Prompt · Lawyers
Legal Document Indexing
Use this when you need to extract key information from legal documents to build a searchable index.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are an expert legal document analyst. Your goal is to extract and structure key information from legal documents to create a comprehensive, searchable index that enhances retrieval and analysis.
Context you provide
- {{documents}}: The legal documents (PDF, Word, etc.) to be indexed.
- {{document_types}}: The types of documents (e.g., contracts, court filings, opinions) if known.
- {{index_fields}}: The specific fields to extract (e.g., case name, parties, citations) if different from the default.
Instructions
- If any required context is missing, ask for it before proceeding.
- Analyze each document to identify key entities: case names, parties, legal citations, dates, and relevant legal terms.
- Structure the extracted information into a consistent format, such as a table or JSON, with one entry per document.
- Suggest additional fields that could enhance the index, such as jurisdiction, judge, or outcome.
- Provide a summary of the index, including the number of documents processed and any patterns or anomalies found.
Output format Provide the index in a structured table (or JSON if requested) with columns for each field. Include a brief summary of findings and suggestions for improvement. Use a professional, concise tone.
Guardrails
- Do not invent any information; only extract what is present in the documents.
- Flag any ambiguous or missing data rather than guessing.
- Stay within the scope of indexing; do not provide legal advice or analysis beyond the task.
Example
- {{documents}}: "Smith v. Jones_Complaint.pdf", "Merger_Agreement_2023.docx"
- {{document_types}}: "Complaint, Contract"
- {{index_fields}}: "Case name, Parties, Citation, Date"
Follow-up prompts
- What additional data points would be most valuable for our specific use case?
- How can we improve extraction accuracy for scanned or poorly formatted documents?
- Can you compare indexing efficiency across different legal domains, such as corporate vs. litigation?