the course take?
About 15 hours of video lessons, notes and practice, taken at your own pace. The optional project takes about 10 hours more.
What is the project?
You build a small dashboard for a clear-water tank skid at a textile processing unit with an AI agent: a specification, a tag list, tests written first, a read-only data path, a risk register, a test report and an honest log of what the agent produced and what you changed.

The Professional Module is five live days of Siemens PLC, HMI and SCADA with an instructor, then a resume session and a CPD certificate.

See the Professional Module