Level 1 ● Blue: track card

Coding goal: Explain how one user input meets a rule and produces a response; distinguish a Show page from a Respond tool.

These are planning estimates, not measured learner completion times. Keep the whole-room schedule. Use generation time to check content, write expectations or review the plan; do not fill it with cosmetic changes.

Evidence to leave with:

• Show and Respond versions use the same teacher-checked content or preparation steps.
• Explain one input, its decision or rule, and the visible response in your own words.
• Run all three success checks on the final Respond artifact and record expected and observed results.
• A partner uses the tool without coaching and contributes a finding or clarified requirement.
• Save the tested version and name any unmet check honestly on your station card.

Sprint 1: fifty minutes

At elapsed minute 20, save the available version, even if partial. A saved reference page, current project backup or numbered file is evidence of progress; name what still fails.

Peer testing: In the 20-minute swap, use the story/setup and two nine-minute silent tests. Your partner runs the three checks and two relevant edge cases, logs a finding, and hands back the most serious issue.

Sprint 2: twenty minutes

If stuck: At the save point, save what exists and raise a sticky note. With a helper, use your menu scaffold or a checked starter and focus on one useful interaction. Record unmet checks; do not spend the session on login, generation waiting or cosmetic changes.

If ready: When all three checks pass, use S12 first for a personal workflow. Otherwise choose one useful stretch: handoff, explaining feedback or comparing the same checks in a second permitted tool. Skip a card whose behaviour already exists.

Do not pretend a partial tool is finished. The final version is ready when its success checks pass; record every unmet check honestly. Use the four-minute retest for the changed or new case and three short core checks. Start content and access review during Sprint 1; ask a helper to review code and Network activity in parallel. If a check needs longer, record Not run, its next action and the version saved. Do not claim a pass or finished delivery from an incomplete run.

Explain one behaviour

Fill this in using your actual tool and explain it to your partner without reading the AI reply. Point to the governing instruction in your spec. HTML gives the page its structure, CSS its appearance, and JavaScript the responses to actions; you do not need to memorise syntax to explain the behaviour.

For menu 9, use complete, undo or Reset and explain the remaining count. For a classroom quiz, use a selected answer or an empty Check. Say what changes between Show and Respond: the same checked content gains a response to the user's action.

Your build menu item (card 13) has this spec ready-made, as a Show prompt and a Respond prompt: fill in their blanks. The blank shape below (card 03, version A) is for a problem the menu doesn't cover. Check every question, label and answer yourself before you paste: don't rely on the tool to check them.

Teacher workflow, including menu 9: use its Show and Respond prompts on card 13 instead of the classroom scaffold below. Use complete, undo, reset and empty-state checks; add no quiz, right/wrong feedback, wrong-try rule or retrieval question. Your own preparation task is an equally valid outcome.

• Show build first: keep only the Show part of the "It should" line, and delete the "After two wrong tries" line. Check at a glance: it opens, it reads well at phone width, every fact is right. Narrow the browser window to its smallest, or send the file to your phone. Save it. Canva: Your save point is the version number.
• Then your Respond build: in a fresh chat, keep only the Respond part and the "After two wrong tries" line, and use your canvas's three success checks.

Build a single web page for [who: year group or age] in [subject].
The change I want: after using it, they can [outcome].
It should [Show: show … | Respond: ask … and, after each answer, say whether it is right and explain why].
After two wrong tries on a question, it says "Ask your teacher" or shows a worked example.
The content is: [paste your questions, labels or steps, checked by you].
It must work on a phone and with a keyboard alone, and show right and wrong in words, not colour alone.
It must never: ask for names or save anything; call AI or any website; use timers, points, leaderboards or confetti; [your own red line].
It is working when:
1. [success check 1]
2. [success check 2]
3. [success check 3]
Give me one self-contained HTML file. Before you build, tell me in three lines what you will make.

Before you paste, write down three things you expect to see and one thing you expect it to get wrong.

• Canva: Canva builds straight away. Open the preview.
• AI chat tools only: the prompt asks it to tell you in three lines what it will make before it builds. Read them, correct anything wrong, then reply "Go ahead". If it builds straight away, check what it made against your spec.

Then run your success checks one at a time, exactly as written.

• Save a version. Level 1 ● Blue in Canva: Your save point is the version number. In an AI chat tool: download the file, or copy the code into a file (card 09), and name it [toolname]-v1.html.
• Rate yourself. Stuck: a sticky note on your laptop lid; a helper comes. On track: carry on. Ready for more: take a stretch card (card 14).

Find your test partner before the break. Pair with anyone at a different level; if you can't, pair with someone who hasn't seen your build. Sit next to them when you come back. An odd number makes one trio, with 6-minute turns.

1. The maker hands over the tool, the canvas and this card, then says nothing until the turn ends.
2. The tester runs each success check exactly as written, then tries two relevant edge cases from card 05: for a quiz, try no answer or a right answer in another form; for a workflow, try repeated use or an empty list; test keyboard use and phone width too. For phone width: Narrow the browser window to its smallest, or send the file to your phone.
3. The tester logs each failure in the bug log below: Check / Expected / What happened.
4. Swap roles.

Bug log. The tester writes here, on the maker's card.

Fix failed checks only: no new features. If none failed, write one new boundary check or clarify an unclear requirement; test it and repair only a real failure. One change per prompt. Re-run the check, then the others. Save each version that passes: in Canva, note the version number; in an AI chat tool, save it as -v2, -v3.

Success check [number] failed. When I [what I did], I expected [what should happen], but [what happened]. Fix only this.
Keep everything else unchanged. Explain what you changed and how I'd check it.

Every check passes? A personal workflow takes S12 first: another person uses the final artifact unaided and contributes a requirement or finding. For other builds, choose S12 or a useful card on card 14. S1 is optional: compare the same three checks in a second permitted tool and explain a difference. Skip a stretch whose behaviour already exists.

• Ready for more at the save point? Move to Level 2 ▲ Orange: take your own problem into the headed spec (card 03, version B) and pick up track card 11.
• Your checks before anyone else uses it: card 08, safe building, then quality items 1, 2, 3, 4 and 9, then its light accessibility check. Canva builds need internet; skip the offline test.

The whole kit: www.deepeducationnetwork.com/courses/build-with-ai/kit