Few-Shot Learning
Providing 3 labeled examples teaches the model the exact output format and classification logic without needing a long explanation. The model generalizes the pattern to new inputs.
Convert the following customer feedback into a structured tag. Here are examples:\n\nFeedback: "The app crashes every time I try to upload a photo"\nTag: bug:upload, severity:critical, component:media\n\nFeedback: "Would love a dark mode option"\nTag: feature-request:ui, priority:low, component:settings\n\nFeedback: "Checkout is confusing, I almost gave up"\nTag: ux-issue:checkout, severity:high, component:payments\n\nNow classify this feedback:\nFeedback: "{{customer_feedback}}"\nTag:Variables to customize
Why this prompt works
Providing 3 labeled examples teaches the model the exact output format and classification logic without needing a long explanation. The model generalizes the pattern to new inputs.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
$ npm i -g @promptingbox/mcpUse Everywhere
Access prompts from Claude, Cursor, ChatGPT & more via MCP integration.
Your prompts, organized
Save, version, and access your best prompts across ChatGPT, Claude, Cursor, and more.