AI prompts for Document intelligence

Summarize an article with author, topics, coherence, persuasion, and a grounded counterpoint in JSON.

Extract explicit character traits into a flat JSON object with snake_case keys and typed values.

Diff two contract versions and list material differences.

Explain a legal letter or contract clause in plain English with risks called out (not legal advice).

Copy email addresses from text exactly, returning one address per line or N/A when none appear.

Compress a long brief into three executive bullets with a risk callout.

This prompt reads a company register document and returns its shareholders as a JSON array. Each entry has the name, register details, address, date of birth, number of shares, and percentage held, and the prompt includes rules for checking and removing duplicates. Share amounts are assumed to be in euros.

Extract invoice fields into spreadsheet-ready rows and flag missing values.

Extract structured fields from messy text using a JSON-only output schema.

Write a clear knowledge-base article from product and support information.

Answer a question from multiple documents by quoting relevant passages before presenting grounded information.

Extract people, organizations, locations, and other named entities with supporting context in JSON.

Turn a long PDF or document paste into a one-page brief with claims, numbers, and next steps.

Draft a privacy policy outline/first draft from a product checklist.

Rewrite a document with PII redacted for safer sharing.

This prompt reads a terms-and-conditions or terms-of-service text from the user's side. It looks at data use, charges, limits on what you can do, who is liable, and how the agreement can end, restates legal wording in plain English, and marks clauses to worry about. It ends with a recommendation on whether to agree.

Summarize parties, property, term, rent, responsibilities, notices, and special provisions in XML-tagged sections.

Write a system architecture document with clear, structured sections.

This prompt reads a home rental lease from the renter's side and returns JSON. It pulls out key terms, quotes clauses that are risky or unclear, totals move-in and yearly costs, notes what is missing, and lists changes to ask for before signing. It is not legal advice.

Map messy JSON to a reference schema, translate values to English, and format dates.