Skip to content

AI adventures for young learners

Help kids understand AI through play.

Join Dogo on hands-on adventures: teach it with examples, guide it with feedback, and check its answers.

Cinematic scenes and actual gameplay

Meet Mindogo

Our approach & sources

Real AI ideas behind every adventure.

Read our approach & sources

Our games draw on established AI ideas. You can explore the sources and see what we’ve simplified for play.

For parents

Before you begin

What is Mindogo, and what can children learn?

Mindogo is an AI learning game for young learners. Through hands-on adventures with Dogo, children explore how AI learns, why it makes mistakes, and how to improve its results. No coding knowledge is needed.
See all missions

Who is it for? Should a parent join in?

Curious young learners who can read short instructions and enjoy trying things out. Play the first mission together to see if it fits. Then let your child make the decisions, helping with reading or controls when needed.

What device do we need?

Missions work on phones, tablets, and computers. A larger screen makes it easier to compare maps, evidence, and results.

Do we need an account? How is progress saved?

Missions 01–05 need no account and save progress in this browser. A verified parent account can sync progress. Purchased access is linked to the account used at checkout.

Do the games use real large language models?

They use controlled, repeatable teaching models that show key principles, rather than every mechanism of a commercial model. Children do not need to send chat messages to an external AI service.

How do free access and purchasing differ?

The first five missions are free with no account. The remaining released missions unlock with a one-time purchase and no automatic renewal. See the pricing page for prices, included content, and refunds.
Pricing & purchase

Reference / Stanford CS229
CS229 Lecture Notes

Stanford University · Course notes

CS229 Machine Learning

CS229 Lecture Notes
Tengyu Ma · Andrew Ng

Stanford University · CS229
Version cited: August 23, 2026

Visit the Stanford course website

What the source supports

The notes describe clustering as grouping similar examples using features of the data, without predefined class labels. Chapter 10 introduces k-means as one way to do this.

How it informs the missions

In Starlight Radio, children adjust the grouping rule and observe similar rhythms forming groups. In the first act of Homebound Rescue, they compare rhythms, paths, and waveforms to group unlabeled signals into channels. Both make grouping by similarity something children can observe and explain.

Limits of the reference

The radio setting, rhythm features, and grouping rules are teaching choices, not an implementation of the chapter’s k-means algorithm. The notes support the underlying idea, not measured learning outcomes in children or endorsement by Stanford University or the authors.