Wovi

Session 2 of 4 · Complete free trial edition

Example explorer

Inspect a false alarm in Reef Rescue, add the missing examples and compare the evidence behind the new prediction.

  • About 20–30 minutes
  • Ages 9–13 with an adult
  • Paper + pencil
  • No email or account
Open Reef Rescue in a new tab ↗

Read below, print, or choose “Save as PDF” in your browser. You can also copy the prompts onto plain paper. Keep written answers with your family; none are uploaded.

WOVI · SESSION 2 OF 4 · LEARNER WORKSHEET

Example explorer

Ages 9–13 with an adult · About 20–30 minutes · Free trial edition

You need: Reef Rescue at wovi.world/demo, a parent or guardian, paper and a pencil. Keep your notes; no name or upload is needed.

  1. Set up a fresh mission · 3 minutes

    Open Reef Rescue and choose Start the mission. If the game is already partway through, reload its tab to start fresh. Three examples are already selected: Healthy coral garden, Plastic fragments and Polluted runoff. Add only Heat-stressed coral, so the counter shows 4/4.

    I think these examples might miss:

  2. Predict, then inspect · 5 minutes

    Will cloudy water always mean danger? Write your prediction, then choose Train & scan four zones. Find Cloudy sand plume. Compare Wovi’s label, the ranger’s label and the closest training example. Record the overall score too.

    My prediction:

    First scan: ___ / 4 correct. Wovi says ___; ranger says ___.

    Cloudy sand plume’s closest example:

  3. Add evidence and compare · 6 minutes

    Choose Review mistakes & improve Wovi. Keep the first four examples and add Natural seaweed meadow and Passing sand current. The counter should show 6/6. Predict whether the sand-plume label will change, then choose Train & scan four zones again.

    My new prediction:

    Second scan: ___ / 4 correct. Sand plume label: ___.

    Its new closest example:

  4. Explain the change · 4 minutes

    A false alarm calls a safe case risky. A missed risk calls a risky case safe. Which happened to the sand plume on the first scan? What changed in the evidence? Choose Explain what changed in the game, then discuss your reasoning with your adult.

    The first mistake was ___ because:

    The new prediction makes sense because:

  5. Plan a more careful test · 3–6 minutes

    We added two examples together. On paper, plan a comparison that adds only Passing sand current to the first four examples. What would you keep the same? Which label would you inspect? This is a test plan: the current game requires all six examples for its second scan.

    I would keep ___ the same and inspect:

    A different reef situation I would test next:

What four correct answers do—and do not—show: We improved on the same four game cases we had already seen. That does not show how well the model will work on a new reef. Keep one result, its supporting example and one limit for your family investigation record.

Wovi AI Investigator · Session 2 · wovi.world/family-pack-session-2

Session 2 parent guide: Example explorer

WOVI · SESSION 2 OF 4 · PARENT REFERENCE

Example explorer

Ages 9–13 with an adult · About 20–30 minutes · Free trial edition

Purpose: Help the learner connect a prediction to its closest training example, distinguish a false alarm from a missed risk, and notice the limits of reusing the same test cases. Read the expected results after the learner predicts.

Prepare the exact comparison

Start a fresh Reef Rescue mission at wovi.world/demo. Reload the game tab if it is mid-mission; this restarts the current simulation. The three fixed examples are Healthy coral garden, Plastic fragments and Polluted runoff. For the first scan, select Heat-stressed coral as the one optional example, making four. Other first choices can produce different results.

Expected results for these selections on the current four cases
CheckFirst scan: 4 examplesSecond scan: all 6
Correct classifications3 / 4 (75%)4 / 4 (100%)
False alarms10
Missed risks00

Read the evidence, not just the score

In the first scan, Cloudy sand plume is predicted RISK although the ranger label is SAFE: a false alarm. Its closest example is Polluted runoff. Hidden warm pocket and Floating bottle are correctly labeled RISK; Seaweed nursery is correctly labeled SAFE. Seaweed nursery initially matches Healthy coral garden, so the missing seaweed example does not cause an error in this particular test.

What changes in the second scan?

After Review mistakes & improve Wovi, add both Natural seaweed meadow and Passing sand current, leaving the original four selected. The game enables scanning at six examples. Cloudy sand plume now matches Passing sand current and is labeled SAFE. Seaweed nursery now matches Natural seaweed meadow and remains SAFE. The other two labels stay RISK; no classification errors remain on these four cases.

Explain that this model assigns each test case the label of its nearest example. The visible closest match helps explain the changed sand-plume decision. Because this game run adds two examples at once, do not present the overall improvement as an experiment that changed only one example.

Support the learner’s explanation and next test

A useful answer is: “The first set treated harmless sand like polluted runoff. With a reviewed sand-current example, the sand plume gets a closer SAFE match.” In the game’s final question, Wovi saw more diverse evidence is the matching explanation. The world and four test cases stayed the same.

For the paper test plan, keep the first four examples, classifier and four test cases fixed; add only Passing sand current and inspect the sand-plume label and its nearest example. This describes a comparison to run in a tool that permits five examples; it is not an extra scan available in the current game. Ask for another situation too, such as heat stress combined with cloudy water, without promising how the model would classify it.

State the limit clearly

These are four fixed, hand-designed game cases. After seeing mistakes and changing the examples, scanning those same cases again is practice and debugging, not an independent test on unseen data. The displayed percentage is not real-ocean accuracy. “Match” is a distance-based display, not a calibrated probability that the answer is correct. New cases would be needed to investigate whether the rule generalizes.

Keep: the first and second results, the changed closest example, a one-example test plan and one limitation. The family keeps these paper notes; they are not uploaded or automatically assessed.

Wovi AI Investigator · Session 2 · Parent reference · wovi.world/family-pack-session-2

Keep the investigation going.

Keep this worksheet for Session 4, then continue to transfer lab when your family is ready.

Next: Transfer lab →Get all four worksheets →