Home › Practical AI learning › The build collection
The Open Practice Collection
Explore practical AI. Build something useful.
Explore 36 practical AI build paths. Learn from worked examples, experiment with real tools, and take your projects from a first question to something useful.
36Build paths
266Activities
55Free resources
~177hEstimated practice
NEW / 50 GUIDED EXPERIMENTS
Make a little. Learn a lot.
Prompt experiments, source checks, creative briefs, useful data and everyday workflows. Every activity has its own cover, illustrated guide, worked example and evidence checklist.
For people across underserved and excluded regions. Check country eligibility, language, identity requirements, cost, quotas and data terms before choosing a service. Use legitimate available alternatives; never false residency or restriction bypasses. Downloaded lessons and fictional fixtures remain useful without a live provider.
Read the example. Try the activity. Test what you made. Keep your evidence. Review the limitations before you share.
“The best way to understand a tool is to make something with it—and know where it stops being useful.” — The Open Practice approach
THE OPEN PRACTICE PROMISELearn freely. Build honestly. Keep what you make.
Open lessons. Practical experiments. No accreditation claims. Just tools, understanding, and work you can show.
YOUR WORKBENCH IS WAITING
THE COMPLETE BUILD COLLECTION
06 BUILD PATHS / 36 PRACTICAL ACTIVITIES
Explore every build path.
No courses match. Try a different skill.
A FEW THINGS WORTH KNOWING
Before you begin.
Is the learning material really free?
Yes. The activities, original handbooks and practice packs are free to read and download. No payment is required. External AI providers may have their own quotas, costs and terms.
Can I learn without an account?
Yes. Explore activities and keep local notes without signing in. An account is needed for cross-device cloud saves and the learner-owned provider connection. Browser drafts do not automatically sync.
What can I use offline?
Download a standalone HTML workspace and the separate practice pack before disconnecting. The HTML includes activities, editable notes, review questions and the capstone rubric. Keep edits by downloading an updated copy. Live cloud inference requires connectivity.
Is this an accredited qualification?
No. Open Practice is independent, non-degree and non-accredited. Progress and rubric scores are learner self-reports. Keep your actual project evidence; do not present the completion indicator as verified certification.
OP ↗LEARNING WITH SOMETHING TO SHOW.
Make something useful. Keep learning from it.
Each build path ends with something you can test, explain, and keep. Completion means a self-reported practice record—not a verified qualification, accreditation, or a promise of employment.
YOUR BUILD CHALLENGE
Your workspace, your copy.
Check your understanding
Ask the workshop tutor
Checking connection…
Optional cloud AI. Your question and this course's lesson text may be sent to configured Groq, Cloudflare, and Pollinations providers, in that order by default. A failed request may be retried with the next provider. Do not enter private data. Answers can be wrong.
Practice with your own AI connection
Your key is used only for the current request through this platform server. It is not saved in an account, browser storage, downloads, or analytics. Your prompt goes to your selected provider and may use your quota or paid balance. GitHub Models is retired; a GitHub login is not an inference key.
