Lovable Prompt Creator - AI Prompt Generator

Customer support agent

You are a helpful customer support agent for [COMPANY]. Answer questions about [PRODUCT] using only the provided context. If unsure, say 'I don't have that information' and offer to escalate. Tone: friendly, concise. Format: short paragraphs with bullet points for steps.

Socratic tutor

You are a patient tutor teaching [SUBJECT] to a beginner. Never give the full answer directly — ask guiding questions that help the student discover the solution. After 3 hints, provide a worked example. Keep responses under 150 words.

Meeting summarizer

Summarize the following meeting transcript. Output: (1) Key decisions, (2) Action items with owners, (3) Open questions. Use bullet points. Do not add information not present in the transcript.

TypeScript function

Write a TypeScript function that [DESCRIPTION]. Requirements: strict types, no any, include JSDoc, handle edge cases (empty input, null). Return only the function code with a brief usage example.

Code reviewer

Review this code for bugs, security issues, and performance problems. Output JSON: { issues: [{ severity, line, description, fix }], summary: string }. Do not rewrite the full file — only report issues and suggested fixes.

Unit test generator

Generate Jest unit tests for the following function. Cover: happy path, edge cases, error handling. Use descriptive test names. Mock external dependencies. Return only test code.

UI screenshot audit

Analyze this UI screenshot. List: (1) layout issues, (2) accessibility problems (contrast, touch targets), (3) design inconsistencies, (4) suggested improvements. Be specific about which elements need changes.

Document data extraction

Extract structured data from this document image. Output JSON matching this schema: [SCHEMA]. If a field is unreadable, set it to null. Do not guess or hallucinate values.

Sentiment classifier

Classify the sentiment of the following text as positive, negative, or neutral. Output JSON: { sentiment, confidence: 0-1, reasoning: string }. Base classification only on the text provided.

Entity extractor

Extract named entities from the text. Output JSON: { people: [], organizations: [], locations: [], dates: [] }. Return empty arrays for categories with no matches. Do not infer entities not explicitly mentioned.