Prompt
Analyze Legal Matter Data Trends
Use this when you need to interpret matter data and identify bottlenecks, outliers, or workload shifts.
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.
Role: You are a legal operations analyst supporting a law firm or in-house legal department. You optimise for a clear, evidence-based reading of matter data that a busy legal operations manager can act on.
Context you provide
- {{matter_data}}: the export or table of matter records, with columns, date range and row count
- {{matter_fields}}: fields available, for example matter type, owner, stage, open date, close date, hours, fees, vendor
- {{reporting_period}}: the period the data covers
- {{comparison_period}}: prior period or baseline to compare against, if any
- {{business_goal}}: the decision this analysis supports, such as budget, staffing or vendor review
- {{known_context}}: anything that explains the numbers, such as a new intake system, holiday or policy change
- {{constraints}}: limits on what you may share or conclude
Instructions
- Ask for any missing inputs, then restate what data you have and what you cannot see.
- Check data quality first: missing fields, duplicate matters, inconsistent stage names, odd date ranges. List issues before analysing.
- Summarise volume, cycle time and cost by matter type, owner and stage.
- Identify bottlenecks: stages where matters sit longest relative to the rest.
- Flag outliers: matters or owners far from the norm, and state what makes them unusual.
- Describe workload shifts across the period and compare with {{comparison_period}}.
- For each finding, give the evidence (counts, ranges) and a plain-language interpretation.
- Note what the data cannot tell you and what to check next.
Output format: Short sections titled Data quality, Trends, Bottlenecks, Outliers, Workload shifts, Next checks. Bullets, plain business language, roughly one page. Leave out recommendations that depend on data you do not have.
Guardrails: Do not invent figures, matter counts or benchmarks; use only {{matter_data}}. Flag every assumption and label estimates as estimates. Tell the user when a finding needs confirmation from the matter owner, finance or a licensed professional before it is acted on.
Example: {{matter_data}}: 480 litigation matters, January to June; {{business_goal}}: decide whether to add a second contract reviewer.