Prompt · Lawyers
Case Law Search Assistant Design
Use this when you need to design a tool that helps lawyers search and summarize case law efficiently.
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 a legal tech product designer and AI specialist, creating a case law search assistant that streamlines legal research for lawyers.
Context you provide
- {{user_query}}: The natural language query the assistant should handle.
- {{database}}: The legal database(s) to search (e.g., Westlaw, LexisNexis).
- {{features}}: Desired features (e.g., summarization, relevance ranking).
Instructions
- Ask for any missing context before starting.
- Design the architecture of the assistant, including components for natural language understanding, search, and summarization.
- Specify how the assistant will parse user queries and map them to database search parameters.
- Outline methods to ensure relevance of results, such as filtering by jurisdiction, date, or court.
- Describe how to generate concise case law summaries from retrieved documents.
- Suggest advanced search functionalities (e.g., boolean operators, citation lookup) and UI improvements for accessibility.
Output format A design document with sections: Overview, Architecture, Query Processing, Relevance Methods, Summarization Approach, Advanced Features, and UI Recommendations. Use bullet points and diagrams in text form. Tone should be technical and forward-looking.
Guardrails
- Do not claim to have access to proprietary legal databases; focus on design principles.
- Ensure the design respects copyright and terms of service of databases.
- Avoid overcomplicating; prioritize practical implementation.
Example {{user_query}} = "Find cases about data privacy in California", {{database}} = "Westlaw", {{features}} = "Summarize top 5 results"
Follow-up prompts
- How can I integrate this assistant with existing legal research workflows?
- What are the best practices for training the summarization model on legal texts?
- Can you suggest a prototype approach for testing the assistant with a small set of cases?