Score tracker, Threshold guide, ACT card
Open mission materials →
Concept art made with Gemini 3.1 Flash Image← Mission map
Mission 6 of 12Decision lab35 to 45 minutes
Mochi's Cozy Pet Cafe: Prism Panic
A fast cafe threshold serves the wrong snacks; a strict one serves nobody. Mochi needs a smarter shield.
Today's AI power
Scores and thresholds
A score shows how strong a guess is. A threshold decides whether the game acts or asks again.
Start here
Tune the threshold to protect the combo while completing one ACT and one ASK AGAIN order.
One false positive and one false negative are identified.
Prism Shield and Threshold Policy v1
See how this game works
Game loop preview
See the power before you build it.
- 1SignalA prediction score
- 2AI moveThe score meets or misses your threshold
- 3Your ruleThe exact game logic checks what happens next.
- 4Game stateASK AGAIN
Your mission
One step at a time. One AI power to unlock.
Step 1 of 9Story
Story
Meet the mission problem.
Story signal: A fast cafe threshold serves the wrong snacks; a strict one serves nobody. Mochi needs a smarter shield.
Do this now
- 1LOOK
Spot the problem in the opening story and tell your crew what needs to change.
Goal
Know what winning looks like.
Your choice: Choose a threshold by comparing the cost of both mistake types.
Watch this change: The chosen threshold visibly routes each score to ACT or ASK AGAIN.
Do this now
- 2CHOOSE
Win by proving this: One false positive and one false negative are identified.
Get ready
Gather the props and get your grown-up guide.
Do this now
- 3CHECK
Open the Mission 6 materials on screen or print them, then gather the listed props.
- 4CHECK
Use scores only for this game and let a person make every important real-world decision.
Predict
Guess first, then test.
Do this now
- 5CHOOSE
Predict what a low threshold will do to speed and mistakes.
Build
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.
OPEN TOGETHER
Teachable Machine
Adult and child operate together
Build thisExisting image project preview
Save asThreshold Policy v1
Do these steps
- Open the model preview.
- Show each score case prop.
- Read the top label and score.
- Record the score without changing it.
- Apply the exact threshold rule outside the tool.
You are done whenPrediction scores appear for the exact game rule to route into ACT or ASK AGAIN.
Need setup help?
- Bring
- Image Model v1
- Score Tracker
- Threshold Guide
- ACT and ASK AGAIN cards
- Next move
- Compare false actions and missed actions, then defend the chosen threshold.
- If stuck
- Check the label map and model input before changing the threshold.
Bring it back
Return with the result you can see.
Do this now
- 7CHECK
Send every below-threshold case to ASK AGAIN. Save the exact mission artifact as Threshold Policy v1, then return to this card.
Glitch test
Make a funny mistake on purpose.
Funny glitch: A tiny cloud-cat receives a treat shaped like a giant fish rocket.
Do this now
- 8TEST
Try the tempting fastest threshold and watch a character confidently choose the wrong prop.
Boss round
Change one thing and retry.
Game move: Cafe rush with pet reactions and a confidence prism
Harder remix: Compute the displayed game cost for two thresholds and defend the lower-cost policy.
Do this now
- 9REMIX
Choose one evidence-based change, run the same test again, and compare what changed.
- 10TEST
Run the boss round: At least one ACT and one ASK AGAIN result appear.
Explain
Say what the AI did and prove it.
Power reward: Threshold Guardian · Prism Shield and Threshold Policy v1
A score shows how strong a guess is. A threshold decides whether the game acts or asks again.
Different mistakes have different costs. Kids learn that confidence is evidence, not truth.
Do this now
- 11SAY
Why can a high score still be wrong, and when should the game ask again?
- 12SAVE
Complete the mission proof and save only the named artifact: Threshold Policy v1.
What counts as finished?
Why can a high score still be wrong, and when should the game ask again?
- One false positive and one false negative are identified.
- The chosen threshold follows the case cost table.
- At least one ACT and one ASK AGAIN result appear.
Need help or want a harder challenge?
Make this step easier
Sort cases into green ACT and gold ASK AGAIN hoops using a preset slider.
Say it this way: The AI noticed ___. The exact game rule ___. I know because ___.
Try the deeper remix
Compute the displayed game cost for two thresholds and defend the lower-cost policy.
- 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: One false positive and one false negative are identified. · The chosen threshold follows the case cost table. · At least one ACT and one ASK AGAIN result appear.
Quick power check