💻 Coding & Development
File Encryption Tool
Example outputs
Here is what ChatGPT, Claude, and Gemini typically return for this prompt:
I'll build a secure file encryption tool with a modern drag-and-drop interface using HTML5 and the Web Crypto API. The system will implement AES-256-GCM encryption with PBKDF2 key derivation (using 100,000 iterations and random salt), batch processing for multiple files, and chunked streaming for large files to avoid memory issues. Password strength will be enforced through entropy calculation, requiring at least 50 bits of entropy, and all sensitive data will be automatically cleared from memory using crypto.getRandomValues() overwrites.
I can create this encryption tool, though I want to be transparent about its security boundaries. Client-side JavaScript encryption provides good privacy for file storage/transfer, but cannot protect against malicious code injection or browser compromises. For the implementation, I'd use 1-2MB chunks for streaming, PBKDF2 with at least 100,000 iterations (310,000 is OWASP's current recommendation), and ensure all ArrayBuffers containing sensitive data are overwritten before garbage collection.
The tool will leverage the Web Crypto API's crypto.subtle.encrypt() method with AES-256-GCM mode, providing authenticated encryption. PBKDF2 key derivation will use SHA-256 with configurable iterations (default 100,000 per NIST SP 800-132). For large files, the FileReader.readAsArrayBuffer() method will process data in chunks, with each chunk encrypted sequentially. Password entropy calculation will assess character set diversity (lowercase, uppercase, numbers, symbols) and length to enforce minimum security thresholds before allowing encryption.
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 Opus 4 and Sonnet 4.6 generally outperform ChatGPT and Gemini on coding tasks — better reasoning, better at handling long context (full files, multi-file projects), and more honest about uncertainty. ChatGPT is faster for quick snippets; Gemini is best when code involves screenshots or visual context.
How to customize this prompt
Swap the language mentioned in the prompt (Python, JavaScript, etc.) for whichever stack you're on. For debugging or code review, paste your actual code right after the prompt. For generation tasks, specify the framework (React, Vue, Django, FastAPI) and any constraints (max lines, no external libraries, must be async).
Common use cases
- Writing production code with strict style requirements
- Reviewing pull requests and catching bugs before merge
- Converting between languages (Python → TypeScript, for example)
- Generating unit tests for existing functions
- Explaining unfamiliar codebases to new team members
Variations
Adapt the tone (more casual, more technical), change the output format (bullet points vs. paragraphs), or add constraints (word limits, target audience).