BUILD SOMETHING USABLE
Build something
you can use.
Explore the campus module, then identify one small interaction that would help students think in your course.
Make the behaviour serve the learning
The demonstration module turns the campus transport brief into something a learner can operate. Selecting a mode changes the visible records and descriptive averages. Reasoning checks respond to an answer, and a reflection invites a recommendation. These behaviours give us concrete questions to ask about usefulness, accuracy, and access.
Explore the finished example.
A small, complete learning experience built from the supplied brief, scenario, and dataset.
Choose your first small build.
Adapt one of the talk’s prompts to your course and approved materials.
Create an explanation, practice, feedback, and reflection in one local page.
Read COURSE_BRIEF.md and APPROVED_READING.md. Plan a 10-minute introductory learning module about evaluating a campus sustainability decision. Show the learning outcome, student journey, proposed sections, and acceptance checks before building. After I approve the plan, create module.html with an outcome, a concise explanation grounded only in the supplied reading, one worked comparison, a practice decision with explanatory feedback, and a two-sentence exit-ticket prompt. Label the authored teaching reading accurately; do not invent external citations. Include a source note and a printable view. Use one self-contained HTML file with inline CSS and JavaScript. It must open by double-clicking the file, with no build step, external library, network request, API key, account, or learner-data collection. Use semantic headings, explicit form labels, keyboard controls, visible focus, readable contrast, and feedback that does not depend on colour alone. Keep student answers only in page memory until reset or reload. Do not promise LMS gradebook integration.
Copy the starter kit into your project first. Review the proposed files and plan before building.
Read COURSE_BRIEF.md and APPROVED_READING.md. Plan a 10-minute introductory learning module about evaluating a campus sustainability decision. Show the learning outcome, student journey, proposed sections, and acceptance checks before building. After I approve the plan, create module.html with an outcome, a concise explanation grounded only in the supplied reading, one worked comparison, a practice decision with explanatory feedback, and a two-sentence exit-ticket prompt. Label the authored teaching reading accurately; do not invent external citations. Include a source note and a printable view. Use one self-contained HTML file with inline CSS and JavaScript. It must open by double-clicking the file, with no build step, external library, network request, API key, account, or learner-data collection. Use semantic headings, explicit form labels, keyboard controls, visible focus, readable contrast, and feedback that does not depend on colour alone. Keep student answers only in page memory until reset or reload. Do not promise LMS gradebook integration.Read the course brief and approved teaching reading. Design a campus sustainability decision scenario with exactly three sequential decision points and two options at each point. Keep all eight choice sequences reachable. Branch-specific consequences may differ, but every sequence must reach a debrief about evidence, stakeholder priorities and trade-offs. First save scenario-map.md with each decision, the two options, immediate feedback, possible accumulated consequences and all eight terminal sequences. Use fictional context and no unsupported claims about a real institution. After I approve the map, build scenario.html. Include a visible record of the learner's choices, a debrief, and restart. Ask the learner to defend one trade-off; do not reduce a defensible policy choice to a single simplistic right answer. Use one self-contained HTML file with inline CSS and JavaScript. It must open by double-clicking the file, with no build step, external library, network request, API key, account, or learner-data collection. Use semantic headings, explicit form labels, keyboard controls, visible focus, readable contrast, and feedback that does not depend on colour alone. Also save a path-test.md table recording the eight paths and whether each reaches its debrief.Read sample-data.csv first and report its actual columns, units, row count and missing values. Propose one learning question this synthetic campus transit dataset can support. Do not invent columns or treat the observations as causal evidence. After I approve, build transit-explorer.html: embed the exact CSV rows in the file; offer one meaningful category filter; show a clearly labelled bar chart, count of included rows, the displayed summary calculation, and the matching source rows in an accessible table. Use a zero baseline for bars. Distinguish totals, averages and percentages and state the denominator. Include three interpretation questions and a revealable teaching note explaining one limitation. Handle an empty result with a readable message. Use one self-contained HTML file with inline CSS and JavaScript. It must open by double-clicking the file, with no build step, external library, network request, API key, account, or learner-data collection. Use semantic headings, explicit form labels, keyboard controls, visible focus, readable contrast, and feedback that does not depend on colour alone. If the file lacks the fields needed for the requested chart, explain the mismatch and propose a supported chart instead. Save data-check.md comparing three displayed results with calculations from the underlying rows.Look for an intellectual move
A control is useful when it helps the learner notice, predict, compare, or explain something. Before changing a filter, ask what pattern students expect. Afterward, ask what the display actually shows and which conclusion would go beyond the evidence. The sixteen synthetic commute records are useful for practising that distinction: a group mean describes these records, while a claim about a proposed intervention needs different evidence. Explore the embedded module with those questions in mind. For your own build, name the student action and the evidence it will reveal before requesting another button or visual effect.
Build a small complete version
Ask Cursor, Antigravity, or another suitable environment to propose the content, student journey, files, and checks. Review the plan, then build a resource you can open independently. A single local page can contain an explanation, practice, feedback, and an exit question. A branching case can support a consequential choice, provided its paths and feedback remain coherent. The bundled examples use authored scenarios and synthetic records, allowing faculty to practise without real student data. Keep the input files intact and save drafts separately. When a requested feature depends on an unavailable tool, ask for a simpler output you can still inspect.
Test the learner's whole journey
Begin at the opening instruction and complete the intended task. Try an unanswered item, a plausible wrong answer, a changed selection, and a restart. Check calculations against source rows and confirm that the feedback addresses the reasoning rather than rewarding one preferred policy choice. Use a keyboard, enlarge the text, and inspect whether controls and explanations remain usable. An automated report can support these observations but does not establish complete accessibility. Ask a colleague to follow the visible instructions without your extra explanation. Their hesitation may reveal a problem that code checks missed. Record what you actually tested and what still needs review.
PUT THE IDEA TO WORK
Try this in your course.
Create a case with a decision
Build a fictional case with competing priorities, enough evidence, and a decision students must justify.
Build a one-page module
Ask Cursor or Antigravity to turn your brief into a local web page with outcomes, explanation, practice, and an exit ticket.
Build a branching scenario
Turn a case into three decision points with consequences and feedback. Map every path before generating the page.
Let students explore data
Use a small synthetic dataset to build a filterable chart and interpretation questions. Check the chart against the source rows.