Learn something new.
Make it your own.
AI, work, creativity and everyday skills. Clear lessons, concrete examples and practice at your own pace.
In-demand learning paths
ChatGPT, automation, websites and AI agents. Choose a course and start with an open lesson.
ChatGPT From Scratch: How to Use AI Every Day
A practical introduction to ChatGPT, from making a first request to building a personal kit of 10 repeatable tasks. The course explains how to write useful requests, work with photos, files and voice, check answers, protect private information, and follow rules at work or in education. Separate lessons cover memory, instructions, projects, and everyday uses such as planning food, trips, spending and paperwork. Feature names and availability may vary by product version, plan and settings.
How to Talk to AI: Prompts That Help You Get the Answer You Need
This course teaches you to give AI a clear task and improve its output systematically. You will examine why answers become generic, which context to provide, how to teach with examples, and how to specify the format. You will then practise working through a conversation, using roles when they add useful perspective, splitting large tasks into stages, checking output against criteria, testing popular prompting advice, and building a reusable prompt library. The goal is not to find one magic phrase, but to manage the task and inspect what the AI produces.
Save Time With AI: Email, Documents, Meetings and Planning
A practical course about choosing work where AI may reduce routine effort after the time needed for preparation, review, and correction is included. The programme moves through email, document reading, drafting, meetings, planning, reusable templates, limited automation, and responsible handling of work data. The final result is a measurable 30-day system with human review, data boundaries, and rules for continuing or stopping each workflow.
Coding agents: small changes you can verify
Use Codex or another officially documented coding assistant on a tiny JavaScript repository: context, bounded edits, tests, permissions, review and rollback. Requires Git and Node.js 22+. Check current account access and usage limits before starting; subscription allowances and API-key billing differ. The exercises also work manually if no included assistant usage remains.
AI n8n workflow: request to reviewed draft
Prepare a local AI pipeline with JSON schema, validators, fixture approval, stable keys and a test matrix.
Build an accessible landing page with AI
Build real HTML, CSS and JavaScript files for a fictional workshop page, using an assistant for bounded suggestions. Requires an editor, browser and basic file handling; Node.js is optional for a local server. A static local demo needs no paid API. Assistant allowances, hosting plans, domains and real form providers have separate terms and possible costs.
AI for Research: Find Information Fast and Check What’s True
This course teaches you to use AI as a research assistant without treating a confident answer as evidence. You will work through the full process: frame a checkable question, find sources, open links, verify quotations, examine numbers and studies, reconcile conflicting claims, and write a conclusion with an appropriate level of confidence. Special attention goes to research grounded in your own documents and to areas where an error can cause harm: health, money, law, and news.
Your Personal AI Assistant: Build One That Knows Your Context, No Code Needed
This course moves in order from a first personal assistant to a system you can inspect, limit, maintain, and move. You will examine five layers: memory, instructions, workspaces, reference files, and specialized roles. You will then set up short commands, regular check-ins, voice capture, and controlled access to email, calendars, and files. Dedicated parts address excessive agreement, preparing major decisions without delegating the decision itself, tracing mistakes to the responsible layer, and creating an assistant passport for maintenance or migration. The course does not promise an outcome in 20 minutes; that number remains only in the title of the programme’s first module.
OpenAI tools and agents without paid execution
Build an offline harness for current Responses function calling, structured output, approvals and evals with explicit API-budget boundaries.
Critical Thinking: Check Claims, Spot Traps and Change Your Mind Well
This course teaches you to take everyday claims apart, distinguish evidence from distraction, and avoid treating a fast answer as the right answer. You will examine five reasoning traps and five distraction tricks, then work with confirmation bias, base rates, vivid examples, and levels of confidence. Finally, you will combine these tools into one practical process: state the argument, test an alternative, estimate your confidence, keep a record of predictions, and revise a conclusion calmly when the facts change.
Local image workflows with ComfyUI
Build and review a bounded seven-node local image workflow for a fictional unbranded ceramic bowl. Requires basic file management, a supported Windows practice machine, adequate disk/RAM and a compatible GPU or slower CPU path. The course uses official ComfyUI Portable and an inspected SD1.5 checkpoint as a modest teaching baseline, not a quality recommendation. No model is executed while authoring, no paid service is required, and hardware, electricity or rented GPUs still have costs.
OpenClaw in a read-only lab
Configure an isolated Linux VM, local Gateway and Ollama, restrict the agent to reading and verify a custom skill without external actions.
Try a question
What would you like to learn?
How it works
Read a step, put it into practice and check what you remember.
Bite-sized lessons
Work at your own pace and return to any step.
A knowledge check
See your result and an explanation after answering. Try again when you need to.
Cards to remember it
Review key ideas and mark what you want to revisit.
Your own practical work
Complete a task and review your finished work with a checklist.
Start free
Start with an open lesson. Full course access includes all of its language versions.
Frequently asked questions
Is the first lesson really free?+
Yes. An open lesson and its quiz are available without payment. An account saves your progress across devices.
Does changing language reset my progress?+
No. The four language versions share progress. Your current step and your own text stay in place.
How do I get the full course?+
Start with the free lessons. Online payment for full course access is being set up.
Who reviews my practical work?+
Mentor review of practical assignments is planned. Until it is available, use the self-check checklist.
Try an open lesson
No sign-up needed to start reading.
Start the free lesson