100 Best Gemini Excel Data Analysis Prompts for Law Firms

Direct Answer

The best Gemini prompts for Excel data analysis for law firms are designed to extract actionable insights from legal data, optimize operations, and improve profitability through structured prompts that guide Gemini to analyze matters, costs, revenues, and timelines. Use them with your Excel datasets to generate clear tables, dashboards, and recommendations. The prompts assume your workbook contains fields like Matter, Client, HoursBilled, Fees, Costs, OpenDate, CloseDate, Status, and related metadata. Adjust placeholders to fit your data schema and verify outputs against source records.

Introduction

This page provides a practical prompt library of Gemini prompts specifically for Excel data analysis in law firms. It is intended for legal operations teams, finance analysts, and partners who want repeatable prompts to surface insights from case data.

The prompts guide Gemini to produce ready-to-use outputs such as tables, CSV-ready results, and dashboard-ready datasets without requiring you to invent missing context.

How to Use These Gemini Prompts

• Replace placeholders like [Matter] and [Fees] with your actual column names.
• Add constraints such as time ranges, currencies, or status filters to tighten results.
• Request outputs in a specific format like JSON, CSV, or table for easy ingestion.
• Always verify outputs against source data and document any assumptions.
• If data is incomplete, ask for data enrichment steps or quality checks.
• Incorporate prompts into your data workflow for automation and consistency.

100 Best Gemini Excel Data Analysis Prompts for Law Firms

1. Caseload by matter type: Act as a data analyst for a law firm. Your task is to analyze a provided Excel workbook containing columns: MatterType, OpenDate, CloseDate, HoursBilled, MatterStatus, ClientFee. Your goal is to produce an executive summary in bullet points with a chart-ready dataset: compute counts by MatterType, average hours per matter, and total billed hours per month. Output: JSON with fields: matter_type, count, avg_hours, total_billed, month, trend. Constraints: focus on the last 12 months, ignore closed matters with status archived, ensure date parsing uses ISO format, and provide guidance for a dashboard.
2. Billing efficiency by department: Role: Financial analyst for a law firm. Task: Given an Excel sheet with Department, Matter, Client, HoursBilled, FeeReceived, InvoicedDate, write a summary that ranks departments by revenue per hour and identifies outliers where hours per matter exceed 8. Output: a ranked list with department, total_revenue, total_hours, revenue_per_hour, outlier_noted. Provide a CSV-ready table and a brief interpretation.
3. Avg case duration per practice area: You are a data scientist for a law firm. Analyze an Excel workbook with columns: PracticeArea, OpenDate, CloseDate, MatterStatus. Compute average case duration per PracticeArea and provide a short interpretation for leadership. Output: a table with PracticeArea, avg_duration_days, sample_size. Include a note on data quality and gaps.
4. Probability of win by year: Act as a predictive analyst. Using historical case outcomes in an Excel sheet with Year, PracticeArea, Outcome (Win/Loss), Hours, Fee. Build a simple probability model of winning per year and per PracticeArea. Output: table with Year, PracticeArea, win_probability, confidence_note. Include a brief caveat about dataset size.
5. Top clients by profitability: Role: Portfolio analyst. Given a workbook with Client, Matter, Revenue, Costs, Hours, Department. Compute profitability per client (net_profit / hours) and identify top 5 clients. Output: table with Client, NetProfit, Hours, Profitability, top_5_flag. Include optional visual cues recommendations.
6. Open matters heatmap: Task: Create a heatmap-ready dataset from columns Matter, OpenDate, Stage, ExpectedCloseDate, Priority. Group by Month and Stage to show volume and expected revenue. Output: table with Month, Stage, Count, ExpectedRevenue, heat_score. Provide guidance for color ramp selection.
7. Matter aging report: Role: Operations analyst. From an Excel sheet with Matter, OpenDate, CloseDate, Status, Fees. Compute age_days for open matters, segment by Status, and flag matters older than 180 days. Output: aging_table with Matter, AgeDays, Status, Flag. Include notes on follow-up actions.
8. Litigation cost trap: You are a cost analyst. Given an Excel workbook with Matter, Stage, Costs, Fees, Date. Identify stages where costs exceed 60 percent of fees on average across matters. Output: stage_costs table with Stage, AvgCosts, AvgFees, CostShare, alert_flag. Recommend mitigation steps.
9. Hourly rate benchmarking: Act as a pricing analyst. Using data with Attorney, Department, HourlyRate, HoursBilled, Matter, Client. Compute median hourly rate per Attorney and per Department, compare to firm-wide benchmarks, and flag outliers. Output: benchmark_table with Entity, MedianRate, MedianHours, BenchmarkFlag. Provide actionable recommendations.
10. Cash collection forecast: Role: Collections analyst. From InvoicedDate, Amount, Status, DaysSinceInvoiced in an Excel sheet, forecast cash collections for the next 60 days. Output: forecast_table with Day, ExpectedCash, Confidence, Actions. Include assumptions text.
11. Matter type trendline: Task: For a workbook with MatterType, OpenDate, CloseDate, Year. Build a trendline of count per Month by MatterType. Output: trend_table with MatterType, Month, Count, TrendSlope. Include a note on seasonality.
12. Resource load forecast: You are an operations planner. Given HoursAllocated per Attorney and a calendar of scheduled matters, forecast resource load for next quarter. Output: table with Attorney, ForecastHours, PeakWeeks, GapWarnings. Include guidance for hiring or outsourcing triggers.
13. Client churn risk: Role: Client success analyst. From Client, Matter, Status, LastInteractionDate, Revenue. Compute churn_risk_score per client and identify high-risk accounts. Output: table with Client, Revenue, LastInteractionDate, ChurnRisk, recommendedAction.
14. Billing cycle adherence: Task: Analyze invoicing dates vs contractual cycles. Input: InvoicedDate, CycleStart, CycleEnd, Amount. Output: compliance_rate, issues_list, recommended_schedule_changes. Provide a CSV-ready table.
15. Fee realization by matter: Role: Revenue analyst. Using data: Matter, Client, Fee, Costs, GrossMargin. Compute fee_realization = Fees / (Fees + Costs) and rank top matters by realization. Output: table with Matter, Fee, Costs, Realization, Rank.
16. Due date risk scoring: You are a risk analyst. Given data: DueDate, Status, openHours, Priority. Build a risk_score for each matter based on days overdue, priority, and status. Output: table with Matter, DueDate, RiskScore, SuggestedAction.
17. Contract renewal window: Task: For each Client with RenewalDate, compute 12-month renewal window and alert if within 90 days. Output: renewals_table with Client, RenewalDate, Window, ActionNeeded.
18. matter resolution time: Role: Process analyst. Using OpenDate, CloseDate, Matter, Outcome, generate average resolution_time per Outcome and per PracticeArea. Output: table with PracticeArea, Outcome, AvgDays, SampleSize.
19. Billing by matter type: You are a billing analyst. Given MatterType, HoursBilled, Fee, Output: total_hours_by_type, total_fees_by_type, avg_rate_by_type. Provide insights for pricing strategy.
20. Unbilled work snapshot: Task: From unbilled matters, compute potential_revenue = HoursBilled * AvgRate. Output: snapshot_table with Matter, Client, HoursBilled, PotentialRevenue, UnbilledFlag.
21. Cost-to-serve by client: Role: Cost analyst. Using Client, Matter, Costs, Fees, HoursBilled. Compute cost_to_serve = Costs / HoursBilled and rank clients by lowest cost_to_serve. Output: table with Client, Cost, Hours, CostToServe, Rank.
22. Discovery phase efficiency: Act as a process improvement consultant. From data: Phase, DurationDays, Costs, Outcomes. Identify phases with longest duration and highest cost per outcome. Output: table with Phase, AvgDuration, AvgCost, OutcomeRate. Provide improvement recommendations.
23. Settlement probability model: Role: Risk analyst. Using Year, Stage, Outcome, and Fees, build a simple model predicting settlement probability by Stage. Output: table with Stage, SettlementProbability, Confidence. Include usage notes.
24. Judge-specific trends: Task: With data including Judge, MatterType, Outcome, compute outcome_rate per Judge and per MatterType. Output: table with Judge, MatterType, WinRate. Add interpretation guidance.
25. Priority matters backlog: You are an operations lead. From Matter, Priority, OpenDate, Status, DaysOpen, build a backlog score and list top 10 urgent matters. Output: table with Matter, Priority, DaysOpen, BacklogScore, Action.
26. Export-ready dashboard pack: Role: BI lead. From a dataset with multiple metrics, prepare a dashboard-ready summary: key_kpis, top_drivers, and a data_quality_note. Output: json_ready for a dashboard blend. Include field names and sample rows.
27. Attorney utilization report: Task: Compute attorney_utilization = billed_hours / available_hours for each attorney. Output: table with Attorney, BilledHours, AvailableHours, Utilization, FlagLowUtilization.
28. Matter status drift: You are a governance analyst. Compare current matter statuses to the previous month and highlight drift in counts by Status. Output: drift_table with Status, ThisMonthCount, LastMonthCount, Delta.
29. Client profitability by matter: Role: Profitability analyst. Using Client, Matter, Revenue, Costs. Compute client_profitability = Revenue - Costs and rank top clients. Output: table with Client, Revenue, Costs, Profitability, Rank.
30. Excel data quality checks: Task: Create a data_quality_report template for a legal data workbook. Include fields: RecordID, MissingFields, DuplicateCount, AnomalyFlag. Output: quality_report with sample rows and remediation steps.
31. Matter close reason insights: Role: Analyst. From CloseReason, MatterType, Count, compute most common close reasons by MatterType. Output: table with MatterType, CloseReason, Count.
32. Hourly rate by seniority: You are a pricing analyst. Given data including AttorneySeniority, HourlyRate. Compute average rate by seniority level and recommend tiered pricing. Output: table with Seniority, AvgRate, Recommendation.
33. Client concentration risk: Task: From Client, Revenue, DiversificationScore. Compute concentration risk per client and identify high-risk accounts. Output: table with Client, Revenue, Diversification, RiskFlag.
34. Seasonality in matters: Role: Data analyst. Analyze matter counts by Month and PracticeArea to identify seasonality patterns. Output: table with PracticeArea, Month, Count, SeasonalityNote.
35. Matter aging by department: You are an operations analyst. From Matter, Department, OpenDate, CloseDate, compute aging by Department and flag departments with rising aging trends. Output: table with Department, AvgAging, Trend.
36. Cost forecast by matter: Task: For upcoming quarters, forecast Costs per Matter using historical Cost data by Matter and Phase. Output: table with Matter, Quarter, ForecastCosts, Confidence.
37. Remittance timing insights: Role: Collections analyst. Using InvoicedDate, PaymentDate, Amount. Compute average remittance time and identify debts passed due. Output: table with DaysToPay, AvgAmount, PastDueCount.
38. Fee mix by matter: You are a pricing analyst. From Fee, Costs, classify by FeeCategory and compute share of each category in total fees. Output: table with FeeCategory, Share, TotalFees.
39. Litigation milestone tracker: Task: Build a milestone tracker template from data with Milestone, Date, Status. Output: tracker_table with Matter, Milestone, Date, Status, Completion. Provide guidance for automation.
40. Attorney turnover risk: Role: HR analyst. Using HireDate, ExitDate, Matter, HoursBilled. Compute turnover_risk = (ExitDate - HireDate) / tenure and identify at-risk attorneys. Output: table with Attorney, Tenure, TurnoverRisk.
41. Client lifetime value: You are a finance analyst. From Client, Revenue, Costs, EngagementLength, compute CLV = sum(Revenue) - sum(Costs) across clients, plot top 5. Output: table with Client, CLV, EngagementLength.
42. Billing error flags: Task: From InvoicedDate, Amount, Adjustments, Errors. Build an error_flag table for invoices with significant adjustments or negative adjustments. Output: table with InvoiceID, ErrorType, AdjustmentAmount, Flag.
43. Data dictionary builder: Role: Data steward. Create a concise data_dictionary for the workbook including FieldName, DataType, Example, ValidRange. Output: dictionary_table.
44. Cross-sell opportunity radar: You are a market analyst. Using Client and Matter data, identify clients with adjacent practice areas where cross-sell is likely. Output: list of Opportunities with Client, CurrentArea, SuggestedArea, Rationale.
45. Compliance flag checklist: Task: For legal compliance data, create a checklist of flags for records missing licensing or conflict checks. Output: checklist_table with Field, Issue, Recommendation.
46. Forecast revenue by month: Role: Revenue planner. From InvoicedDate, Amount, build a monthly revenue forecast for the next six months. Output: table with Month, ForecastRevenue, Confidence.
47. Open matter backlog by priority: You are an operations lead. From OpenDate, Priority, Status, DaysOpen, create a prioritized backlog list for open matters. Output: table with Matter, Priority, DaysOpen, Action.
48. POS data integrity check: Task: Validate a dataset with PointOfSale-like entries for legal services. Check date formats, currency consistency, and missing fields. Output: integrity_report with IssuesFound and Remediation.
49. Matter type contribution: Role: Data analyst. From MatterType and Revenue, compute contribution margin by type and highlight most profitable types. Output: table with MatterType, Revenue, Costs, Margin.
50. Export format presets: Task: Create presets for common export formats from Excel data into CSV, Excel, or JSON. Output: presets_table with Format, Delimiter, Encoding, Sample.
51. Practice area overlap map: You are a data visualization specialist. From PracticeArea and MatterType, identify overlaps and map co-occurrence. Output: table with PracticeArea, Overlaps, RelatedAreas.
52. Jurisdiction risk profile: Role: Risk analyst. Using Jurisdiction, CaseVolume, Outcome, build a risk_profile per jurisdiction. Output: table with Jurisdiction, Volume, WinRate, RiskScore.
53. Data quality heat score: Task: Compute a data_quality_score based on missing_fields, duplicates, and anomalies per record. Output: table with RecordID, QualityScore, Remediation.
54. Case mix optimization: You are a practice optimization consultant. Given MatterType, HoursBilled, Fees, compute optimal case mix to maximize margins. Output: matrix with Type, SuggestedShare, ExpectedMargin.
55. Client segmentation by value: Role: Marketing analyst. Using Client and Revenue, segment clients into tiers (A, B, C) and provide rationale. Output: table with Client, Tier, Revenue, Justification.
56. Outcome recovery rate: Task: From Outcome and Fees, compute recovery_rate = FeesPaid / FeesBilled per Matter and overall. Output: table with Matter, Outcome, RecoveryRate.
57. Data lineage snapshot: Role: Data governance. Produce a lineage snapshot outlining source, transformations, and destination for key fields. Output: lineage_table with Field, Source, Transformation, Destination.
58. Conflict check readiness: You are a compliance analyst. For each matter, assess whether conflict_check is complete and flag if pending. Output: table with Matter, ConflictStatus, DueDate, Action.
59. Document review throughput: Task: Analyze review milestones by reviewer and document type. Output: throughput_table with Reviewer, DocType, ItemsReviewed, AvgDays.
60. Settlement funding plan: Role: Financial planner. For matters with settlements, propose a funding plan including cash flow timing and reserves. Output: plan_table with Matter, SettlementDate, CashNeed, Reserve.
61. Alternative fee arrangement fit: You are a pricing strategist. Determine which matters are good candidates for alternative_fee_arrangements based on hours, margins, and client type. Output: table with Matter, Margin, CandidateFlag.
62. Cycle time by matter: Task: Compute cycle_time = CloseDate - OpenDate by Matter and summarize by Month. Output: table with Month, AverageCycleTime, Count.
63. Budget variance tracker: Role: Finance analyst. Compare actual costs to budget by Matter and Department. Output: variance_table with Matter, Department, Budget, Actual, Variance, Flag.
64. Recovery leakage audit: You are a process auditor. Identify stages where revenue leaks occur by comparing Fees and InvoicedAmount across Matters. Output: leak_table with Stage, Leakage, RecommendControls.
65. Litigation spend buckets: Task: Classify Costs into buckets (Discovery, Expert, CourtFees) and show share per matter. Output: bucket_table with Matter, Bucket, Cost, Share.
66. Client feedback sentiment: Role: Client success analyst. From FeedbackScore and Client, generate sentiment by client and top drivers of dissatisfaction. Output: table with Client, Sentiment, TopDrivers.
67. Matter closure ROI: You are a finance analyst. For closed matters, compute ROI = (Fees - Costs) / Costs and rank matters. Output: table with Matter, ROI, Rank.
68. Data lag detector: Task: Detect data lag by comparing LastUpdated timestamp with current date and flag records not updated in over 30 days. Output: lag_table with RecordID, DaysSinceUpdate, Flag.
69. Billing dispute tracker: Role: Collections analyst. From DisputeStatus, DisputeReason, Amount, build a tracker for open disputes with priority. Output: table with Matter, DisputeStatus, Reason, Amount, Priority.
70. Vendor cost comparison: You are a procurement data analyst. Compare vendor costs for outside counsel by Matter and provide savings opportunities. Output: table with Vendor, Matter, Cost, Benchmark, Savings.
71. Matter attribute matrix: Task: Build a cross-tab of MatterType x PracticeArea vs Revenue and Costs. Output: matrix_table with Type, Area, Revenue, Costs, Margin.
72. NLP-ready summaries: Role: Knowledge manager. Create concise summaries of matters suitable for internal search like a knowledge base. Output: summary_table with Matter, Summary.
73. Time capture completeness: You are a compliance auditor. From Timesheets, ensure fields like Start, End, and Task are complete. Output: completeness_table with RecordID, MissingFields, CompletenessFlag.
74. Conflict risk heatmap: Task: Map conflicts by Client and Matter across regions to identify concentration. Output: heatmap_table with Client, Region, ConflictCount, RiskLevel.
75. Expert witness cost plan: Role: Budget planner. For matters involving experts, estimate approximate costs and create a plan. Output: plan_table with Matter, ExpertType, EstimatedCost, Timeline.
76. Settlement impact analysis: You are a strategic analyst. Compare expected vs actual settlement outcomes and differences in fees. Output: table with Settlement, ExpectedFee, ActualFee, Delta.
77. Open vs closed matters: Task: Compare counts of open vs closed matters by Month and Status. Output: comparison_table with Month, OpenCount, ClosedCount, Delta.
78. Data normalization rules: Role: Data engineer. Provide normalization rules for common fields like ClientName, MatterID, and Currency to ensure consistency. Output: rules_table with Field, Rule, Example.
79. Client communication plan: You are a client success strategist. For high-value clients, draft a quarterly communication plan with milestones and metrics. Output: plan_table with Client, Quarter, Milestones, Metrics.
80. Document drafting templates: Role: Knowledge engineer. Provide templates for common legal document types used in the firm. Output: template_table with DocumentType, Template, Fields.
81. Data security checklist: Task: Create a security checklist for legal data handling including access controls and encryption. Output: checklist_table with Control, Status, Owner.
82. Cross-border matter costs: You are a cost analyst. For matters with cross-border elements, compare cost profiles by country and propose optimizations. Output: table with Country, Cost, Share, Recommendation.
83. Matter networking map: Role: Knowledge graph designer. Build a map linking Matters by shared Clients, Counsel, or PracticeArea. Output: network_table with NodeA, NodeB, LinkType, Weight.
84. Audit trail generator: Task: Create an audit trail template capturing changes to matter records including timestamp, user, and change_type. Output: trail_table with RecordID, Timestamp, User, ChangeType.
85. Outcome-driven pricing: You are a pricing strategist. Determine pricing adjustments based on historical outcomes by MatterType. Output: table with MatterType, AvgOutcome, Price_adjustment.
86. Legal hold readiness: Role: Compliance analyst. From Matter and Custodian data, assess readiness for legal holds and flag gaps. Output: readiness_table with Matter, Custodians, GapFlag.
87. Remedial action tracker: Task: For data quality issues, assign owners and due dates. Output: tracker_table with Issue, Owner, DueDate, Status.
88. Advisory notes generator: Role: Knowledge manager. Generate concise advisory notes summarizing key findings from a matter dataset. Output: notes_table with Matter, Findings.
89. Forecast scenario planning: You are a scenario planner. Build three scenarios for revenue under different market conditions. Output: scenario_table with Scenario, Probability, Revenue, Notes.
90. Automated alert rules: Task: Create a set of alert rules for anomalies in invoicing and hours. Output: alerts_table with Rule, Condition, Action, Severity.
91. Practice area growth forecast: Role: Market analyst. Forecast growth rate per PracticeArea for the next 12 months. Output: table with PracticeArea, GrowthRate, Confidence.
92. Case outcome benchmarking: You are an analytics lead. Compare your firm's win rate to industry benchmarks by PracticeArea. Output: table with PracticeArea, OurWinRate, BenchmarkWinRate, Gap.
93. Matter namespace naming: Task: Propose a consistent naming convention for matters to improve searchability. Output: naming_rules_table with Field, Rule, Example.
94. Cost sensitivity analysis: Role: Financial analyst. For key costs, run a sensitivity test showing impact of +/- 10 percent on profitability. Output: sensitivity_table with Cost, Change, NewProfit.
95. Partner profitability map: You are a portfolio manager. Visualize partner contribution by hours and profitability across matters. Output: map_table with Partner, Matter, Hours, Profit.
96. Data export validation: Task: After exporting data for external partners, validate integrity by cross-checking row counts and sums. Output: validation_table with ExportID, RowCountMatch, SumMatch.
97. Client onboarding analytics: Role: Onboarding analyst. Measure time to onboard new clients by stage and identify bottlenecks. Output: table with Stage, AvgDays, Count.
98. Matter de-risking plan: You are a risk manager. For high-risk matters, propose a de-risking plan including milestones and owners. Output: plan_table with Matter, RiskFactor, Milestones, Owner.
99. Knowledge base auto-tagging: Task: Generate tags for matters to improve searchability in the knowledge base. Output: tag_table with Matter, Tags.
100. Excel data cleanup checklist: Role: Data steward. Provide a step-by-step cleanup checklist for an existing legal data workbook including deduplication, normalization, and validation. Output: cleanup_table with Step, Action, Responsible.

Best Practices

• Test prompts on small datasets before scaling to full datasets.
• Reuse prompts with consistent field names to build a reliable analytics layer.
• Document any data cleaning or transformation applied prior to analysis.
• Keep prompts focused on measurable metrics to avoid vague insights.
• Safeguard client privacy by omitting or masking sensitive fields in outputs.

Common Mistakes to Avoid

• Using vague or ambiguous placeholders that require guesswork from Gemini.
• Asking for outputs without defining the required format or data scope.
• Overloading prompts with too many objectives, causing mixed results.
• Neglecting data quality issues that undermine analysis accuracy.
• Not validating Gemini outputs against the actual data source.

FAQ

What are Gemini prompts for Excel data analysis in law firms?

Gemini prompts are structured directives that guide the AI to analyze Excel data, produce actionable tables, and generate insights tailored to law firm workflows.

How should I format outputs from Gemini prompts?

Ask for outputs in CSV, JSON, or table formats, and specify fields, aggregates, and ordering to fit your dashboards.

Can I reuse prompts across datasets?

Yes, use consistent field naming and business rules so prompts yield comparable results across datasets.

What data quality checks should I perform?

Check for missing fields, duplicates, inconsistent currencies, and date formats before analysis.

How do I handle sensitive client data in prompts?

Mask or exclude sensitive fields in outputs and follow your firm's data governance rules when sharing results.

How to validate Gemini results?

Cross-verify Gemini outputs with source data, perform spot checks, and reconcile any discrepancies.