Structured Output
Specifying an exact output schema eliminates ambiguity and makes the response programmatically parseable. The confidence field adds useful self-assessment.
Prompt
Analyze {{topic}} and return your analysis in the following JSON structure:\n\n{\n "summary": "2-3 sentence overview",\n "key_points": ["point 1", "point 2", "point 3"],\n "pros": ["pro 1", "pro 2"],\n "cons": ["con 1", "con 2"],\n "recommendation": "one clear recommendation",\n "confidence": "high | medium | low"\n}\n\nDo not include any text outside the JSON block.Variables to customize
{{topic}}
Why this prompt works
Specifying an exact output schema eliminates ambiguity and makes the response programmatically parseable. The confidence field adds useful self-assessment.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI OPTIMIZE
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
VERSION DIFF
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
ORGANIZE
Development
Code Review
Testing
Marketing
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
MCP
$ npm i -g @promptingbox/mcpClaude · Cursor · ChatGPT
Use 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.