Nine Job Cards, Three system station cards, System Map
Open mission materials →
Concept art made with Gemini 3.1 Flash ImageSpirit Squad: Three-Mind Stage
Three stage systems are shouting at once. Route every job correctly before Vela's boss spotlight lands.
Classifier, Gemini, or rule?
Use a classifier for labels, Gemini for drafts, and rules for exact decisions.
Start here
Sort nine crisis cards and fire one three-system team combo.
All nine jobs reach the correct station.
System Map v1 and the squad attack
See how this game works
Game loop preview
See the power before you build it.
- 1SignalA new game job
- 2AI moveThe right kind of system takes the job
- 3Your ruleThe exact game logic checks what happens next.
- 4Game stateGEMINI DRAFT
Your mission
One step at a time. One AI power to unlock.
Meet the mission problem.
Story signal: Three stage systems are shouting at once. Route every job correctly before Vela's boss spotlight lands.
Do this now
- 1LOOK
Spot the problem in the opening story and tell your crew what needs to change.
Know what winning looks like.
Your choice: Choose which system handles each game job.
Watch this change: The right station returns a label, a draft, or an exact decision.
Do this now
- 2CHOOSE
Win by proving this: All nine jobs reach the correct station.
Gather the props and get your grown-up guide.
Do this now
- 3CHECK
Open the Mission 3 materials on screen or print them, then gather the listed props.
- 4CHECK
Use the supplied fictional character and game details. An adult enters and reviews the prompt.
Guess first, then test.
Do this now
- 5CHOOSE
Read one game job and predict which station should handle it.
Make the AI power in the Google tool.
Do this now
- 6MAKE
Follow the Google tool card below. Complete each step in order, then bring the visible result back here.
Google tool step
Open the tool, make the power, then bring one result back.
Teachable Machine
Adult and child operate together
Do these steps
- Open Image Model v1.
- Show one prop input.
- Observe the predicted label and score.
- Return without retraining.
You are done whenThe classifier produces a learned label and score, not a story or fixed rule.
Need setup help?
- Bring
- Image Model v1
- Three classifier Job Cards
- Next move
- Place the classifier output in the System Map.
- If stuck
- Use the supplied prediction sample if the saved project cannot be opened.
Gemini
Adult operates; child directs and reviews
Do these steps
- Open Gemini on the adult account.
- Submit the fictional job prompt.
- Review the draft together.
- Copy only the chosen fictional draft onto the System Map.
- Close the chat when the comparison is complete.
You are done whenA fluent, variable text draft appears for review.
Need setup help?
- Bring
- One fictional story Job Card
- Supplied fictional details
- Next move
- Compare the draft output with the classifier output and exact rule.
- If stuck
- Use the supplied sample draft card if Gemini is unavailable or unsuitable for the account.
Return with the result you can see.
Do this now
- 7CHECK
Say why prompting Gemini did not retrain Image Model v1. Save the exact mission artifact as System Map v1 plus System Map v1, then return to this card.
Make a funny mistake on purpose.
Funny glitch: The improvising referee awards points for glitter instead of goals.
Do this now
- 8TEST
Give the scoring job to Gemini and compare its variable answer with the exact referee rule.
Change one thing and retry.
Game move: Fast routing gauntlet with a boss combo meter
Harder remix: Draw the full input-output diagram and mark where uncertainty enters and where exact rules begin.
Do this now
- 9REMIX
Choose one evidence-based change, run the same test again, and compare what changed.
- 10TEST
Run the boss round: The learner states that prompting does not retrain Teachable Machine.
Say what the AI did and prove it.
Power reward: System Router · System Map v1 and the squad attack
Use a classifier for labels, Gemini for drafts, and rules for exact decisions.
Choosing the right system prevents kids from treating every program as the same kind of AI.
Do this now
- 11SAY
What does each of the three systems do, and which one can still make up a fluent answer?
- 12SAVE
Complete the mission proof and save only the named artifact: System Map v1 plus System Map v1.
What counts as finished?
What does each of the three systems do, and which one can still make up a fluent answer?
- All nine jobs reach the correct station.
- The learner completes System Map v1.
- The learner states that prompting does not retrain Teachable Machine.
Need help or want a harder challenge?
Make this step easier
Match each job to a lens icon, spark icon, or gear icon before explaining it aloud.
Say it this way: The AI noticed ___. The exact game rule ___. I know because ___.
Try the deeper remix
Draw the full input-output diagram and mark where uncertainty enters and where exact rules begin.
- Record the inputs and outputs.
- Compare two versions or conditions.
- Name the constraint or exact rule.
- Design one fair remix test.
Everyone proves the same AI idea: All nine jobs reach the correct station. · The learner completes System Map v1. · The learner states that prompting does not retrain Teachable Machine.
Quick power check