AI and machine learning
AI Coding for Engineers: Claude Code, Cursor and Copilot
Use Claude Code, Cursor and GitHub Copilot as an engineer should: spec first, review every change, test it, and keep secrets safe.
AI Coding for Engineers: Claude Code, Cursor and Copilot is a free, self-paced online course from EDWartens for engineers who script: PLC and SCADA engineers, data and AI learners, and engineering students. It has 13 modules and takes about 15.3 hours, with written notes, a practice task per module, a practical project and a final assessment of 15 questions (pass mark 60%). Learning costs nothing and needs only a free account. The optional EDWartens Certificate of Completion, verifiable by code, is a one-off US$23.99 for you; it is not a vendor credential. Updated 1 November 2026.
- Free
- Beginner
- 15.3 hours
- Self-paced
- Certificate optional
- Lab practice in your browser
No card, no trial. The course is free for good. Certificate US$23.99, optional.
- Who it is for
- Engineers who script: PLC and SCADA engineers, data and AI learners, and engineering students
- Jobs
- Roles that use this skill: AI engineer, machine learning engineer, data analyst and automation developer. No course guarantees a job.
- Tools
- 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.
- Updated
After this course you can
By the end you will be able to:
- Set up Claude Code, Cursor and GitHub Copilot with safe permissions
- Write a spec and acceptance tests before prompting
- Review AI-written code with a checklist
- Use pytest and Git to prove or undo any agent change
- Build a tested Python Modbus and OPC UA data logger
Who it is for, and what you need first
Who it is for
Engineers who script: PLC and SCADA engineers, data and AI learners, and engineering students.
Level: Beginner. Beginner to intermediate. For engineers who script or want to: PLC and SCADA engineers, data and AI learners, and engineering students. You should be able to read a short Python program; no professional software experience is needed.
What you need
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.. What to download, and how.
How this course works
Watch the lessons
Short video lessons, one module at a time, at your own pace.
Read the notes
Open the Reading tab for the written notes and diagrams of the module.
Practise in the 3D labOptional
Try the module in the free 3D lab, in your browser.
Check yourself
Answer the questions to see what stuck before you move on.
Final assessment
Pass the final once you have been through the modules.
Certificate, if you want oneOptional
Optional, with a page anyone can use to verify it.
What you learn
13 modules in order, at your own pace. 15.3 hours of video lessons, with written notes and a practice task in each module.
- 1What agentic coding is, and what it is not31m
- 2Setting up Claude Code1h 4m
- 3Setting up Cursor1h 5m
- 4Setting up GitHub Copilot30m
- 5Spec first: prompting an agent for code1h 4m
- 6Reading and reviewing AI code, with lab practice: 50m
- 7Tests as guardrails51m
- 8Git and safe rollbacks52m
Show the other 5 modules
- 9MCP and tool use1h 25m
- 10Security, secrets and sandboxing, with lab practice: 40m
- 11Worked build: a Python Modbus and OPC UA data logger27m
- 12Structured Text with AI: check every line, simulate before the machine55m
- 13Final Assessment
Software you need
What to download, where from, what it costs and how to install it. Every link goes to the maker's own site, never a mirror.
One AI coding tool is enough for every exercise. pymodbus, asyncua, pytest and streamlit install with pip; the Structured Text module needs one PLC simulator.
Show what to download (11 tools)
Required
- 01Free
Python
Python Software Foundation
- Runs on
- Windows (not Windows 7 or earlier), macOS and Linux. Windows builds for x64, 32-bit and Arm64.
- Account
- None needed
Python is free, open source software. You can use it for learning and for commercial work at no cost.
Steps
- 1.Open python.org/downloads and click the download button for your system.
- 2.On Windows, run the Python install manager (or the classic 64-bit installer) you downloaded.
- 3.If you use the classic installer, tick "Add python.exe to PATH" on the first screen, then click Install Now.
- 4.Open a new Command Prompt or Terminal and run: python --version (on Windows you can also run: py --version).
- 5.Install packages with pip, for example: python -m pip install requests
- pip comes with Python. Run it as python -m pip so it always matches the Python you are using.
- Python.org now recommends the Python install manager on Windows. If it offers to add its folder to PATH, say yes so the python command works everywhere.
- Make a virtual environment for each project: python -m venv .venv
Official download pagepython.orgAlternatives
- Anaconda Distribution: Python with 600+ data science packages and Jupyter already included.
- 02Free
Visual Studio Code
Microsoft
- Runs on
- Windows 64-bit (supported Windows client versions), macOS (latest and two previous releases), Linux (Ubuntu 20.04, Debian 10, RHEL 8, Fedora 36 or later)
- Account
- None needed
- Size
- Less than 200 MB download, under 500 MB installed
Free to download and use. Extensions from the Marketplace each have their own licence.
Steps
- 1.Open code.visualstudio.com/download.
- 2.Pick the installer for your system (on Windows, the User Installer is fine).
- 3.Run the installer. On Windows, tick "Add to PATH" if it is offered.
- 4.Open VS Code and install the extensions your course uses, for example the Python extension.
- Hardware needs are small: a 1.6 GHz processor and 1 GB of RAM.
- On Windows, the "Open with Code" options in the installer let you open folders from File Explorer.
Official download pagecode.visualstudio.com - 03Free
Git
Git project (git-scm.com)
- Runs on
- Windows (x64 and ARM64), macOS, Linux
- Account
- None needed
Git is free and open source software. Use it for any purpose at no cost.
Steps
- 1.Open git-scm.com/downloads and choose your system.
- 2.On Windows, download the x64 Setup (or ARM64 Setup) and run it. The default choices are fine for most learners.
- 3.Open a new terminal and run: git --version
- 4.Set your name: git config --global user.name "Your Name"
- 5.Set your email: git config --global user.email "you@example.com"
- On Windows you can also install with: winget install --id Git.Git -e --source winget
- A portable version (no installer) is offered for PCs where you cannot install software.
Official download pagegit-scm.com
One AI coding tool
Any one is enough.
- 04Paid plan or API account
Claude Code
Anthropic
- Runs on
- macOS 13 or later, Windows 10 1809 or later, Ubuntu 20.04 or later, Debian 10 or later; 4 GB of RAM
- Account
- A Claude Pro, Max, Team or Enterprise plan, or a Claude Console (API) account
The free claude.ai plan does not include Claude Code. It runs in the terminal, in VS Code and JetBrains through extensions, and in a desktop app.
Steps
- 1.Open code.claude.com/docs/en/setup and follow the native installer for your system.
- 2.On macOS, Linux or WSL run: curl -fsSL https://claude.ai/install.sh | bash. On Windows PowerShell run: irm https://claude.ai/install.ps1 | iex.
- 3.Open a new terminal and run claude --version, then claude doctor.
- 4.Go to your project folder, run claude and follow the browser prompt to log in.
- 5.Run /init to create a CLAUDE.md, then cut it down to the rules that matter.
- On native Windows, install Git for Windows so Claude Code can use Git Bash.
- Start new work in plan mode (Shift+Tab) and commit before every task.
Anthropic product pagecode.claude.comLegitimate free routes
- Cursor (Hobby plan): A free plan with limited Agent requests
- GitHub Copilot Free in VS Code: A free monthly allowance
- 05Free plan with limited Agent requests
Cursor
Anysphere
- Runs on
- macOS 12 or later (Apple silicon and Intel), Windows 10 or later, Linux (apt, dnf or AppImage)
- Account
- A Cursor account (email, Google or GitHub sign-in)
The Hobby plan is free with limited Agent requests and needs no card. Paid individual and team plans give more usage; check cursor.com/pricing for the current plans.
Steps
- 1.Open cursor.com/download and pick the installer for your system.
- 2.Run the installer and open Cursor.
- 3.Sign in or create a free account when asked.
- 4.Open your project folder, then open Agent with Ctrl+I (Cmd+I on a Mac).
- 5.Press Shift+Tab in the agent input to switch to Plan Mode for larger changes.
- Cursor can import your VS Code extensions and settings on first start.
- Put project rules in .cursor/rules as .mdc files, or use an AGENTS.md at the root.
Official download pagecursor.com - 06Free plan with a monthly allowance
GitHub Copilot in VS Code
GitHub (Microsoft)
- Runs on
- Wherever VS Code runs: Windows, macOS and Linux
- Account
- A GitHub account
Copilot Free gives a monthly allowance of inline suggestions and AI credits. Verified students can use Copilot Student. Paid plans (Pro, Pro+, Max, Business, Enterprise) add more usage and Copilot cloud agent; check GitHub's plans page for the current terms.
Steps
- 1.Install VS Code from code.visualstudio.com/download.
- 2.Open VS Code, select the Copilot icon in the Status Bar and choose Use AI Features.
- 3.Sign in with your GitHub account when the browser asks.
- 4.Open the Chat view and pick Agent or Plan for a task in your project.
- 5.Add a .github/copilot-instructions.md or an AGENTS.md with your project's rules.
- Copilot cloud agent is not part of Copilot Free; on Business and Enterprise an administrator must enable it.
Official download pagecode.visualstudio.com
Optional
Useful, not needed to finish the course.
- 07Free
PyModbus
pymodbus-dev (open source project), a Python or npm package
- Runs on
- Windows, macOS and Linux with Python 3.10 or later
- Account
- None needed
Free, open source under the BSD 3-Clause licence.
Steps
- 1.Install Python 3.10 or later and create a virtual environment.
- 2.Run: pip install "pymodbus==3.8.6" (the version the course code is written and tested for; 3.10 renamed slave= to device_id=)
- 3.For serial (RS-485) devices, run: pip install "pymodbus[serial]==3.8.6"
- 4.Follow the client examples in the documentation to read holding registers from a device or the built-in simulator.
- PyModbus includes a server simulator with a web interface, so you can practise without real hardware.
- Only write registers on lab equipment. Writes can move real machines.
Official download pagegithub.com - 08Free
CODESYS Development System V3
CODESYS GmbH
- Runs on
- Windows 10 or 11, 64-bit (8 GB RAM and 12 GB free disk recommended)
- Account
- A free CODESYS Store account (one-time registration)
The Development System is free in the CODESYS Store. The setup also installs a demo of the CODESYS Control Win SL SoftPLC, which runs for two hours without a licence and then needs a manual restart.
Steps
- 1.Open the CODESYS Development System page in the CODESYS Store.
- 2.Register once for a free CODESYS Store account and sign in.
- 3.Download the 64-bit setup.
- 4.Run the installer as administrator.
- 5.Start CODESYS Control Win SL from the system tray and connect your project to it.
- When the SoftPLC stops after two hours, restart it from the system tray and log in again.
- Allow at least 12 GB of free disk space.
Official download pagestore.codesys.com - 09Free
OpenPLC Editor and OpenPLC Runtime
Autonomy Logic (OpenPLC project)
- Runs on
- Editor: Windows 10 or 11 (x64), macOS (Apple silicon or Intel), Linux x64. Runtime: Linux or Docker
- Account
- None needed
OpenPLC is free and open source. The Runtime v4 is MIT licensed and the Editor source is on GitHub under GPL-3.0.
Steps
- 1.Open the OpenPLC download page and download the Editor for your system.
- 2.Install and open the OpenPLC Editor.
- 3.Install OpenPLC Runtime v4 on a Linux PC, Raspberry Pi or in Docker, following the GitHub instructions.
- 4.In the Editor, set the runtime IP address and log in to it.
- 5.Write a ladder or structured text program and upload it to the runtime.
- Runtime v4 has no web page at port 8443; connect to it from the Editor instead.
- The old OpenPLC_v3 runtime has been replaced by Runtime v4.
Official download pageautonomylogic.com - 10Free trial: 21 days
S7-PLCSIM V21 (TIA Portal) Trial
Siemens
- Runs on
- Windows 11 Pro or Enterprise 64-bit (24H2), Windows 10 Enterprise 2021 LTSC, or Windows Server 2022/2025. Windows 11 Home is supported only for the Basic editions.
- Account
- A free Siemens account registered for Industry Online Support (SiePortal)
- Size
- about 2.5 GB (ISO)
S7-PLCSIM V21 is offered as a 21-day trial on the same Siemens page as the STEP 7 and WinCC V21 trial. It needs STEP 7 V21 installed on the same PC.
Steps
- 1.Open the Siemens STEP 7 and WinCC V21 trial page (entry 109989774) and sign in.
- 2.Install STEP 7 V21 from the main TIA Portal ISO first.
- 3.Download S7-PLCSIM_V21.iso (2.5 GB) from the section Download S7-PLCSIM Standard V21.
- 4.Mount the ISO, run Start.exe as administrator and follow the setup.
- 5.In TIA Portal, select your CPU and click Start simulation to open PLCSIM.
- Siemens notes that the PLCSIM Standard V21 installation also includes S7-PLCSIM Advanced V8.0.
Official download pagesupport.industry.siemens.com - 11Free for personal use, education and small businesses
Docker Desktop
Docker, Inc.
- Runs on
- Windows 10 64-bit version 22H2 (build 19045) or Windows 11 64-bit version 23H2 (build 22631) or later, with WSL 2 and hardware virtualisation on, 8 GB RAM. Also macOS and Linux.
- Account
- None needed
Free for personal use, education, non-commercial open source projects, and businesses with fewer than 250 employees and less than 10 million US dollars in annual revenue. Larger businesses need a paid subscription. Docker Engine on Linux is open source and is not covered by these terms.
Steps
- 1.Open docker.com/products/docker-desktop and download the installer for your system.
- 2.On Windows, install WSL first (wsl --install) if you do not have it.
- 3.Run the installer and keep the WSL 2 option selected.
- 4.Restart if asked, then start Docker Desktop and accept the subscription terms.
- 5.Open a terminal and run: docker run hello-world
- Turn on virtualisation in BIOS or UEFI if Docker says it is not available.
- On Linux servers, install Docker Engine instead of Docker Desktop.
Official download pagedocker.comAlternatives
- Docker Engine (Linux): Free, open source engine for Linux. Not covered by the Docker Desktop subscription terms.
Checked against each maker's own page on 27 September 2026. Trial lengths and editions change; the maker's page is the final word.
Practise in the 3D 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.
- Check the AI's work: financeAI Workbench, about 20 minOpen in the lab (opens in a new tab): Check the AI's work: finance
- A safe agentAI Workbench, about 30 minOpen in the lab (opens in a new tab): A safe agent
Optional. Skip it whenever you like: it never blocks your progress or your certificate.
Course project, about 10 hours
Building a tank skid dashboard with an AI coding agent: spec, tests, review log and a read-only data path
Use Claude Code, Cursor or GitHub Copilot to build a small dashboard for a chilled glycol buffer tank. It reads the CSV written by the course's Modbus logger, shows the latest good values, raises high and low alarms and reports data availability. You write the spec and the tests first, review everything the agent produces and keep the data path read only.
- 5documents in the pack
- 7steps to follow
- 6things to hand in
- 10 hof work, at your pace
- FDSFunctional specification: T-101 buffer tank dashboard
- Tag listTag list: T-101 dashboard
- Risk registerRisk register: building the dashboard with an AI agent
- Test reportTest report: T-101 dashboard, version A
- ReportAI review log: what the agent produced and what was changed
The project is optional practice. The certificate needs only the modules and the final assessment.
After the course, your next step
Show what you can do, then keep going in the same field.
A certificate you can verify
Finish the modules and pass the final assessment (15 questions, pass mark 60%) and you can add a certificate with a public verification page. One-off, US$23.99 for you. It is not a vendor credential.
Want a free certificate? Do the matching Free internship: 4 weeks, nothing to buy, with a free certificate of completion.
Generative AI and Prompt Engineering
Eight short weeks of how language models work, prompting that gets better answers, and the risks to manage: notes, diagrams, a few videos and worked exercises. Finish weeks 1 to 4 and the final, then claim a free Internship Completion Certificate with your real dates and study hours, and a QR code anyone can scan to verify it. Training, not employment.
See the internshipMore free courses
Roles that use this skill
- AI engineer
- Machine learning engineer
- Data analyst
- Automation developer
These are the kinds of roles where the skill is used. We make no promise of a job or an interview.
Plain notes
- Free: the whole course, the notes, the practice tasks, the final assessment and support from practising engineers.
- Paid, and optional: the course certificate, and the Engineer-verified internship (the Free internship costs nothing).
- No job promise: the course teaches a skill. It does not place you in a job.
- Lessons by: Anthropic, Tech With Tim, freeCodeCamp.org, Cursor, Visual Studio Code, GitHub, IBM Technology, Microsoft Developer, Corey Schafer, Jakob Sagatowski. Independent creators; the lessons stream from their own channels. EDWartens wrote the study plan, notes, practice tasks and assessments.
Anthropic · Tech With Tim · freeCodeCamp.org · Cursor · Visual Studio Code · GitHub · IBM Technology · Microsoft Developer · Owain Lewis · John Kim · Corey Schafer · Snyk · SiteGround.com · Nate Herk | AI Automation · Fuzz Puppy · APMonitor.com · Fusion Automate · Siemens Knowledge Hub · Jakob Sagatowski · Automatedo · LEARNACON. If you are one of these creators and want a lesson removed or credited differently, write to info@edwartens.com.
Practise what you learn in the free 3D 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.
Why learn with EDWartens
What you get with this course, and what comes after it.
- Free from the first lesson to the final assessment.
- Practice in a free 3D lab in your browser, with nothing to install.
- Video lessons with written notes and a project.
- An optional certificate that anyone can verify online.
- Free internships to keep practising afterwards.
Common questions
Who is the AI Coding for Engineers 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. It must also be tested in a simulator such as PLCSIM, CODESYS or OpenPLC before it goes near a machine. 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 AI Coding for Engineers 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 does the AI Coding for Engineers course give?
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 AI Coding for Engineers 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 in the AI Coding for Engineers course?
You build a small dashboard for a clear-water tank skid at a textile processing unit, working with an AI agent. You produce a specification, a tag list, tests written first, a read-only data path, a risk register and a test report. You also keep an honest log of what the agent produced and what you changed.
Do I have to use the lab?
No. The lab is optional practice. You can skip it whenever you like, and it never blocks your progress, the final assessment or your certificate.
Is the lab free?
Yes. Every lab level for this course opens in your browser, free, with nothing to install.
What topics does the AI Coding for Engineers course cover, module by module?
The AI Coding for Engineers course has 13 modules. It opens with "What agentic coding is, and what it is not", goes through "Setting up Claude Code", "Spec first: prompting an agent for code", "MCP and tool use" and "Structured Text with AI: check every line, simulate before the machine" and ends with "Final Assessment". The full list with minutes is under "What you learn" on this page.
What can I do after the AI Coding for Engineers course?
After the AI Coding for Engineers course: 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. These are the practical outcomes the course is written around, and the final assessment of 15 questions checks them.
What software and hardware do I need for the AI Coding for Engineers course, and does it cost anything?
For the AI Coding for Engineers course, 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. The course itself is free.
Is the AI Coding for Engineers course suitable for me, and what level is it?
AI Coding for Engineers is rated beginner. Beginner to intermediate. For engineers who script or want to: PLC and SCADA engineers, data and AI learners, and engineering students. You should be able to read a short Python program; no professional software experience is needed. It is written for engineers who script: PLC and SCADA engineers, data and AI learners, and engineering students, and takes about 15.3 hours at your own pace.
Which jobs use the skills from the AI Coding for Engineers course?
Skills from the AI Coding for Engineers course (for example: explain what a coding agent does and which engineering tasks to give it) are used in roles such as AI engineer, machine learning engineer, data analyst and automation developer, and in automation software engineer work. The course gives you practical evidence of the skill; it does not promise a job, and employers decide on experience and interview.
Start free today
AI Coding for Engineers: Claude Code, Cursor and Copilot, at your own pace. Add the certificate only if you want one.