Val is available to all RMIT staff and students. Your prompts, files and generated code stay inside the University — no personal AI accounts needed.
Describe what you want in plain language. Val writes the code. You refine the result through conversation, not syntax — and leave with an activity ready for your own course.
We start with a simple teaching request. Val turns the description into a working interactive activity — one self-contained .html file.
Simple interest = Principal × Rate × Time
You will see a scenario. Work out the interest earned and type it in. Round to the nearest dollar.
Tell us what you teach, what students should achieve, and what the finished activity should look like. Then choose a format and we will write your starting prompt for Val.
Start with your course and topic.
Describe the learning goal in one or two sentences.
Describe what students see on screen: layout, colours, tone, what is where, what happens after each action.
Each format already carries its full description — mechanics, timing, feedback — into the prompt. Nothing else to fill in.
Whichever format you pick, the generated prompt instructs Val to design the activity so that it is:
You will see this as a labelled block in your prompt. Keep it — it is what stops Val defaulting to a recall quiz.
Use this as your starting prompt in val.rmit.edu.au. Then improve it one change at a time: content, interaction, feedback, accessibility, visual design.
my-activity.html.Your activity is one .html file. In about five minutes you can have it sitting inside a Canvas page, next to your instructions, with a fallback link for anyone whose browser blocks the frame. Follow the seven steps in order — the example alongside each step shows exactly what you should be seeing.
week5-cashflow-quiz.html, not Final version (2).html.In your Canvas course, click Files in the left-hand course menu, then the blue Upload button at the top right. Choose your .html file. Keep it at the top level of Files, or in a folder called activities — be consistent so you can find it next semester.
IN CANVAS
Click the file name. Canvas opens a preview. Now look at your browser's address bar. The address contains the two numbers you need: the course ID after /courses/ and the file ID after /files/. Write both down, or leave the tab open.
YOUR BROWSER'S ADDRESS BAR
123456 ← the number after /courses/78901234 ← the number after /files/
Type the two numbers into the generator. Set a height that fits your activity — 600 to 700 px suits most quizzes and games; a tall worked example may need 900. You can change it later. Click Generate, then Copy code.
<iframe> shows your file inside the page. The <p> underneath is a plain link to the same file that opens in a new tab — keep it. It is the fallback for phones, for anyone using a screen reader, and for the day a browser update blocks the frame.Go to Pages, open the page for that week and click Edit. First write the instruction your students need, in the normal editor — one or two lines: what to do, how long it takes, what happens afterwards. Then put the cursor on a new line where the activity should appear.
IN CANVAS — PAGE EDITOR
At the bottom right of the editor box is a small </> icon (“Switch to raw HTML editor”). Click it. The page turns into code. Scroll to the end — just after your instruction text — and paste the code you copied in step 3. Click </> again to return to the normal view.
IN CANVAS — RAW HTML EDITOR
Highlighted: the code you paste from step 3.
Click Save. The activity should now run inside the page. Then click Student View (top right of the course) and open the same page. Do the activity as a student would: answer, read the feedback, try it on your phone through the Canvas app.
IN CANVAS — SAVED PAGE, STUDENT VIEW
Before Tuesday's tutorial, complete the quiz below (about 8 minutes)…
Publish the page. In Modules, click + on the relevant week, choose Page, select your page and click Add item. Publish the item. Students now reach the activity through the week's module, with your instructions above it.
IN CANVAS — MODULES
Green row: the page you just added.
Your feedback helps us understand where vibe coding can support teaching and where more guidance is needed.
Val is available to all RMIT staff at val.rmit.edu.au. Join the vibe coding community of practice to share what you build and see what colleagues are making.
Every one of these can be built as a single .html file. Choose the level of thinking you want first, then the mechanic — and put the name and the one-line description into the Goal of your prompt. Adapted from the mechanics list of the PolyU Educational Development Centre.
Learner verbs: recall, recognise, list, order
Learner verbs: compare, classify, summarise, distinguish
Learner verbs: execute, use, select, modify
Learner verbs: differentiate, attribute, deconstruct, relate
Learner verbs: judge, critique, check, defend
Learner verbs: design, invent, formulate, compose
Everything in this workshop fits in a single .html file. Some ideas outgrow that — a live model with analytics, accounts, an AI opponent. This section is drawn from a research paper From Knowing to Doing: Design Propositions for Simulation-Based Learning Across Feedback Paradigms (Pham, Nkhoma and Le, 2026): a design recipe with its evidence base, what building a full platform took, and the judgements that stayed human.
Each step answers to a body of evidence, not to preference. The recipe applies just as well to a single-file activity.
| Step | What it means | Evidence | |
|---|---|---|---|
| 1 | Pick one misconception | Not a topic — a specific, documented student confusion. | Procedural fluency and conceptual understanding are distinct; target the gap between them (Hiebert & Lefevre, 1986). |
| 2 | Find the relationship behind it | What does the formula hide? That is your content. | Understanding is constructed by acting on relationships, not by receiving them (Piaget, 1952; Vygotsky, 1978). |
| 3 | Make it a picture | The chart is the answer; the number is a footnote. | Externalising relational structure aids understanding; offloading computation frees working memory (Mayer, 2009; Sweller, 1988). |
| 4 | Make it instant | No submit button — every change updates everything, immediately. | Feedback is among the strongest influences on learning when task-focused and timely (Hattie & Timperley, 2007; Nicol & Macfarlane-Dick, 2006). |
| 5 | Start simple, let them add | Minimal default first; complexity is opt-in, not default. | Scaffolding extends what a learner can accomplish unaided (Wood, Bruner & Ross, 1976). |
Starting assets were discipline knowledge and pedagogical instinct — not programming.
Each module began as a one-page description of the misconception and what the student should see — the five-step recipe, written down.
Conversational iteration: "make the curve respond to the slider", "hide advanced controls by default". The same refine loop you used today.
Connecting a database for analytics, linking APIs and keys, configuring deployment, reading error messages.
Expert testers found the first interface overwhelming → a progressive-disclosure redesign. No AI flagged this.
A learnable curve: weeks of tinkering, not years of programming.
Turn the brief into a component structure, data model and interaction plan — before any code. Fast and creative; the AI is a strong design partner, but you decide what is pedagogically right.
Generates and edits the code from the brief, iterated conversationally. Expect to read code you did not write and to describe bugs precisely.
Tables, keys, row-level security, analytics — and, for anything with accounts, user state. The steepest step, where most first-timers stall.
Push the repository, get a live URL in minutes. Near one-click; only environment variables and API keys need care.
A constant-cost WACC curve is impossible in theory — the designer, not the AI, knows costs must respond to leverage.
The SML plots the asset on the line by construction — deciding that this shows equilibrium, not a bug, is a disciplinary judgement.
Colleague walkthroughs caught what no AI flagged: the full interface was too much at first sight.
Every model simplifies; deciding what to disclose is disciplinary honesty.
Source: Pham, Nkhoma and Le (2026). From Knowing to Doing: Design Propositions for Simulation-Based Learning Across Feedback Paradigms. Working Paper, RMIT University. Happy to sit with you for your first build.