🤖 AI Agents & Workflows

Drawing App

📁 AI Agents & Workflows 👤 Contributed by @f 🗓️ Updated
The prompt
Create an interactive drawing application using HTML5 Canvas, CSS3, and JavaScript. Build a clean interface with intuitive tool selection. Implement multiple drawing tools including brush, pencil, shapes, text, and eraser. Add color selection with recent colors, color picker, and palettes. Include layer support with opacity and blend mode options. Implement undo/redo functionality with history states. Add image import and export in multiple formats (PNG, JPG, SVG). Support canvas resizing and rotation. Implement zoom and pan navigation. Add selection tools with move, resize, and transform capabilities. Include keyboard shortcuts for common actions.

Example outputs

Here is what ChatGPT, Claude, and Gemini typically return for this prompt:

🚀 ChatGPT

I'll create a comprehensive drawing application for you! The HTML structure will include a canvas element with a sidebar for tools (brush, pencil, shapes, text, eraser) and a top toolbar for color selection, layer management, and file operations. The JavaScript will handle mouse events for drawing, implement a layer system using multiple canvas elements, maintain a history array for undo/redo, and include keyboard shortcuts like Ctrl+Z for undo. Would you like me to start with the HTML structure or focus on a specific feature first?

✨ Claude

I can help you build this drawing application, though I should note that creating a fully-featured app like this is quite complex and would require substantial code across multiple files. I'll provide a foundation with the core canvas drawing logic, tool switching, and basic color selection, but features like layer blending modes and SVG export involve advanced techniques that may need refinement based on your specific browser compatibility needs. Would you like me to start with a minimal working version that we can iteratively enhance?

💎 Gemini

Here's a complete HTML5 drawing application with canvas-based rendering. The implementation uses event listeners for mouse/touch input, maintains drawing state in JavaScript objects, and leverages the Canvas 2D context API for rendering operations. Color management uses both HSL and hex values, layers are implemented as stacked canvas elements with CSS positioning, and export functionality uses canvas.toDataURL() and toBlob() methods for format conversion.

How to use this prompt

Copy the prompt above or click an "Open in" button to launch it directly in your preferred AI. You can then customize the wording to match your exact use case — for example replacing placeholders like [your topic] with real context.

Which AI model works best

Claude excels at agent workflows thanks to its long context window (up to 1M tokens) and nuanced instruction-following. ChatGPT has native Actions (tool-calling) built in. Gemini integrates best with Google Workspace data. For autonomous workflows, Claude Sonnet 4.6 is the current sweet-spot for quality and cost.

How to customize this prompt

Adjust the agent's role and constraints to your environment. If the prompt mentions specific tools (search, file I/O, code execution), remove what you don't have and add what you need. Add guardrails: "Always ask for confirmation before writing files." Define success criteria explicitly.

Common use cases

  • Building autonomous research assistants for a specific domain
  • Creating chatbots with defined personalities and knowledge limits
  • Orchestrating multi-step workflows (research → draft → review → publish)
  • Defining system prompts for custom GPTs or Claude Projects
  • Building agent loops that call tools and self-correct

Variations

Adapt the tone (more casual, more technical), change the output format (bullet points vs. paragraphs), or add constraints (word limits, target audience).

Related prompts