100 Prompt AI สำหรับวิเคราะห์ธุรกิจครบ 4 ระดับ ตามแนวคิด Gartner’s

Objective:
Create an executive summary from the dataset or business information I provide.

Context:
I want a concise summary focused on “what happened” only, based on Gartner’s Descriptive Analytics stage.

Tasks:
1. Summarize the most important metrics.
2. Highlight notable increases, decreases, and anomalies.
3. Show the top 5 insights from the data.
4. Separate facts from interpretation.
5. End with a short management takeaway.

Output format:
– Section 1: Executive Summary
– Section 2: Key Metrics
– Section 3: Notable Changes
– Section 4: Top 5 Facts
– Section 5: Management Takeaway

Constraints:
– Do not guess causes.
– Use only the information provided.
– Write in clear business language.
– If data is missing, state what is missing.

Here is the data/information:
[PASTE DATA]

Goal:
Summarize KPI performance and explain what happened during the selected period.

Use Gartner’s Descriptive Analytics logic:
Focus only on observed results, trends, and metric movements.

Please:
1. List all KPIs with current value, target, variance, and status.
2. Identify which KPIs beat target, missed target, or stayed flat.
3. Rank the 3 strongest and 3 weakest KPIs.
4. Summarize the overall performance in plain business language.

Output:
– KPI table
– Wins
– Gaps
– Overall summary
– Questions for the team to investigate next

Data:
[PASTE KPI DATA]

Task:
Analyze the sales data and summarize what happened in this period.

Focus areas:
– Revenue
– Units sold
– Average order value
– Top products
– Top channels
– Top regions
– Significant fluctuations

Please provide:
1. A concise narrative summary
2. A breakdown by time period
3. A breakdown by product/channel/region
4. A list of unusual observations

Rules:
– Stay descriptive only.
– Do not speculate on causes.
– Use bullet points where helpful.

Data:
[PASTE SALES DATA]

Using Gartner’s Descriptive Analytics stage, summarize what happened in customer behavior data.

Analyze:
– Number of customers
– New vs returning customers
– Purchase frequency
– Basket size
– Channel usage
– Engagement levels
– Retention indicators

Output format:
– Customer overview
– Metric summary
– Segment highlights
– Pattern observations
– Data gaps

Input:
[PASTE CUSTOMER DATA]

Objective:
Summarize the campaign results based on descriptive analytics only.

Please evaluate:
– Reach
– Impressions
– CTR
– CPC
– Leads
– Conversions
– Cost per lead
– ROAS or ROI if available

Deliver:
1. Campaign summary
2. Best-performing metrics
3. Weakest metrics
4. Top-performing channels/creatives/audiences
5. A simple conclusion on what happened

Data:
[PASTE CAMPAIGN DATA]

Analyze the product data and summarize what happened.

Include:
– Top-selling products
– Low-performing products
– Sales contribution by product
– Margin if available
– Growth/decline by SKU
– Product mix shifts

Output:
– Summary
– Product ranking
– Contribution analysis
– Key observations
– Items needing deeper review

Data:
[PASTE PRODUCT DATA]

I need a descriptive summary of branch/regional performance.

Analyze:
– Sales
– Footfall
– Conversion
– Productivity
– Average transaction value
– Branch ranking
– Outliers

Format:
– Overall summary
– Top branches
– Underperforming branches
– Regional comparison
– Key factual findings

Do not explain why performance differs yet.

Data:
[PASTE DATA]

Based on the dashboard figures I provide, write a weekly business narrative using descriptive analytics.

Requirements:
1. Explain what changed this week versus last week.
2. Highlight major metric movements.
3. Point out visible patterns.
4. Use concise executive language.
5. Keep the summary under 400 words.

Dashboard data:
[PASTE DASHBOARD METRICS]

Compare the following data across periods and summarize what happened.

Please compare:
– Current period vs previous period
– Current period vs same period last year
– Absolute change
– Percentage change
– Notable trend shifts

Output:
– Comparison summary
– Table of changes
– Biggest positive shifts
– Biggest negative shifts
– Neutral observations

Data:
[PASTE DATA]

Create a formal descriptive analytics report from the information below.

Sections required:
1. Report objective
2. Scope of data
3. Summary of results
4. Key metrics
5. Trend observations
6. Notable outliers
7. Recommended next questions for analysis

Tone:
Professional, concise, suitable for management review.

Data:
[PASTE DATA]

Objective:
Identify likely reasons behind the performance changes in the data.

Use Gartner’s Diagnostic Analytics logic:
Move from “what happened” to “why it likely happened.”

Tasks:
1. Identify the main issue or change.
2. List possible contributing factors.
3. Separate strong evidence from weak assumptions.
4. Show relationships between variables if visible.
5. Suggest what additional data is needed to confirm the root cause.

Output:
– Main issue
– Possible causes
– Evidence supporting each cause
– Confidence level
– Next data to check

Data:
[PASTE DATA]

Analyze why sales may have dropped based on the information below.

Check possible drivers such as:
– Traffic decline
– Conversion decline
– Price changes
– Product availability
– Channel mix
– Competitor actions
– Seasonality
– Customer mix changes

Output:
– Problem statement
– Likely causes ranked by probability
– Evidence for each cause
– What should be validated next

Data:
[PASTE DATA]

I need to diagnose why conversion performance changed.

Analyze:
– Traffic quality
– Landing page behavior
– Drop-off points
– Offer attractiveness
– Channel mismatch
– Audience relevance
– Sales follow-up issues if applicable

Deliver:
1. Funnel breakdown
2. Where the biggest leakage occurs
3. Hypotheses for why it occurs
4. Priority areas for investigation

Data:
[PASTE FUNNEL DATA]

Task:
Diagnose why customer churn may be happening.

Please assess:
– Churn pattern by segment
– Time-to-churn
– Product/service usage changes
– Complaint trends
– Service issues
– Pricing issues
– Engagement drop
– Competitive alternatives if mentioned

Output:
– Churn summary
– Likely churn drivers
– Segment-level diagnosis
– Warning signs
– Questions to validate

Input data:
[PASTE DATA]

Diagnose why this campaign underperformed.

Review:
– Audience targeting
– Creative performance
– Channel fit
– Offer/message fit
– Funnel friction
– Budget allocation
– Timing
– Tracking/data quality

Output:
– Main underperformance symptoms
– Most likely reasons
– Evidence by metric
– Priority fixes to test

Campaign data:
[PASTE DATA]

Analyze why certain SKUs are underperforming.

Investigate possible causes:
– Price positioning
– Shelf visibility
– Promotion support
– Stockouts
– Product-market mismatch
– Packaging issues
– Low awareness
– Weak distribution

Output:
– Underperforming SKU list
– Root cause hypotheses
– Supporting signals
– Missing information to verify

Data:
[PASTE DATA]

Compare strong and weak branches to diagnose why gaps exist.

Assess:
– Traffic
– Staffing
– Conversion
– Product mix
– Local demand
– Operations quality
– Promotions
– Service levels

Output:
– Gap summary
– Main likely causes
– Branch comparison table
– Recommendations for further investigation

Data:
[PASTE DATA]

Diagnose why customer complaints increased.

Analyze:
– Complaint categories
– Timing
– Affected products/services
– Customer segments
– Branch/channel concentration
– Operational incidents
– Staff/process issues

Output:
– Complaint spike summary
– Likely causes
– Supporting evidence
– Immediate issues to review

Data:
[PASTE DATA]

Explain why actual results differ from plan, target, or budget.

Please break down variance by:
– Volume
– Price
– Mix
– Productivity
– Timing
– Channel
– Geography
– Operational factors

Output:
– Total variance summary
– Variance drivers
– What appears controllable vs uncontrollable
– What needs management attention

Data:
[PASTE PLAN VS ACTUAL DATA]

Apply a structured 5 Whys analysis to the issue below using the provided data.

Instructions:
1. Define the problem clearly.
2. Walk through 5 layers of why.
3. At each step, distinguish fact, inference, and assumption.
4. Identify the most probable root cause.
5. Suggest what evidence is needed to confirm.

Issue:
[DESCRIBE ISSUE]

Supporting data:
[PASTE DATA]

Goal:
Forecast future sales based on historical patterns and business context.

Please:
1. Estimate the next [period].
2. Identify trend, seasonality, and anomalies.
3. Provide base case, optimistic case, and conservative case.
4. State assumptions clearly.
5. Highlight risks to forecast accuracy.

Output:
– Forecast summary
– Scenario forecast table
– Key assumptions
– Risk factors
– Confidence notes

Historical data:
[PASTE DATA]
Business context:
[PASTE CONTEXT]

Forecast customer demand for the next [time period].

Use:
– Historical volume
– Seasonality
– Promotions
– Customer trends
– Channel shifts
– Business events if provided

Please deliver:
– Expected demand
– Drivers behind the forecast
– High/medium/low scenario
– Where uncertainty is highest

Data:
[PASTE DATA]

Based on the data and customer behavior patterns provided, estimate which customer groups are at highest risk of churn.

Please:
1. Identify leading indicators of churn.
2. Rank customer segments by churn risk.
3. Explain why each segment is high/medium/low risk.
4. Suggest early warning signals to monitor.

Output:
– Churn risk ranking
– Risk rationale
– Warning indicators
– Monitoring recommendations

Data:
[PASTE DATA]

Forecast lead-to-sale conversion outcomes based on past performance and current pipeline data.

Analyze:
– Lead volume
– Lead quality
– Funnel stage movement
– Sales cycle duration
– Conversion history
– Source/channel quality

Output:
– Forecasted conversions
– Expected revenue range
– Best/worst case
– Risks and assumptions

Data:
[PASTE PIPELINE DATA]

Predict inventory risks for the next [period].

Assess:
– Stockout risk
– Overstock risk
– Demand volatility
– Reorder timing
– Slow movers
– Fast movers

Output:
– Risk summary
– SKU/category risk table
– Forecast signals
– Suggested watchlist

Data:
[PASTE DATA]

Create revenue projections under multiple scenarios.

Scenarios required:
– Base case
– Upside case
– Downside case

Include assumptions for:
– Volume
– Price
– Conversion
– Retention
– Marketing efficiency
– Market factors if available

Output:
– Scenario table
– Narrative summary
– Sensitivity drivers
– Risks to each scenario

Data:
[PASTE DATA]

Forecast branch/store traffic for the next [period].

Use:
– Historical traffic
– Day-of-week patterns
– Seasonality
– Promotions
– Local events if provided
– Store-level trends

Output:
– Traffic forecast by branch
– Peak/low traffic expectations
– Risk areas
– Operational implications

Data:
[PASTE DATA]

Predict likely campaign results given the following budget, channel mix, historical performance, and target audience.

Estimate:
– Reach
– Clicks
– Leads
– Conversions
– Cost efficiency
– ROI if possible

Output:
– Forecast summary
– Assumptions
– Scenario comparison
– Major forecast risks

Inputs:
[PASTE DATA]

Forecast staffing requirements based on projected workload, service demand, and historical productivity.

Please estimate:
– Required headcount
– Peak demand periods
– Capacity gaps
– Overtime risk
– Team bottlenecks

Output:
– Workforce forecast
– Capacity assumptions
– Risk analysis
– Hiring or scheduling implications

Data:
[PASTE DATA]

Using the data below, identify early warning indicators that may signal future performance issues.

Focus on:
– Revenue risk
– Churn risk
– Margin risk
– Inventory risk
– Service quality risk
– Operational delay risk

Output:
– Early warning dashboard
– Leading indicators
– Risk severity
– What to monitor weekly

Data:
[PASTE DATA]

Based on the analysis and business context below, recommend the best next actions.

Use Gartner’s Prescriptive Analytics logic:
Move from insight to recommended action.

Please:
1. List the top action options.
2. Rank them by impact and feasibility.
3. Explain expected benefit, cost, and risk.
4. Suggest a 30-60-90 day action plan.

Output:
– Recommended actions
– Priority ranking
– Rationale
– 30-60-90 plan

Context and data:
[PASTE DATA]

Recommend practical actions to recover sales performance.

Requirements:
– Prioritize actions by impact and speed
– Separate quick wins from structural fixes
– Suggest owners, timelines, and KPIs
– Include risks and dependencies

Output:
– Immediate actions
– Short-term actions
– Medium-term actions
– KPIs to monitor

Business data:
[PASTE DATA]

Review the current allocation and recommend how to reallocate budget for better results.

Please evaluate:
– Which areas are overfunded
– Which areas are underfunded
– What should be reduced, increased, paused, or tested
– Expected trade-offs

Output:
– Reallocation recommendations
– Rationale
– Expected impact
– Risks
– Pilot approach

Data:
[PASTE BUDGET + PERFORMANCE DATA]

Recommend actions to reduce churn and improve retention.

Please structure recommendations by:
– Segment
– Offer
– Timing
– Channel
– Service intervention
– Communication strategy

Output:
– Priority customer segments
– Recommended interventions
– Expected effect
– Measurement plan

Data:
[PASTE DATA]

Based on the performance data, recommend what to do with each product or SKU:
– Invest more
– Maintain
– Fix
– Bundle
– Reposition
– Delist

Please justify each recommendation with evidence.

Output:
– Portfolio decision matrix
– Recommended actions by SKU
– Expected business impact
– Risks and cautions

Data:
[PASTE DATA]

Recommend action plans for improving weak branch/store performance.

Please include:
– Immediate fixes
– Process fixes
– Staffing or training fixes
– Local marketing actions
– Management controls
– KPIs for follow-up

Output:
– Branch issue summary
– Action plan by branch
– Priority sequence
– Tracking plan

Data:
[PASTE DATA]

Recommend the best actions to improve conversion based on the funnel data provided.

Cover:
– Traffic quality
– Messaging
– Offer
– UX
– Sales follow-up
– Retargeting
– Lead qualification

Output:
– Highest-priority actions
– Test ideas
– Expected impact
– Metrics to track

Data:
[PASTE FUNNEL DATA]

Recommend pricing actions based on the sales, margin, and customer response data.

Please advise on:
– Raise price
– Lower price
– Keep price
– Repackage offer
– Use promotion instead of price cut
– Segment-based pricing if relevant

Output:
– Recommended pricing path
– Why
– Potential upside/downside
– Validation tests to run

Data:
[PASTE DATA]

Write a decision memo recommending what management should do next based on the analysis.

Memo structure:
1. Situation
2. Key findings
3. Options considered
4. Recommended decision
5. Why this option is best
6. Risks
7. Immediate next steps

Tone:
Executive, concise, actionable.

Input:
[PASTE DATA]

Create a practical roadmap from analysis to execution.

Please provide:
– Priority initiatives
– Timeline
– Owners
– Dependencies
– Required resources
– KPIs
– Risk controls

Format:
– 0-30 days
– 31-90 days
– 91-180 days

Context:
[PASTE DATA]

Evaluate the organization’s current analytics maturity using Gartner’s Analytics Maturity Model:
– Descriptive
– Diagnostic
– Predictive
– Prescriptive

Assess across:
– Data quality
– Reporting
– Insight generation
– Forecasting capability
– Decision-making discipline
– Automation
– People and skills
– Governance

Output:
– Current maturity level
– Evidence for the assessment
– Strengths
– Gaps
– What is needed to move to the next stage

Organization information:
[PASTE CONTEXT]

Assess analytics maturity by department/function.

Functions to review:
[LIST DEPARTMENTS]

For each function, evaluate:
– Data usage
– Reporting maturity
– Root cause analysis capability
– Forecasting capability
– Decision support capability
– Process integration

Output:
– Maturity score by department
– Stage classification
– Key gaps
– Development priorities

Context:
[PASTE CONTEXT]

Compare the organization’s current analytics maturity with the target maturity level.

Please identify:
– Current capabilities
– Missing capabilities
– Required tools/processes/skills
– Quick wins
– Structural changes needed

Output:
– Current state
– Target state
– Gap analysis
– Priority actions

Context:
[PASTE CONTEXT]
Target maturity:
[DESCRIBE TARGET]

Evaluate whether this organization is ready to move into predictive analytics.

Assess:
– Historical data sufficiency
– Data quality and consistency
– Business definitions
– Modeling use cases
– Team skills
– Technology readiness
– Governance

Output:
– Readiness verdict
– Strengths
– Risks
– Gaps to fix first
– Suggested next steps

Context:
[PASTE CONTEXT]

Assess readiness for prescriptive analytics and decision optimization.

Check:
– Forecast reliability
– Decision rules
– Business constraints
– Scenario planning ability
– Cross-functional alignment
– Execution mechanisms
– Monitoring capability

Output:
– Readiness assessment
– Missing building blocks
– Major risks
– Roadmap to readiness

Context:
[PASTE CONTEXT]

Create a self-assessment questionnaire for managers to evaluate analytics maturity.

Requirements:
– 25 to 40 questions
– Cover people, process, data, tools, governance, and decision-making
– Map questions to the 4 Gartner maturity stages
– Include a simple scoring method

Output:
– Questionnaire
– Scoring rubric
– Interpretation guide

Context:
[PASTE ORG TYPE]

Based on the assessment findings below, create a maturity heatmap structure.

Dimensions:
– Business unit
– Data quality
– Reporting
– Diagnostics
– Forecasting
– Prescriptive decision support
– Talent
– Governance

Output:
– Heatmap table
– Color legend suggestion
– Executive interpretation
– Priority red zones

Input:
[PASTE FINDINGS]

Identify the highest-priority investments to improve analytics maturity.

Please rank opportunities by:
– Business impact
– Feasibility
– Cost
– Time to value
– Dependency level

Output:
– Ranked priority list
– Why each item matters
– Recommended sequencing
– Quick wins vs foundational work

Assessment input:
[PASTE CONTEXT]

Write a leadership brief summarizing the organization’s analytics maturity.

Include:
– Where we are today
– What that means in business terms
– Risks of staying here
– Benefits of moving up one level
– Top 5 actions leadership should support

Tone:
Executive, non-technical, persuasive.

Input:
[PASTE ASSESSMENT]

Create a discussion guide to help leadership evaluate analytics maturity and agree on the next-stage ambition.

Please include:
– Key reflection questions
– Warning signs of low maturity
– Signs of readiness for the next stage
– Debate questions
– Decision criteria

Context:
[PASTE CONTEXT]

Build a KPI tree from the business objective below.

Please:
1. Start with the main business goal.
2. Break it into driver metrics.
3. Break each driver into operational metrics.
4. Distinguish leading vs lagging indicators.
5. Explain how each KPI supports analytics maturity.

Business objective:
[PASTE OBJECTIVE]

Standardize the following KPI definitions.

For each metric, define:
– Business definition
– Formula
– Data source
– Frequency
– Owner
– Caveats
– Misinterpretation risks

Output:
– KPI dictionary
– Recommended standard definitions
– Governance notes

Metrics:
[PASTE KPI LIST]

Classify the following KPIs into leading indicators and lagging indicators.

For each KPI, explain:
– Why it is leading or lagging
– What decision it supports
– Which maturity stage it is most useful for
– How it should be monitored

KPIs:
[PASTE LIST]

Create a data requirements checklist for the following analytics use case.

Include:
– Required data fields
– Time horizon
– Granularity
– Data quality checks
– Access requirements
– Business definitions
– Risks if missing

Use case:
[PASTE USE CASE]

Design dashboard requirements for the business scenario below.

Please include:
– Target users
– Key decisions the dashboard should support
– Must-have KPIs
– Drill-down dimensions
– Alert conditions
– Recommended layout sections

Business scenario:
[PASTE SCENARIO]

Review the data below and identify possible quality issues that may distort analytics.

Check for:
– Missing values
– Duplicates
– Inconsistent definitions
– Abnormal spikes
– Timing mismatches
– Unit errors
– Data integrity concerns

Output:
– Data quality issues
– Severity
– Likely business impact
– Suggested fixes

Data:
[PASTE DATA]

Map each KPI to its likely source systems, data elements, owners, and update frequency.

Output:
– KPI name
– Source system
– Required fields
– Transformation logic
– Owner
– Update frequency
– Risk notes

KPI list:
[PASTE LIST]
System context:
[PASTE CONTEXT]

Convert the business questions below into data requirements and analysis structure.

For each question, provide:
– Analytical objective
– Required metrics
– Required dimensions
– Time period
– Likely method
– Expected output format

Business questions:
[PASTE QUESTIONS]

Prioritize the KPI list below using these criteria:
– Strategic importance
– Actionability
– Data availability
– Reliability
– Predictive value

Output:
– Priority matrix
– Must-track KPIs
– Nice-to-have KPIs
– KPIs to retire or deprioritize

KPI list:
[PASTE LIST]

Assess whether the available data is sufficient to support descriptive, diagnostic, predictive, and prescriptive decision-making.

Output:
– What decisions can already be supported
– What cannot yet be supported
– Missing data or logic
– Maturity stage currently enabled
– Next steps to improve readiness

Available data/context:
[PASTE DATA]

Generate analytics use cases for the marketing team based on Gartner’s maturity model.

Please organize by:
– Descriptive use cases
– Diagnostic use cases
– Predictive use cases
– Prescriptive use cases

For each use case, include:
– Objective
– Example question
– Data needed
– Expected business value

Business context:
[PASTE CONTEXT]

Generate practical analytics use cases for sales teams using Gartner’s analytics maturity framework.

Please structure each use case with:
– Business question
– Maturity stage
– Data needed
– Output
– Action supported

Context:
[PASTE SALES CONTEXT]

Create HR analytics use cases across the 4 Gartner maturity stages.

Cover areas such as:
– Recruitment
– Turnover
– Performance
– Engagement
– Training
– Workforce planning

For each use case, show:
– What question it answers
– Which maturity stage it belongs to
– What data is required
– What decision it improves

Context:
[PASTE HR CONTEXT]

Generate finance analytics use cases aligned to Gartner’s analytics maturity model.

Include examples for:
– Revenue
– Cost control
– Margin
– Variance analysis
– Forecasting
– Cash flow
– Decision support

Output:
– Use case list by maturity stage
– Business value
– Implementation difficulty

Context:
[PASTE FINANCE CONTEXT]

Create analytics use cases for operations teams using the Gartner maturity framework.

Consider:
– Productivity
– Cycle time
– Quality
– Capacity
– Bottlenecks
– Service levels
– Forecasting
– Optimization

For each use case, include objective, data, insight, and action.

Context:
[PASTE OPS CONTEXT]

Generate branch/store analytics use cases by maturity stage.

Cover:
– Traffic
– Conversion
– Basket size
– Product mix
– Promotion response
– Staffing
– Inventory
– Local actions

Output:
– Descriptive use cases
– Diagnostic use cases
– Predictive use cases
– Prescriptive use cases

Context:
[PASTE CONTEXT]

Generate practical CX analytics use cases across all 4 maturity stages.

Include:
– Complaint analytics
– Satisfaction drivers
– Churn indicators
– Journey friction points
– Next best action ideas

Output:
– Use cases
– Data needed
– Maturity level
– Expected business benefit

Context:
[PASTE CX CONTEXT]

Generate executive-level analytics use cases that help leadership move from reporting to better decisions.

Please include:
– Strategic question
– Maturity stage
– Decision supported
– Metrics required
– Meeting format where it can be used

Context:
[PASTE EXECUTIVE CONTEXT]

Based on the business context below, identify opportunities where AI can enhance analytics maturity.

Please classify opportunities into:
– Better descriptive reporting
– Better diagnostic explanation
– Better prediction
– Better recommendation/decision support

For each opportunity, include:
– Use case
– Value
– Complexity
– Data readiness
– Risk

Context:
[PASTE CONTEXT]

Create a cross-functional analytics roadmap showing how different departments can progress through Gartner’s analytics maturity model together.

Include:
– Shared foundations
– Department-specific quick wins
– Enterprise-wide dependencies
– Governance needs
– Phased roadmap

Organization context:
[PASTE CONTEXT]

Compare the following business scenarios and estimate likely outcomes, trade-offs, and recommended choice.

For each scenario, evaluate:
– Expected impact
– Cost
– Risk
– Time to value
– Operational complexity
– Strategic fit

Output:
– Scenario comparison table
– Best option
– Why
– Cautions
– Decision criteria

Scenarios:
[PASTE SCENARIOS]
Context:
[PASTE DATA]

Create best-case, base-case, and worst-case projections for the situation below.

Include:
– Main assumptions
– Trigger conditions for each scenario
– Business implications
– What management should watch closely

Input:
[PASTE CONTEXT AND DATA]

Build a practical decision tree for the issue below.

Please structure:
– Decision objective
– Key branching criteria
– Thresholds or trigger metrics
– Recommended actions at each branch
– Escalation points

Issue:
[PASTE ISSUE]
Data/context:
[PASTE DATA]

Evaluate the trade-offs among the options below.

Please assess:
– Financial impact
– Strategic fit
– Risk
– Resource requirement
– Speed
– Reversibility
– Customer impact

Output:
– Trade-off matrix
– Recommended option
– What is sacrificed
– What is gained

Options:
[PASTE OPTIONS]
Context:
[PASTE CONTEXT]

Run a structured what-if analysis on the variables below.

Please estimate the likely impact if we change:
– Price
– Budget
– Conversion rate
– Headcount
– Retention
– Demand volume
– Productivity

Output:
– What-if scenarios
– Likely impact by variable
– Most sensitive variables
– Recommended focus area

Base data:
[PASTE DATA]

Based on the risks identified below, recommend mitigation actions.

For each risk, provide:
– Severity
– Likelihood
– Business impact
– Preventive action
– Contingency action
– Monitoring metrics

Risks/data:
[PASTE INPUT]

Recommend which initiatives to prioritize under limited budget, people, and time constraints.

Please rank initiatives by:
– Business impact
– Urgency
– Feasibility
– Dependency
– Cost
– Risk

Output:
– Priority ranking
– Why each initiative is ranked that way
– What to defer
– Suggested sequencing

Initiatives:
[PASTE LIST]
Constraints:
[PASTE CONSTRAINTS]

Create a concise briefing note for the following decision.

Include:
– Decision to be made
– Relevant facts
– Main options
– Pros and cons
– Recommended option
– Questions executives should ask
– Risks after decision

Context:
[PASTE CONTEXT]

Analyze which variables most strongly affect the outcome.

Please test sensitivity for:
– Revenue drivers
– Cost drivers
– Conversion
– Retention
– Demand assumptions
– Pricing assumptions

Output:
– Most sensitive variables
– Low sensitivity variables
– Management implications
– Recommended monitoring priorities

Base model/context:
[PASTE DATA]

Recommend the best course of action, but make your reasoning transparent.

Requirements:
– State assumptions clearly
– Distinguish facts from assumptions
– List recommendation options
– Explain why the chosen option is best
– Highlight uncertainty and missing information

Context and data:
[PASTE INPUT]

Convert the analysis below into plain business language for senior leaders.

Please:
– Avoid technical jargon
– Focus on business meaning
– Explain what happened, why it matters, and what to do next
– Keep it concise and persuasive

Analysis:
[PASTE ANALYSIS]

Turn the analysis below into a board-ready slide summary.

Structure:
– Situation
– Key insights
– Risks
– Recommended decisions
– Expected impact

Tone:
Sharp, concise, executive.

Input:
[PASTE ANALYSIS]

Create a report that connects:
1. What happened
2. Why it happened
3. What may happen next
4. What we should do

Use the analysis below and structure the report clearly.

Input:
[PASTE ANALYSIS OR DATA]

Create a one-page analytics brief from the information below.

Must include:
– Objective
– What happened
– Why it matters
– Risks
– Recommended next actions
– KPIs to watch

Keep it concise and decision-oriented.

Input:
[PASTE DATA]

Based on the analysis below, create discussion questions for a management meeting.

Please include:
– Clarifying questions
– Challenge questions
– Decision questions
– Risk questions
– Next-step questions

Analysis:
[PASTE ANALYSIS]

Turn the data and findings below into a clear storyline:
– What happened
– Why it happened
– What will likely happen
– What we should do now

Output:
– Headline
– Narrative arc
– Supporting evidence
– Final recommendation

Input:
[PASTE DATA]

Write a concise leadership email summarizing the analytics findings and recommended actions.

Requirements:
– Clear subject line
– 5-7 short paragraphs or bullet sections
– Focus on implications and decisions
– End with requested actions or approvals

Input:
[PASTE DATA/ANALYSIS]

Translate the analysis below into a team action summary.

Include:
– What the team needs to know
– What actions are required
– Who should do what
– What metrics to track
– What deadline matters

Input:
[PASTE ANALYSIS]

Write dashboard commentary based on the KPI movements below.

Please include:
– Key movements
– Likely interpretation
– Issues needing attention
– Follow-up questions
– Action areas

Dashboard metrics:
[PASTE DATA]

Prepare an approval summary for the proposed action plan.

Include:
– Background
– Key evidence
– Recommended action
– Expected impact
– Cost/resource needs
– Risks
– Approval needed

Input:
[PASTE PROPOSAL OR ANALYSIS]

Analyze the input using Gartner’s Analytics Maturity Model in 4 stages:

Stage 1: Descriptive
– What happened?

Stage 2: Diagnostic
– Why did it happen?

Stage 3: Predictive
– What is likely to happen next?

Stage 4: Prescriptive
– What should we do now?

Requirements:
– Separate each stage clearly
– Distinguish fact, inference, and assumption
– Highlight missing data
– End with a prioritized action plan

Input:
[PASTE DATA]

Work in 4 steps and pause conceptually between each step:
1. Summarize what happened
2. Diagnose likely causes
3. Predict near-term outcomes
4. Recommend actions

For each step:
– Show reasoning summary
– State confidence level
– Mention missing information
– Keep business language simple

Business data:
[PASTE INPUT]

Based on the business situation below, generate the best analytical questions to ask at each Gartner maturity stage.

Please provide:
– Descriptive questions
– Diagnostic questions
– Predictive questions
– Prescriptive questions

For each question, explain:
– Why it matters
– What data is needed
– What decision it may influence

Context:
[PASTE SITUATION]

From the data below:
1. Summarize the issue
2. Generate 5-7 plausible hypotheses
3. Rank hypotheses by likelihood
4. Suggest how each hypothesis can be tested
5. Recommend next actions based on the strongest hypothesis

Input:
[PASTE DATA]

Analyze the situation below with the explicit goal of supporting a business decision.

Please provide:
– What happened
– Why it matters
– What options exist
– Which option is best
– What assumptions could change the recommendation

Business context:
[PASTE INPUT]
Decision to support:
[PASTE DECISION]

Review the analysis below and identify weaknesses.

Check for:
– Unsupported conclusions
– Confusion between fact and assumption
– Missing diagnostic depth
– Weak forecasting logic
– Poor action recommendations
– Data quality concerns

Output:
– Strengths
– Weaknesses
– What to fix
– Better version suggestions

Analysis:
[PASTE ANALYSIS]

Create a structured template that turns raw data into:
– Insight
– Interpretation
– Forecast
– Recommendation
– Action tracking

Make the template easy to reuse weekly or monthly.

Business context:
[PASTE CONTEXT]

Follow these operating rules in every analysis:
1. Start with descriptive facts.
2. Do not jump to conclusions without evidence.
3. Separate diagnosis from prediction.
4. Separate prediction from recommendation.
5. Always state assumptions and confidence.
6. Identify missing data.
7. Make recommendations practical and prioritized.

Now apply these rules to the following case:
[PASTE CASE]

Help the team work through Gartner’s 4 analytics maturity stages for the business issue below.

Please provide:
– Workshop agenda
– Key questions by stage
– Required data inputs
– Activities for each team
– Expected outputs
– Final action alignment questions

Business issue:
[PASTE ISSUE]

Use Gartner’s Analytics Maturity Model to analyze the information I provide.

Your workflow must follow these stages:

1. Descriptive Analytics
– Summarize what happened
– Highlight key metrics, patterns, and anomalies

2. Diagnostic Analytics
– Explain why it may have happened
– List likely causes and supporting evidence
– Distinguish fact from assumption

3. Predictive Analytics
– Forecast what is likely to happen next
– Show scenarios, assumptions, and uncertainty

4. Prescriptive Analytics
– Recommend what we should do next
– Prioritize actions by impact and feasibility
– Suggest KPIs to monitor after action

Output format:
– Executive Summary
– Stage 1: Descriptive
– Stage 2: Diagnostic
– Stage 3: Predictive
– Stage 4: Prescriptive
– Priority Action Plan
– Risks and Assumptions
– Missing Data / Next Questions

Constraints:
– Use only the provided information unless I ask for external assumptions
– Be explicit when confidence is low
– Keep language business-friendly
– Focus on actionable outcomes

Business context / data:
[PASTE INPUT]