Free ChatGPT Prompts Library

Extract all structured commercial data from this document strictly conforming to standard accounting schemas. Fields required: - vendor_name: (Full legal business entity name) - invoice_number: (Alphanumeric invoice/receipt identifier) - issue_date: (Format: YYYY-MM-DD) - due_date: (Format: YYYY-MM-DD) - subtotal: (Numeric currency amount without symbol) - tax_rate_percentage: (e.g. 5.0) - total_amount_due: (Final payable amount) - line_items: (Array containing description, unit_price, quantity, and line_total) If any field is missing or unreadable, mark it explicitly as null. Do not hallucinate values.

Act as an expert financial forensic auditor. Analyze the uploaded unstructured bank statement/ledger text. Task: 1. Reconstruct all transaction tables into standard rows with columns: [Date | Description | Transaction Type (Debit/Credit) | Amount | Running Balance]. 2. Standardize all transaction descriptions by stripping merchant terminal codes (e.g., turn "POS 4829 SQ *COFFEE SHOP NYC" into "Coffee Shop"). 3. Flag any duplicate entries or statistical outliers. Output format: Provide a markdown table followed by direct CSV copyable code.

Design a ready-to-use Supabase (PostgreSQL) relational database schema for [App Concept, e.g. a multi-tenant document extraction SaaS with team billing]. Include: 1. UUIDv4 primary keys for all tables. 2. Row Level Security (RLS) policies enforcing strict tenant isolation: users can only SELECT, INSERT, UPDATE their own organization's records. 3. Atomic credit deduction stored procedure with row-level locking (`FOR UPDATE`) to prevent concurrency race conditions. 4. Auto-updating `updated_at` trigger. 5. Optimized indexes on foreign keys and frequently queried status columns.

Act as a world-class Direct Response Copywriter (an experienced direct-response copywriter). Write high-converting landing page copy for [Product, e.g. B2B SaaS platform or productivity software]. Target Audience: Small business owners and teams looking to streamline repetitive manual workflows. Provide: 1. 3 Killer Headline + Sub-headline variants (focused on pain relief, speed, and cost savings). 2. "The Enemy" section: Agitate why slow manual processes lead to errors, delays, and hidden costs. 3. The Solution: How automated AI extraction eliminates manual bottlenecks. 4. 3 Proof/Metric Callouts. 5. 5 Objection-crushing FAQs with persuasive answers. Tone: Punchy, authoritative, zero marketing fluff, no buzzwords like "unleash" or "revolutionize".

Write a 3-step personalized B2B cold email sequence targeting [Target Role, e.g. Chief Financial Officers and Accounting Agency Heads]. Goal: Get them to try our free 10-credit document extraction workflow to automate invoice processing. Constraint Rules: - Email 1 (Day 1): Under 80 words. Observation -> Specific Pain Point -> Low-friction CTA (e.g. "Mind if I send a 30-sec demo?"). No attachments, zero sales pitch. - Email 2 (Day 4): Value add sharing a 1-sentence case study on saving time on invoice entry with automated extraction. - Email 3 (Day 8): Polite breakup email with an open door. Subject lines must look like informal internal 1-to-1 work emails (e.g. "quick question re: invoice processing").

Act as a Senior Principal Frontend Engineer. Build a sleek, dark-mode modern SaaS analytics dashboard using React, Next.js 14 (App Router), Tailwind CSS, and Lucide React icons. Include a sidebar navigation, a top navbar with user profile dropdown, and a main content grid featuring interactive charts using Recharts. Ensure clean component structure, responsive design, smooth transition animations, and accessible accessibility attributes.

Act as a world-class growth copywriter. Write a high-converting, viral 7-part educational thread about [Topic: e.g. How to automate data extraction with AI]. Format rules: - Tweet 1 (Hook): Must use a counter-intuitive insight or curiosity gap that stops scrolling. Zero clichés. - Tweet 2: The costly mistake 90% of people make. - Tweets 3-5: Step-by-step actionable framework with concrete numbers or examples. - Tweet 6: Concise takeaway summary (bulleted). - Tweet 7 (CTA): Friendly call-to-action encouraging bookmarks, retweets, and trying your free software or tool.

Write a high-converting 90-word cold email to a [Target Role, e.g. Finance Director at a logistics company] offering [Solution, e.g. automated invoice extraction that eliminates manual data entry]. Rules: 1. Subject line: under 4 words, lowercase, intriguing and casual (e.g., "quick question on invoices?") 2. First sentence: personalized observation of their operational bottleneck (no generic pleasantries) 3. The value proposition: show how they save 15+ hours/week without changing existing software 4. Zero aggressive sales pitches or attachments 5. Soft CTA: "Open to a 4-minute demo this Thursday?"

You are a world-class Conversion Rate Optimization (CRO) copywriter trained on direct-response copywriting frameworks. Write 3 distinct landing page Hero Section variations for a SaaS tool named "Document Extraction API". Include: 1) A punchy 6-8 word H1 Headline that addresses core pain points, 2) A 2-sentence Subheadline with value proposition, 3) Primary & Secondary CTA button text, and 4) A 3-bullet Social Proof bar. Tone: Authoritative, modern, high-energy, direct.

Parse this Bill of Lading (BOL) / Freight Manifest into structured tabular format. Extract: 1. Carrier Name, SCAC Code & Master BOL # 2. Shipper (Origin Address, Contact, Pickup Date) 3. Consignee (Destination Address, Delivery Window) 4. Third-Party Freight Bill-To Information 5. Commodity Breakdown Table: [Handling Units | Package Type | NMFC # | Class | Weight (LBS/KG) | Hazardous Material (Y/N) | Description of Articles] 6. Special Instructions & Temperature Control specs Sanitize output: Output markdown table and clean JSON object. Strip commas from numerical weights.

Perform precision extraction of tax information from this scanned US IRS tax document (W-2 or 1099-NEC/MISC). Detect the document type automatically, then extract box-by-box: - Form Type & Tax Year - Payer/Employer Name, Address, and Federal EIN - Recipient/Employee Name, Masked SSN (***-**-1234) - Box 1 (Wages/Nonemployee Compensation) - Box 2 (Federal Income Tax Withheld) - Social Security / Medicare Wages & Tax Withheld (if W-2) - State & Local Tax breakdowns (Boxes 15-20) Format as strict key-value JSON matching IRS electronic filing schema.

Reconcile this e-commerce settlement report (Amazon FBA bi-weekly statement or Shopify Payments export). Categorize every transaction into accounting buckets: - Gross Product Sales (Principal) - Shipping Credits & Gift Wrap Credits - Marketplace Facilitator Sales Tax Collected - Amazon Referral Fees / Commission - FBA Fulfillment Fees (Pick & Pack) - FBA Monthly Storage Fees & Long-term Storage Surcharges - Customer Refunds & Restocking Fees - Promotional Rebates & Coupons - Advertising Spend (Sponsored Products Deduction) - Net Bank Transfer Payout Amount. Check math: Sum of categories MUST equal net transfer payout.

Extract the full loan payment amortization schedule from this promissory note or bank debt statement. Extract: 1. Core Terms: Principal Loan Amount, Annual Interest Rate, Term (Months), Compounding Frequency, Origination Date, First Payment Due Date. 2. Schedule Table: For each payment period, extract [Payment # | Due Date | Monthly Total Payment | Principal Component | Interest Component | Escrow/Insurance (if any) | Remaining Principal Balance]. 3. Calculate summary metrics: Total interest paid over lifetime of loan and balloon payment at maturity if applicable. Output direct CSV format ready to paste into Excel.

Extract all financial components from this employee pay stub / payroll journal (ADP, Paychex, Gusto). Structure the data into three balanced columns: 1. Earnings: [Earning Type (Regular, Overtime, Bonus, PTO) | Hours | Rate | Current Amount | YTD Amount] 2. Taxes Withheld: [Federal Income Tax, Social Security (OASDI), Medicare, State Withholding, Local/City Tax | Current | YTD] 3. Deductions: [Pre-Tax (401k, Health Insurance, HSA) | Post-Tax (Roth, Garnishments) | Current | YTD] 4. Net Pay Verification: Confirm Gross Earnings - Total Taxes - Total Deductions = Net Direct Deposit Amount.

Process this automotive fleet dealership repair order / mechanic invoice. Extract: - Vehicle VIN (17 characters), Year, Make, Model, License Plate # - Odometer In / Odometer Out mileage - Customer Complaint / Symptom noted - Diagnostic Trouble Codes (DTCs, e.g. P0300) - Technician Labor Lines: [Job Description | Labor Hours | Labor Rate | Labor Total] - Replacement Parts Table: [OEM Part # | Part Description | Qty | List Price | Sale Price | Extended Total] - Environmental Disposal Fees & Shop Supplies charge - Total Invoiced Amount.

Write a ready-to-use JavaScript Code Node for an n8n workflow that ingests binary files from a document extraction webhook and sends them to Gemini. Requirements: 1. Validate HMAC-SHA256 signature in incoming `x-webhook-signature` header. 2. Extract base64 buffer from binary item without memory leaks. 3. Construct multimodal payload for Gemini with structured JSON schema enforcement. 4. Handle exponential retry on HTTP 429 and 503 errors. 5. Return normalized item containing extracted JSON and execution latency metrics.

Write a high-throughput Python FastAPI endpoint for asynchronous PDF/image file uploads. Requirements: 1. Accept `UploadFile` up to 30MB. 2. Validate magic bytes in memory (reject executable binaries renamed as .pdf). 3. Stream chunks directly to a ClamAV daemon (`pyclamd`) without writing temporary files to disk. 4. Enforce user rate limits using Redis token bucket (10 uploads/minute per API key). 5. Return JSON with file SHA-256 hash, verified MIME type, and temporary S3 presigned URL. Include comprehensive docstrings and Pydantic response models.

Write a production PostgreSQL stored procedure and pg_cron schedule to enforce a strict monthly quota policy. Policy rules: 1. Every user has a monthly limit of 10 free extractions. 2. Zero carry-forward: If a user only extracted 4 files in October, their remaining 6 expire on November 1st. They reset back to exactly 10, NEVER 16. 3. Table schema: `users_quota (user_id UUID PRIMARY KEY, extractions_used INT, quota_limit INT DEFAULT 10, last_reset_month DATE)`. 4. Procedure `check_and_deduct_quota(p_user_id UUID)` that locks row `FOR UPDATE`, checks if `last_reset_month < date_trunc('month', CURRENT_DATE)`, resets `extractions_used = 0` if new month, checks if `extractions_used < quota_limit`, increments by 1, and returns boolean `allowed`. 5. Schedule cron job running at midnight on the 1st of every month.

Write an enterprise-grade multi-stage Dockerfile for a Next.js (App Router) application utilizing standalone output. Stages: 1. `deps`: Alpine Node 20 base, cache npm/bun dependencies. 2. `builder`: Run build script with `NEXT_TELEMETRY_DISABLED=1`. 3. `runner`: Ultra-lightweight non-root user (`nodejs:nodejs`, UID 10001), copy only necessary static assets and standalone server files. Features: - Image size under 150MB. - Healthcheck instruction probing `/api/health` every 15s. - Proper signal handling (`dumb-init` or Node process) for graceful container shutdown on SIGTERM.

Create a complete `.github/workflows/security-audit.yml` pipeline that triggers on pull requests to `main`. Jobs to execute in parallel: 1. Secret Scanning: Run `trufflehog` to detect hardcoded API keys, Supabase service roles, or JWT tokens. 2. Dependency Vulnerability Audit: Run `npm audit --audit-level=high`. 3. Static Code Analysis: Run ESLint with security plugins (`eslint-plugin-security`). 4. Typecheck: Run `tsc --noEmit`. 5. Build: Verify Vite/Next.js production bundle compiles with zero warnings. Block pull request merging if any high-severity vulnerability or leaked secret is found.

Generate 10 high-engagement, controversial social media hooks (for Twitter/X and LinkedIn) positioning automated software against manual data entry outsourcing. Angles to cover: 1. The Math Angle (Paying $15/hr for something that takes a 10-cent AI script 4 seconds). 2. The Data Privacy Angle (Sending bank statements to random laptops in third-party countries). 3. The Typo Disaster Angle (A missed decimal place in invoice entry costing $4,000). 4. The Founder Time Angle (Spending Sunday evenings reviewing Upwork milestones). 5. The Instant Scalability Angle (Processing 500 invoices in 2 minutes during tax season). Tone: Direct, provocative, pragmatic business owner logic.

Create an SEO landing page content blueprint for programmatic URLs like `/solutions/automate-[industry]-invoices`. Variables to interpolate: `[Industry]`, `[Document_Type]`, `[Pain_Point]`, `[Output_Destination]`. Structure: 1. Target Keyword Title Tag: "Automate [Industry] Data Entry | Free [Document_Type] to Excel AI" 2. Hero Section: Direct callout to industry professionals wasting hours every Friday. 3. Real-World Extraction Example showing before/after of industry-specific jargon. 4. Table comparing Manual Freelancer vs Automated Software. 5. 5 Industry-Specific FAQs with rich structured schema markup. 6. Clear CTA for a free starter tier without credit card.

Write a high-retention, narrative-driven LinkedIn post from the perspective of a tech founder. Hook: "In 2024, our accounting agency spent $34,800 on Upwork data entry freelancers. Last month, that number was $0. Here's what changed:" Narrative beats: - The turning point: A freelancer missed 3 invoices before a critical tax filing. - The realization: Humans shouldn't be copy-pasting numbers between PDF viewer and Excel. - The AI shift: How multimodal models turned 48-hour turnarounds into automated instant API processing. - The moral: Don't hire freelancers for mechanical tasks—hire them for strategy and growth. Formatting: Clean 1-2 sentence paragraphs, no emojis spam, authentic humble tone.

Write a complete Product Hunt launch copy package for [Product Name]. Include: 1. Tagline: Under 60 characters, crystal-clear value prop without buzzwords. 2. Short Description: 250 characters summarizing the core feature set. 3. First Maker Comment: - Why we built the product (the frustration with clunky enterprise tools and slow manual workflows). - How our multimodal pipeline is engineered for high-precision, reliable extraction. - Special launch day offer: Free starter quota + community feedback request. 4. 5 Engaging Maker Replies to anticipate common questions (security, OCR accuracy, Excel formula safety).