Best Data Analysis Prompts for Gemini (2026)

Analyze this dataset and provide comprehensive insights.

Dataset

{paste your CSV data here - include headers and a representative sample}

Dataset Context

• What this data represents: {description}
• Time period: {date range}
• Source: {where data comes from}
• Known issues: {any data quality notes}

Analysis Request

1. Data Overview

• Number of records (visible in sample)
• Column descriptions and data types
• Missing values or anomalies observed

2. Summary Statistics

For numerical columns:

Column	Min	Max	Mean	Median	Observations

For categorical columns:

Column	Unique Values	Top 3 Values	Distribution Notes

3. Pattern Analysis

Identify:

• Trends: Direction and magnitude of changes over time
• Correlations: Relationships between variables
• Segments: Natural groupings in the data
• Outliers: Unusual values with possible explanations

4. Key Insights

List 5-7 actionable insights:

#	Insight	Evidence	Implication

5. Data Quality Notes

Issues that affect analysis reliability:

• Missing data patterns
• Potential data entry errors
• Sampling considerations

6. Recommended Next Steps

• Additional analysis to perform
• Questions to investigate
• Data to collect

Extract and prioritize actionable insights from this data/analysis.

Data/Analysis Results

{paste your data, charts, or analysis output}

Business Context

• Decision to inform: {what decision this analysis supports}
• Stakeholders: {who will use these insights}
• Constraints: {budget, time, resources}
• Success metrics: {how we measure good outcomes}

Insight Extraction

1. Raw Findings

List all observations from the data:

Finding	Data Point	Confidence

2. Insight Development

Transform findings into insights:

Finding	So What?	Now What?	Impact

3. Insight Prioritization Matrix

Rank insights by impact and actionability:

Insight	Business Impact	Ease of Action	Priority Score
(Use scale 1-5 for each dimension)

4. Top 5 Insights (Detailed)

For each priority insight:

Insight 1: [Title]

• What the data shows:
• Why it matters:
• Recommended action:
• Expected outcome:
• Risk if ignored:

{Repeat for insights 2-5}

5. Supporting vs. Contradicting Evidence

Insight	Supporting Data	Contradicting Data	Net Confidence

6. Quick Wins vs. Strategic Initiatives

Quick Wins (implement immediately):

Strategic Initiatives (require planning):

7. Insight Communication

How to present each insight to stakeholders:

Insight	Headline	Key Visual	One-line Summary

Analyze this data for anomalies and unusual patterns.

Data to Analyze

{paste your data}

Context

• What's being measured: {metric/process}
• Normal range: {expected values or historical benchmarks}
• Time period: {when data was collected}
• Known events: {anything that might explain anomalies}

Anomaly Analysis

1. Statistical Anomalies

Values outside expected ranges:

Data Point	Value	Expected Range	Deviation	Severity

2. Pattern Anomalies

Unusual sequences or behaviors:

Pattern	Location	Description	Typical Pattern	Difference

3. Temporal Anomalies

Time-based irregularities:

Time Period	Anomaly	Comparison Period	Change %

4. Anomaly Classification

Anomaly	Type	Likely Cause	Investigation Needed
	Data entry error
	System issue
	Genuine outlier
	Process change
	External factor

5. False Positive Assessment

Anomalies that might be explainable:

Anomaly	Possible Explanation	Probability of Real Issue

6. Impact Analysis

Anomaly	If Ignored	If False Alarm	Recommended Action

7. Monitoring Recommendations

Rules to catch similar anomalies in future:

Metric	Threshold	Alert Condition

Create an executive summary of this data analysis for senior leadership.

Detailed Analysis/Data

{paste your analysis, findings, or data}

Executive Context

• Audience: {CEO / CFO / Board / Department head}
• Decision being made: {what this informs}
• Time for review: {30 seconds / 2 minutes / 5 minutes}
• Preferred format: {bullet points / narrative / visual}

Executive Summary

1. The Bottom Line (30 seconds)

One paragraph that answers: What should the executive know and do?

2. Key Metrics Dashboard

Metric	Current	Previous	Change	Status
{Traffic light status: 🟢 🟡 🔴}

3. What's Working

Top 3 positive findings:

1. [Finding] → [Business impact]
2. [Finding] → [Business impact]
3. [Finding] → [Business impact]

4. What Needs Attention

Top 3 concerns:

1. [Issue] → [Risk if not addressed] → [Recommended action]
2. [Issue] → [Risk if not addressed] → [Recommended action]
3. [Issue] → [Risk if not addressed] → [Recommended action]

5. Recommendation

Primary recommendation:

• Action:
• Timeline:
• Investment required:
• Expected ROI:

Alternative options:

Option	Pros	Cons	Investment

6. Next Steps

Immediate actions (next 7 days):

• Action 1
• Action 2
• Action 3

7. Appendix Reference

Where to find supporting details:

• Full analysis: [location]
• Raw data: [location]
• Methodology: [location]

Write a narrative description and insights for this chart/visualization.

Chart Description

• Chart type: {line / bar / pie / scatter / other}
• X-axis: {what it represents}
• Y-axis: {what it represents}
• Data series: {what lines/bars represent}
• Time period: {dates covered}

Chart Data

{paste the data shown in the chart or describe key data points}

Visualization Context

• Where it will appear: {report / presentation / dashboard}
• Audience: {who will see this}
• Key message: {what should they take away}

Chart Narration

1. Chart Title Options (5)

Titles that communicate the key insight: 1. 2. 3. 4. 5.

2. One-Sentence Summary

The main takeaway in one clear sentence:

3. Narrative Description (100-150 words)

Full description of what the chart shows:

4. Key Data Points to Highlight

Data Point	Value	Why It Matters

5. Trend Analysis

• Overall direction: {up / down / stable / volatile}
• Rate of change: {description}
• Notable inflection points: {where trends changed}
• Seasonality: {if applicable}

6. Annotation Suggestions

Location on Chart	Annotation Text	Purpose

7. Comparison Context

How this compares to:

• Previous period:
• Industry benchmark:
• Target/goal:

8. So What? Statement

What action should this chart prompt:

9. Caveats

Important limitations or context:

Create comprehensive metric definitions and documentation.

Metrics to Define

{list the metrics you need documented}

Business Context

• Domain: {e.g., marketing, sales, product, finance}
• Use case: {how these metrics are used}
• Audience: {who needs to understand them}

Metric Documentation

For Each Metric:

---

Metric Name: [Name]

Also known as: [Alternative names/abbreviations]

Definition: [Clear, unambiguous definition in plain language]

Calculation:

Formula: [Mathematical formula]
Example: [Worked example with numbers]

Data Sources:

Source	Table/Field	Notes

Dimensions:

Dimension	Description	Values
Time		Daily/Weekly/Monthly
Segment
Product

Interpretation Guide:

• Good: [value range and what it means]
• Warning: [value range and what it means]
• Critical: [value range and what it means]

Common Misinterpretations:

• Pitfall 1: [what people get wrong]
• Pitfall 2: [what people get wrong]

Related Metrics:

Metric	Relationship

Update Frequency: [How often this metric is calculated]

Owner: [Team/person responsible]

---

{Repeat for each metric}

Metric Relationships

How these metrics connect: [Diagram or description of relationships]

Analyze trends in this data and provide forward-looking insights.

Historical Data

{paste time-series data}

Analysis Parameters

• Time period covered: {dates}
• Granularity: {daily / weekly / monthly / quarterly}
• Metric being analyzed: {what we're measuring}
• Known influencing factors: {events, seasonality, etc.}

Trend Analysis

1. Overall Trend Assessment

Metric	Direction	Strength	Confidence

2. Trend Decomposition

Break down into components:

• Long-term trend: {description}
• Seasonal patterns: {description}
• Cyclical patterns: {description}
• Irregular variations: {description}

3. Rate of Change Analysis

Period	Growth Rate	Acceleration	Notes

4. Inflection Points

When and why trends changed:

Date/Period	What Changed	Likely Cause	Impact

5. Seasonality Patterns

Season/Period	Typical Pattern	Magnitude	Confidence

6. Leading Indicators

What predicts changes in this metric:

Indicator	Lead Time	Correlation	Current Signal

7. Projection Scenarios

Scenario	Assumption	Projection	Confidence
Base case
Optimistic
Pessimistic

8. Risks to Projections

Risk	Probability	Impact	Mitigation

9. Monitoring Plan

What to watch going forward:

Signal	Threshold	Action if Triggered

Perform a comparison analysis across these groups/periods.

Comparison Data

{paste data for comparison}

Comparison Type

• Comparing: {segments / time periods / competitors / products}
• Metrics: {what measurements to compare}
• Purpose: {what decision this informs}

Comparison Analysis

1. Overview Comparison Matrix

Entity	Metric 1	Metric 2	Metric 3	Overall

2. Performance Rankings

For each metric:

Rank	Entity	Value	vs Average	vs Best

3. Gap Analysis

Where are the biggest differences:

Metric	Leader	Laggard	Gap	Gap %

4. Strengths & Weaknesses Matrix

Entity	Top Strength	Top Weakness	Net Assessment

5. Statistical Significance

Are differences meaningful:

Comparison	Difference	Significant?	Confidence

6. Contextual Factors

Factors that affect fair comparison:

Entity	Unique Factors	How It Affects Comparison

7. Best Practices Identified

What leaders do differently:

Leader	Best Practice	Applicable to Others?

8. Recommendations by Entity

Entity	Priority Improvement	Action	Expected Impact

9. Tracking Plan

How to monitor progress on gaps:

Gap	Current	Target	Timeline	Check-in

Perform a cohort analysis on this data.

Cohort Data

{paste your data with cohort identifiers}

Cohort Parameters

• Cohort definition: {what defines a cohort - signup month, acquisition source, etc.}
• Observation period: {how long we track each cohort}
• Key metric: {what we're measuring - retention, revenue, engagement}
• Cohorts to compare: {list specific cohorts}

Cohort Analysis

1. Cohort Summary Table

Cohort	Size	Metric at Month 1	Month 3	Month 6	Month 12

2. Retention/Progression Curves

Cohort	M0	M1	M2	M3	M4	M5	M6
(show retention or metric value over time for each cohort)

3. Cohort Comparison

Cohort	Best Performance	Worst Performance	Key Difference

4. Trend Across Cohorts

Are newer cohorts performing better or worse than older ones?

Time Period	Cohort Performance	Trend Direction	Significance

5. Cohort Quality Indicators

Early signals that predict long-term performance:

Indicator	Measured At	Correlation with LTV	Current Cohort Value

6. Cohort-Specific Insights

For each cohort, what's unique:

Cohort: [Name]

• Defining characteristics:
• Performance highlights:
• Key differences from average:
• Hypotheses for behavior:

7. Predictive Patterns

Based on early behavior, predict long-term outcomes:

Cohort	Month 1 Metric	Predicted Month 12	Confidence

8. Actionable Insights

Insight	Applicable Cohorts	Recommended Action

Perform root cause analysis on this metric change/problem.

The Problem

• Metric affected: {metric name}
• Expected value: {what it should have been}
• Actual value: {what it was}
• Variance: {difference / percentage}
• Time period: {when this occurred}

Available Data

{paste relevant data for investigation}

Root Cause Analysis

1. Problem Statement

Clear description of what went wrong:

2. Timeline of Events

Date/Time	Event	Metric Impact

3. Decomposition Analysis

Break down the metric into components:

Component	Expected	Actual	Variance	Contribution to Problem

4. Hypothesis Generation

Possible causes ranked by likelihood:

#	Hypothesis	Evidence For	Evidence Against	Likelihood

5. 5 Whys Analysis

For top hypothesis:

1. Why did [problem] happen? → [Answer 1]
2. Why did [Answer 1] happen? → [Answer 2]
3. Why did [Answer 2] happen? → [Answer 3]
4. Why did [Answer 3] happen? → [Answer 4]
5. Why did [Answer 4] happen? → [Root Cause]

6. Fishbone Diagram Categories

Categorize contributing factors:

Category	Contributing Factors
People
Process
Technology
Data
External

7. Root Cause Confirmation

Root Cause	Confirming Evidence	Confidence Level

8. Impact Assessment

Root Cause	Direct Impact	Indirect Impact	Total Impact

9. Remediation Plan

Root Cause	Short-term Fix	Long-term Fix	Owner	Timeline

10. Prevention Measures

How to prevent recurrence:

Measure	Type	Implementation Effort	Priority

Assess the quality of this dataset and identify issues.

Dataset to Assess

{paste sample data or data profile}

Data Context

• Source system: {where data comes from}
• Expected records: {how many should there be}
• Critical fields: {most important columns}
• Update frequency: {how often data refreshes}

Data Quality Assessment

1. Completeness Check

Column	Records	Non-Null	Null	Completeness %	Acceptable?

2. Accuracy Check

Column	Valid Values	Invalid Values	Accuracy %	Examples of Invalid

3. Consistency Check

Rule	Description	Passing	Failing	Examples of Failures

4. Timeliness Check

Metric	Expected	Actual	Status
Data freshness
Processing lag
Update gaps

5. Uniqueness Check

Key Column(s)	Total Records	Unique	Duplicates	Duplicate %

6. Data Quality Score

Dimension	Weight	Score (1-100)	Weighted Score
Completeness
Accuracy
Consistency
Timeliness
Uniqueness
Overall	100%

7. Critical Issues

Issue	Severity	Affected Records	Business Impact

8. Remediation Priority

Issue	Fix Complexity	Business Value	Priority Rank

9. Recommendations

Category	Recommendation	Owner	Timeline
Immediate fixes
Process changes
Monitoring

Create a repeatable report template for this type of analysis.

Report Requirements

• Report name: {what this report is called}
• Frequency: {daily / weekly / monthly / quarterly}
• Audience: {who reads this report}
• Purpose: {what decisions it informs}
• Key metrics: {list the metrics to include}

Report Template

1. Report Header

Report Title: [Name] Report — [Period] Generated: [Date/Time] Author: [Name/System] Distribution: [Recipients]

2. Executive Summary Section

[2-3 sentences summarizing the period's performance]

Key Numbers:

Metric	This Period	Previous Period	Change	Status
[Metric 1]	{value}	{value}	{%}	🟢/🟡/🔴
[Metric 2]	{value}	{value}	{%}	🟢/🟡/🔴
[Metric 3]	{value}	{value}	{%}	🟢/🟡/🔴

3. Performance Detail Sections

Section: [Area 1]

• Metric 1: {value} ({context})
• Metric 2: {value} ({context})
• Key insight: {observation}
• Action needed: {if any}

Section: [Area 2]

• Metric 1: {value} ({context})
• Metric 2: {value} ({context})
• Key insight: {observation}
• Action needed: {if any}

4. Trend Charts

[Placeholder for Chart 1: Description] [Placeholder for Chart 2: Description]

5. Highlights & Lowlights

What went well:

• {Highlight 1}
• {Highlight 2}

What needs attention:

• {Issue 1}
• {Issue 2}

6. Actions & Follow-ups

Action	Owner	Due Date	Status

7. Appendix

• Data sources
• Methodology notes
• Glossary of terms

---

Report Automation Notes

Element	Data Source	Calculation	Refresh
[Metric 1]
[Metric 2]

Structure a hypothesis test for this business question.

Business Question

{state the question you're trying to answer with data}

Available Data

{describe or paste the data you have}

Hypothesis Framework

1. Hypothesis Formulation

Null Hypothesis (H0): {The default assumption - what we'd believe without evidence}

Alternative Hypothesis (H1): {What we're testing for - the effect we suspect exists}

One-tailed or Two-tailed: {Direction of test and why}

2. Variables

Variable	Type	Measurement	Role
	Independent/Dependent	Scale/Unit	Treatment/Outcome

3. Test Selection

Recommended test: {test name} Justification: {why this test fits} Assumptions: {what must be true for test to be valid}

4. Sample Analysis

Group	Sample Size	Mean	Std Dev	Notes

5. Test Execution

Test statistic: {calculated value} P-value: {result} Confidence level: {95% / 99%} Effect size: {measure}

6. Results Interpretation

Outcome	Meaning	Confidence
If p < 0.05
If p >= 0.05

7. Practical Significance

Beyond statistical significance:

• Effect size interpretation:
• Business impact:
• Confidence in real-world application:

8. Limitations & Caveats

Limitation	Impact on Conclusions	Mitigation

9. Recommendations

Based on results:

• If hypothesis supported:
• If hypothesis not supported:
• Regardless of outcome:

10. Follow-up Questions

What additional analysis would strengthen conclusions:

Design a dashboard for this use case.

Dashboard Purpose

• Name: {dashboard name}
• Primary user: {role/team}
• Key decisions supported: {what users will decide based on this}
• Refresh frequency: {how often data updates}
• Access level: {who can view}

Dashboard Design

1. Key Performance Indicators (Top-level)

KPI	Definition	Target	Visualization	Position
			Number card	Top left
			Number card	Top center
			Number card	Top right

2. Main Visualizations

Chart #	Type	Data Shown	Insight It Provides	Position
1
2
3
4

3. Filters & Controls

Filter	Type	Default Value	Affects
Date range	Dropdown	Last 30 days	All charts

4. Drill-down Capabilities

Chart	Drill Into	Shows

5. Layout Wireframe

+------------------+------------------+------------------+
|     KPI 1        |     KPI 2        |     KPI 3        |
+------------------+------------------+------------------+
|                                                        |
|                    Chart 1 (wide)                      |
|                                                        |
+---------------------------+----------------------------+
|                           |                            |
|     Chart 2               |     Chart 3                |
|                           |                            |
+---------------------------+----------------------------+
|                                                        |
|                    Chart 4 / Table                     |
|                                                        |
+-------------------------------------------------------+

6. Data Requirements

Metric/Field	Source Table	Calculation	Refresh

7. Alert Conditions

Metric	Condition	Alert Type	Recipients

8. User Interaction Flows

User Action	Expected Result	Navigation

9. Mobile Considerations

Priority metrics for mobile view: 1. 2. 3.

Analyze these survey results and provide actionable insights.

Survey Data

{paste survey results or summary}

Survey Context

• Survey purpose: {why this survey was conducted}
• Target population: {who was surveyed}
• Sample size: {number of responses}
• Response rate: {if known}
• Collection period: {when}

Survey Analysis

1. Response Overview

Metric	Value
Total responses
Complete responses
Partial responses
Response rate
Confidence level

2. Demographic Breakdown

Segment	Count	% of Total	Notes

3. Question-by-Question Analysis

Question: [Question text]

Response Option	Count	Percentage	Insight

Key finding:

{Repeat for each question}

4. Cross-tabulation Insights

Segment	Question	Notable Difference	Significance

5. Open-Ended Response Themes

Theme	Frequency	Example Quotes	Sentiment

6. Key Findings Summary

#	Finding	Data Support	Implications
1
2
3

7. Sentiment Analysis

Topic	Positive	Neutral	Negative	Net Score

8. Recommendations

Priority	Recommendation	Based On	Expected Impact

9. Limitations

Limitation	Impact on Findings	Mitigation

10. Follow-up Research

Questions raised that need further investigation: