Interactive lessons · General-purpose

Google Teachable Machine

Train a small model to recognize images, sounds, or poses, then test how its examples affect its predictions.

Teach AI conceptsCreate visuals & media
Open Google Teachable Machine ↗Official getting-started help ↗

For: Educators demonstrating machine learning with teacher-prepared examples. Documentation reviewed November 7, 2026.

Is it a good fit for your task?

Choose it when…

A visible demonstration of classification, testing, and dataset limitations.

Consider another approach when…

Identifying students, inferring personal traits, or making assessment decisions.

A practical first workflow

Show how training examples shape a model’s predictions

Have this ready

Photograph two ordinary objects against several backgrounds. Reserve some photos for testing rather than training.

  1. Start an image project and name two classes after the objects.
  2. Add several varied examples to each class; keep the reserved test images separate.
  3. Train the model, then try the reserved images in its preview.
  4. Record mistakes and change one factor, such as lighting or background. Add examples and retrain.
  5. Compare the two test rounds and explain which patterns the model may have learned.
You’ll have: A small image classifier plus a teacher-created record of correct and incorrect predictions.

Try this example

Use this sample prompt or task input as a starting point. Adapt the subject and level to your learners.

Class A: a pencil. Class B: a marker. Train with varied angles, then test each object on a different desk.

Check your result before sharing

Check performance on unseen examples. Discuss why confident predictions can still be wrong.

Use non-sensitive object samples. A classroom model is an experiment, not a reliable decision system for people.

Other activities to explore

Keep the official guide beside you

Menus and included features can vary by account or plan. Use the provider’s instructions if your screen differs.

This workflow is an editorial suggestion based on documentation, not a hands-on test or a claim of learning gains. Check school approval, current pricing, and student account eligibility before a classroom rollout. Use public or permitted samples and keep identifiable student information out of unapproved services.

Compare another route to your goal

Back to all 100 AI tools →Build your teaching skills →