Turning Lessons into Games: My Journey with Canva Code

Monday 21st July 2025

Preview image for previous post

↪ Replying to: “I used AI to build vital tools for teaching.”

Sunday 27th April 2025

From binary games to packet simulators, I've discussed how I have used AI to build vital tools for teaching. The journey started with Claude, then tried ChatGPT’s Canvas, and now I use Canva’s AI tools.

Introduction

During our first Teach First in-person training day, we were given a talk from Becci Peters about a unique use of LLM models, specifically Claude.ai. This use was creating generated artefacts, React-based webpages that can be shared with the public via a URL. During the training day we were encouraged to build a tool for teaching, and I built a small Binary number converter widget.

Although only given 10 minutes or so to write a Prompt and generate a widget, I could already see the potential, combining this feature with my own experience of prompt engineering. All I needed was a useful application for this tool in the classroom, and at the end of Term 1, an opportunity presented itself.

Claude AI Artefacts

I used these technology to build a searching and sorting algorithms Visualiser for use with my Year 11 pupils. The wonderful features of this widget is being able to pick which sort or sort, enter or generate a dataset and then see the algorithm in action. These provided a wonderful demonstration of these algorithms for the pupils to watch and engage with.

However, I saw potential. I have found that pupils sometimes struggle with the tag-based structure of HTML programming. I needed a simpler interface for pupils to program in HTML. I looked at programs like Scratch and Trinket.io that provide block-based programming. I therefore used Claude to build a drag-and-drop ‘code editor’ for HTML. Pupils can drag the blocks together to build their websites, add images by dragging an image onto the screen and even apply CSS styling via a list on the side of the page. This was the pot realised although there were so problems faced.

The main problem faced was with the Context Window (context-length) in generations. Claude had a limit on the amount of content (code) the LLM chatbot can generate, and sometimes the code would stop in the middle of the code or not let me prompt the chat any further.

The solution to this was to create new versions of the tool, with my changes and additions added to the prompt. In other words, regenerate the tool with the changes in a new chat window. This worked but felt incredibly clunky to use and made tweaking and refining the tool quite challenging.

ChatGPT Canvas

This process soon became available for ChatGPT through their Canvas feature. This worked a lot better for creating a back-and-forth prompting process and meant I could guide the tool creation much more successfully. I used this to build ‘The Binary Game’; a worksheet I had designed that I instead gamified into a web widget that the pupils could play. This was a fantastic little creation and the pupils responded really well to it.

Canva Code

This changed everything!

Most recently Canva brought out a feature in their Canva Create event called “Canva Code”, where uses can ask Canva to create a webpage / web widget and then it can be used in a design and published to a webpage. Immediately after trying it, the widgets I was able to create were vastly superior to ChatGPT’s Canvas or Claude’s Artefacts. These apps were built using Tailwind for styling, and could create animations, intractable elements and so much more. I’ve been creating tools ever since, with this as my go-to creator, instead of Claude or ChatGPT.

So far these have included a ‘Packet Switching Simulator’, an improved version of my ‘Searching and Sorting Algorithm Visualiser’ and an ‘interactive web design demo’. I’ve put the ‘Packet Switching Simulator’ into my lesson when teaching networks to Year 7 pupils, and they loved it. It’s already on version 3, as I’ve kept thinking of changes and improvements to make to it. Also with this network’s topic, I built a ‘Network Bandwidth Simulator' to show more devices and data affect the speed of the network.

So far I have not noticed a context or generation limit and have been able to generate apps with upwards of 1200 lines of code. There’s also been no limit to the number of prompts I have been able to send, with upwards of 12 back and forths for my ‘interactive web design demo’ app.

Conclusion

This is the best use of AI models in teaching, in my opinion. Taking an idea we have and want to show to our pupils, and making it a reality, quickly and easily. To build this ourselves would take far too long, alongside the normal teacher workload, so this speeds up creating more interactive and engaging lessons. I cannot wait to try this more and take it even further.

Preview image for previous post

↪ Replying to: “I built more vital tools using AI.”

Wednesday 28th May 2025

I've discussed more of my web widgets created using AI, filled with a variety of different tools, that can all be found on my website.

Since my last post about using AI to build interactive webpages to help teaching, I've experimented with creating even more resources that I wish to detail here for your own use. These were built using CanvaCode, by far the best solution for creating these interactive pages, at present.

Networks (Topology) Builder - Game

A game that invites users to connect components together to create different networks. The later levels focus on Network Topologies such as Star, Bus, Ring, etc.). A great visual tool for understanding how network Topology can be arranged.

Screenshot of Networks (Topology) Builder Game
Networks Builder Game

Computer Science (OCR) Revision Minesweeper - Game

For the pupils who enjoy playing games, this game features OCR multiple choice questions built into the traditional game of minesweeper. Questions are asked for each square revealed and as a 'save yourself from losing' last chance.

Screenshot of Computer Science Revision Minesweeper Game
Revision Minesweeper

HTML Drag-and-Drop Block-Based Editor - Version 2

(original / alternative)

The same tool (a drag-and-drop editor for HTML) in two different versions. When building this refined version of my earlier Claude widget, I tried two different approaches that led to different user interfaces of the same toolset.

Ciphers (Encryption/Decryption) Visualiser

A helpful webpage for encrypting and decrypting messages to teach pupils about Ciphers and network security Encryption. The Caesar Cipher is the main focus with other more complex ciphers also available.

Number System Explorer

Calling back to my first test on that Teach First Training Day, this is a more refined converter between different number systems, including Binary, Hexadecimal, octal, and Base64. This fits well into a lesson / unit on data representation.

Final Comments

I've learnt even more about developing these interactive webpages using Canva Code. Feel free to use and experiment with these tools (or similar) and please share your own experiences with me.

This is the third in a trilogy of posts about using AI to build web apps, to use as resources in the classroom. My previous creations and experiments have been incredibly varied, whilst today will remain focused on the idea of building educational games, how gamification can help a classroom and how Canva can be used to build these resources.

Introduction

Earlier this year, I began building resources to aid with teaching, mainly simulators and demonstrations to act as a visual representation of more abstract concepts that could be shared with pupils for them to refer back to. However, occasionally I would attempt to build a type of game for the pupils to use as a revision exercise, usually based around answering questions. A good example of this is my OCR GCSE Minesweeper Game which acted as an additional method of knowledge revision, but in a fun and interactive way.

There is a strong need for gamified elements within the classrooms. It feels like almost every lesson, pupils ask to play a Blooket quiz or they ask if they can play games. After making the GCSE Minesweeper Game, I had an idea to try incorporating games that the pupils like, but with educational elements. And as seen with the Minesweeper Game, AI seemed like the quickest way to go, without putting more workload onto an already busy year. That’s where CanvaCode enters the story. A tool that let me turn my lesson content into full-on playable games.

Gamification

Gamification refers to taking lesson activities and introduce ‘game’ mechanics to make the lessons more engaging for pupils. Some of the advantages of gamification include:

  • Increased engagement with pupils
  • Retention through repetition
  • Motivation via competition and/or rewards
  • Natural Differentiation

One way that this can be done by using existing activities and introducing a scoring system and leaderboard. This promotes healthy competition between pupils in the class, and a reward can be offered later.

Enter Canva Code!

With this growing interest in gamification, I began to explore which tools could help me bring these ideas to life easily… Which is where Canva Code came into play.

The Game Development Process

I started simple, with a Matching Game where pupils 1) match up the tool with its description and 2) match up a scenario with what tool you would use.

Screenshot of SketchUp Matching Game
SketchUp Matching Game

Prompting

Throughout all of this process, I refined my ‘core prompting phrases’ to control and guide the output towards a desired output. Here are a few of the tricks I learnt to get better control and better outputs over the Canva Code generations.

  1. As these games rely on the educational aspect for use in the classroom, I needed to ensure that the information was correct. Before getting Canva Code to generate any code, I asked it to detail what the game would be like and what the educational questions / answers would be. This allowed me to check for Hallucinations.
    Before you generate any code, I would like you to describe the features of the game in detail, and show me what educational question/answers you are going to use

  2. After the initial generation of the game, the next steps for refinements and improvements through play testing. Typically, the initial results were very simplified, so (after all the gameplay mechanics had been tested), I would ask Canva Code to:
    improve the style to make it more modern, incorporating clear colours, clear text, clear graphics and animations
    .

Reflections

One of the unexpected strengths of these games was how naturally they supported Differentiation. Due to the level-based and self-paced nature of these games, pupils could progress at their own speeds. The visual and interactive nature of the games supported a broader range of learning styles, removing the sometimes text-heavy approaches of traditional worksheets. Pupils with SEND responded well to the gamified elements and it led to some really great lessons for them.

A webpage containing all my resources can be found at resources.thetommyverse.com