100 Best ChatGPT Prompts for Business Intelligence

Introduction

This page is a practical prompt library for Business Intelligence, designed for analysts, data engineers, and BI leaders who want to accelerate insights using ChatGPT prompts. Use these prompts to define KPIs, model data, build dashboards, and guide BI decision-making with repeatable, governance-friendly prompts.

Whether you are standing up a new BI program or optimizing an existing one, this prompt library helps you codify best practices and standardize how you interact with your BI data and tools.

Direct Answer

The best ChatGPT prompts for Business Intelligence are those that clearly specify role, task, context, constraints, and expected outputs, enabling repeatable results across datasets and teams. This page provides 100 ready-to-use prompts you can copy, adapt, and run immediately to accelerate BI work.

How to Use These ChatGPT Prompts

• Replace placeholders in brackets [like this] with your real industry, dataset, or audience before running the prompt.
• Attach explicit constraints (format, cadence, thresholds) to steer the output and avoid ambiguity.
• Request a specific output format (bulleted list, JSON, table, or narrative) to make consumption easy for downstream tools.
• Verify outputs by cross-checking with known data sources or conducting a quick sanity check on key metrics.

100 Best ChatGPT Prompts for Business Intelligence

1. 1. Define BI KPIs for [industry] You are an experienced BI analyst. Task: Define a comprehensive KPI set for [industry] based on the provided dataset [dataset]. Context: [industry], [dataset], [audience]. Constraints: deliver in [format] with a maximum of [metrics]. Output: Provide a prioritized KPI list with definitions, data sources, and a suggested refresh cadence.
2. 2. Assess BI data sources for [industry] You are a BI data architect. Task: Audit current data sources for [industry]. Context: [dataset], [systems], [data owners], [stakeholders]. Constraints: identify gaps, recommend data source additions, and propose a mapping to analytics needs. Output: A data-source readiness report with risk rating.
3. 3. Identify top 10 BI metrics for [topic] You are a BI consultant. Task: Identify the top 10 metrics that best measure [topic] within [industry]. Context: historical data in [dataset], stakeholders [audience]. Constraints: exclude noisy metrics, include definitions and data lineage. Output: A ranked metrics list with short definitions.
4. 4. Create a dimensional data model blueprint for [data domain] You are a data modeler. Task: Produce a dimensional model blueprint for [data domain] including fact tables, dimensions, hierarchies, and conformed dimensions. Context: [dataset], [analytics use cases]. Constraints: keep star/snowflake balance, document grain. Output: A model diagram description and a JSON schema snippet.
5. 5. Design an executive BI dashboard layout for [audience] You are a BI designer. Task: Design a high-level dashboard layout for executives focusing on [KPI set]. Context: [audience], [decision makers], [preferred tools]. Constraints: include drill-down paths, mobile considerations, and color-contrast accessibility. Output: Layout blueprint with pane descriptions.
6. 6. Build a data quality checklist for BI pipelines You are a QA-focused BI engineer. Task: Create a data quality checklist for the BI pipeline from ingestion to reporting. Context: [data sources], [ETL processes], [data quality rules]. Constraints: include threshold tolerances and automated validation tests. Output: Checklists and test cases.
7. 7. Generate monthly forecasts using time-series for [industry] You are a forecasting expert. Task: Build a monthly forecast model for [industry] using time-series data in [dataset]. Context: historical data from [time range], seasonality, trend components. Constraints: provide error metrics (MAPE, RMSE), and confidence intervals. Output: Forecast model parameters and sample forecast.
8. 8. Create anomaly-detection prompts for BI metrics You are a data quality engineer. Task: Create prompts to detect anomalies in BI metrics like [metric names]. Context: dataset [dataset], threshold rules, alerting channels. Constraints: specify alert thresholds, notification cadence, and remediation steps. Output: Anomaly prompts and alert definitions.
9. 9. Define alerting rules for BI dashboards You are a BI ops engineer. Task: Define alerting rules for dashboards monitoring [KPI]. Context: data sources [sources], user roles [roles]. Constraints: include severity levels, escalation paths, and false-positive reduction. Output: Alert rule definitions and example alerts.
10. 10. Benchmark BI metrics against industry peers You are a competitive BI analyst. Task: Benchmark [set of metrics] against industry peers using data from [dataset]. Context: [industry], [peer group], [timeframe]. Constraints: compute percentile ranks and identify gaps. Output: Benchmark report with recommendations.
11. 11. Define data governance policies for BI datasets You are a data governance lead. Task: Create governance policies for BI datasets including data ownership, access, retention, and quality. Context: [data domains], regulatory requirements, [audience]. Constraints: include roles and approval workflows. Output: Policy document with a one-page executive summary.
12. 12. Create SQL-to-visual mapping prompts for dashboards You are a BI developer. Task: Map common SQL outputs to visuals for dashboards. Context: [datasets], [BI tool], [audience]. Constraints: specify chart types per metric, and edge-case handling. Output: Mapping table and example queries.
13. 13. Build a BI data dictionary for [dataset] You are a metadata librarian. Task: Build a data dictionary for [dataset], including field names, data types, allowed values, and provenance. Context: [source systems], [ETL], [data owners]. Constraints: include data lineage links. Output: Data dictionary in JSON and narrative summary.
14. 14. Propose data lineage visualization plan You are a data lineage specialist. Task: Propose a plan to visualize data lineage from source to BI consumption for [dataset]. Context: [systems], [ETL], [tools]. Constraints: include impact analysis and automation options. Output: Visual plan and artifacts.
15. 15. Craft data storytelling narratives for BI reports You are a BI storyteller. Task: Create a narrative for BI reports that communicates insights for [audience] and ties to business goals. Context: [dataset], [KPIs], [story arc]. Constraints: keep it under [word limit]. Output: A structured story with visuals suggestions and talking points.
16. 16. Outline BI reporting cadence for [audience] You are a BI operations planner. Task: Define the reporting cadence for [audience], including frequency, channels, and artifacts. Context: [stakeholders], [data latency], [SLAs]. Constraints: align with business cycles. Output: Cadence plan with a calendar.
17. 17. Validate BI model accuracy against holdout data You are a data scientist in BI. Task: Validate the accuracy of a BI model or scoring rule against holdout data. Context: [model], [dataset], [validation method]. Constraints: report metrics and confidence intervals. Output: Validation report with recommendations.
18. 18. Propose KPI weighting for a balanced scorecard You are a strategy BI consultant. Task: Propose a KPI weighting scheme for a balanced scorecard for [organization]. Context: [perspectives], [KPIs], [datasets]. Constraints: rational weights, explain trade-offs. Output: Weight table and rationale.
19. 19. Generate customer segmentation prompts for BI You are a customer analytics BI analyst. Task: Generate prompts to segment customers by [dimension] using [dataset]. Context: [industry], [tools], [audience]. Constraints: specify segmentation criteria, sample sizes, and validation tests. Output: Segment definitions and example queries.
20. 20. Create a data sampling and sampling quality plan You are a data quality engineer. Task: Create a sampling plan for BI validation and testing. Context: [data sources], [sample size], [bias risks]. Constraints: document sampling method and quality checks. Output: Sampling plan and acceptance criteria.
21. 21. Build a churn-monitoring dashboard You are a product BI analyst. Task: Build a dashboard monitoring churn with definitions, cohort analysis, and alert thresholds. Context: [product], [cohorts], [timeframe]. Constraints: provide pre-built visuals and drill-downs. Output: Dashboard specs and sample visuals.
22. 22. Design a revenue attribution dashboard You are a BI attribution specialist. Task: Design a dashboard that attributes revenue across channels, campaigns, and touchpoints. Context: [marketing data], [revenue definitions]. Constraints: show last-touch and multi-touch options. Output: Dashboard layout and data-flow mapping.
23. 23. Identify lead-lag indicators for sales BI You are a sales BI consultant. Task: Identify lead-lag indicators that predict sales outcomes. Context: [sales data], [cycle length], [lead time]. Constraints: quantify lead times and lag effects. Output: Indicator list with hypotheses and validation method.
24. 24. Produce an operations risk dashboard You are an operations BI analyst. Task: Create a dashboard to monitor operational risk with metrics like [kpi list]. Context: [process], [SLAs], [data sources]. Constraints: include alerting and remediation steps. Output: Dashboard spec and example visuals.
25. 25. Create scenario planning prompts for financial BI You are a financial BI strategist. Task: Generate scenarios (e.g., revenue shock, cost changes) and prompts to analyze impact in BI. Context: [financial model], [assumptions], [time horizon]. Constraints: provide outputs for each scenario and sensitivity analysis. Output: Scenario prompts and expected outputs.
26. 26. Build a marketing funnel cohort analysis prompt You are a marketing BI analyst. Task: Create a cohort analysis for the marketing funnel, focusing on conversion rates over cohorts. Context: [channels], [dataset], [labels]. Constraints: provide visuals, identify deterioration drivers. Output: Cohort analysis prompts and example queries.
27. 27. Build a product profitability model for BI You are a product BI manager. Task: Build a profitability model by product lines and channels. Context: [costs], [revenue], [SKU], [timeframe]. Constraints: separate fixed/variable costs and provide ROI. Output: Model prompts and a sample calculation.
28. 28. Create a data quality metrics report template You are a BI QA lead. Task: Create a template for a data quality metrics report including data completeness, accuracy, consistency, and timeliness. Context: [datasets], [definitions], [thresholds]. Constraints: include automated validation prompts. Output: Report template and example filled report.
29. 29. Generate resource-allocation dashboard for BI You are a BI operations planner. Task: Build a dashboard to monitor resource allocation across BI projects. Context: [team], [sprints], [budgets]. Constraints: show capacity vs demand, risk rating. Output: Dashboard spec and example visuals.
30. 30. Create an executive summary BI report outline You are a BI writer. Task: Produce an executive summary outline for a BI report targeting leaders. Context: [KPIs], [insights], [business impact]. Constraints: keep to two pages max. Output: Outline with sections and talking points.
31. 31. Propose BI data governance roles for the team You are a governance advisor. Task: Define roles and responsibilities for a BI team including data steward, data owner, and analytics lead. Context: [organization size], [data domains]. Constraints: map to RACI. Output: Role descriptions and RACI matrix.
32. 32. Build a cost-to-serve dashboard for profitability You are a profitability BI analyst. Task: Create a dashboard showing cost-to-serve by product, region, and channel. Context: [costs], [pricing], [orders]. Constraints: include margin analysis and visualization guidelines. Output: Dashboard spec and example queries.
33. 33. Analyze inventory turnover with BI dashboards You are a supply chain BI analyst. Task: Analyze inventory turnover using BI dashboards and identify optimization opportunities. Context: [SKU], [warehouse], [timeframe]. Constraints: provide KPI definitions, reorder points, and safety stock suggestions. Output: Dashboard plan and recommended actions.
34. 34. Create a data cleaning plan for sparse/dirty data You are a data quality engineer. Task: Develop a data cleaning plan for sparse or dirty data in [dataset]. Context: [source], [quality issues], [tools]. Constraints: specify steps, retries, and verification checks. Output: Cleaning plan with example scripts.
35. 35. Develop a self-serve BI prompt for non-technical users You are a BI accessibility advocate. Task: Create a self-serve prompt set enabling non-technical users to ask BI questions. Context: [datasets], [tools], [user personas]. Constraints: include guardrails and recommended templates. Output: Self-serve prompt kit and usage guide.
36. 36. Create a BI visualization style guide for dashboards You are a visualization designer. Task: Write a style guide for BI dashboards covering colors, typography, and chart choices. Context: [brand], [audience], [tools]. Constraints: ensure accessibility and consistency. Output: Style guide document and examples.
37. 37. Build a time-series forecast for demand planning You are a demand planning BI analyst. Task: Build a time-series forecast for demand planning using [dataset]. Context: [seasonality], [trend], [forecast horizon]. Constraints: provide confidence intervals and validation. Output: Forecast model and visuals.
38. 38. Create a monitoring dashboard for SLA metrics You are an operations BI manager. Task: Design a dashboard to monitor Service Level Agreements (SLAs) with real-time or near-real-time data. Context: [systems], [targets], [alerts]. Constraints: define thresholds and escalation paths. Output: Dashboard specs.
39. 39. Build a cross-functional BI dashboard for leadership You are an analytics lead. Task: Create a cross-functional BI dashboard that aggregates KPIs from multiple domains (sales, marketing, ops). Context: [stakeholders], [datasets]. Constraints: ensure consistent metrics and definitions. Output: Dashboard blueprint and data-mipeline notes.
40. 40. Create a data model review checklist for BI You are a BI architect. Task: Produce a checklist to review data models used in BI, including keys, relationships, and performance. Context: [models], [queries], [ETL]. Constraints: include validation steps. Output: Review checklist.
41. 41. Draft BI data security controls prompt You are a security-conscious BI engineer. Task: Draft data security controls for BI artifacts including dashboards and datasets. Context: [compliance], [roles], [data sensitivity]. Constraints: specify access controls and audit requirements. Output: Security controls doc.
42. 42. Design customer lifetime value model in BI You are a customer analytics BI analyst. Task: Design a customer lifetime value model and prompts to compute LTV in BI environment. Context: [revenue streams], [costs], [churn]. Constraints: include discounting assumptions. Output: LTV model description and sample queries.
43. 43. Create revenue vs cost breakdown dashboard You are a finance BI specialist. Task: Build a dashboard showing revenue and cost breakdown by product, region, and channel. Context: [P&L], [cost types], [periods]. Constraints: provide drill-downs and scenario prompts. Output: Dashboard spec.
44. 44. Build a marketing analytics BI prompt You are a marketing BI analyst. Task: Create prompts to analyze marketing campaigns, attribution, and ROI. Context: [channels], [campaign data], [audience]. Constraints: include attribution models and confidence checks. Output: Set of prompts and example queries.
45. 45. Propose a data retention policy for BI data You are a data governance lead. Task: Propose a data retention policy for BI data to balance cost and compliance. Context: [regulations], [data types], [storage]. Constraints: include purge workflows and archives. Output: Retention policy with schedule.
46. 46. Create operations metrics dashboard for efficiency You are an industrial BI analyst. Task: Build a dashboard tracking operations efficiency metrics such as cycle time, throughput, and utilization. Context: [plants], [shifts], [data sources]. Constraints: include anomaly signals. Output: Dashboard spec and data map.
47. 47. Develop KPI scoring rubric for BI projects You are a BI program manager. Task: Develop a rubric to score BI project KPIs like impact, feasibility, and time-to-value. Context: [portfolio], [stakeholders]. Constraints: include scoring ranges and examples. Output: Rubric and scoring worksheet.
48. 48. Build a supply chain health dashboard You are a supply chain BI analyst. Task: Create a dashboard to monitor supply chain health with metrics like lead time, fill rate, and on-time delivery. Context: [suppliers], [contracts], [timeframe]. Constraints: include supplier risk. Output: Dashboard specs.
49. 49. Create project profitability BI prompt You are a management BI analyst. Task: Develop prompts to analyze project profitability by phase, team, and risk. Context: [projects], [costs], [revenue]. Constraints: provide ROI and payback period. Output: Prompts and example queries.
50. 50. Design HR analytics dashboard prompts You are an HR analytics BI expert. Task: Design prompts to analyze headcount, attrition, recruiting, and diversity metrics. Context: [organization], [timeframe], [privacy constraints]. Constraints: ensure data governance compliance. Output: Prompts and dashboard layout suggestions.
51. 51. Create product analytics BI prompt You are a product analytics BI analyst. Task: Create prompts to analyze product usage, retention, and feature adoption. Context: [product], [cohorts], [event data]. Constraints: include funnel analysis and cohort comparison. Output: Prompts and example queries.
52. 52. Build data imputation plan for missing values You are a data science BI engineer. Task: Outline a plan to impute missing values in [dataset] with acceptable methods. Context: [missingness pattern], [data types], [validation]. Constraints: compare methods and report impact. Output: Imputation plan.
53. 53. Define governance-ready dataset schema for BI You are a data governance architect. Task: Create a governance-ready schema for BI datasets including field-level access and lineage. Context: [domains], [data owners]. Constraints: map to policy controls. Output: Schema spec and governance notes.
54. 54. Create monthly leadership scorecard You are a BI writer. Task: Craft a monthly leadership scorecard covering top KPIs, narrative, and action items. Context: [stakeholders], [timeline]. Constraints: two-page limit. Output: Scorecard ready for distribution.
55. 55. Build cash flow visibility BI prompt You are a finance BI analyst. Task: Build prompts to visualize cash flow visibility across time and scenarios. Context: [accounts], [periods], [FX]. Constraints: include sensitivity analysis. Output: Prompts and sample outputs.
56. 56. Create safety metrics BI prompt for manufacturing You are a manufacturing BI specialist. Task: Create prompts to track safety metrics like incidents, near-misses, and compliance. Context: [plant], [shifts], [regulations]. Constraints: include trend analysis and root-cause prompts. Output: Prompts and visuals.
57. 57. Develop data drift monitoring prompt You are a data quality engineer. Task: Develop prompts to monitor data drift in BI datasets over time. Context: [training data], [production data], [thresholds]. Constraints: define alerting and remediation steps. Output: Drift monitoring prompts and example alerts.
58. 58. Create customer journey analytics BI prompt You are a customer analytics BI analyst. Task: Create prompts to analyze the customer journey across touchpoints and channels. Context: [events], [segments], [conversion events]. Constraints: include journey mapping visuals. Output: Prompts and sample queries.
59. 59. Build forecasting model comparison prompt You are a BI forecasting lead. Task: Compare multiple forecasting models (ARIMA, Prophet, etc.) on [dataset]. Context: [time series], [error metrics], [horizon]. Constraints: provide best model rationale. Output: Comparison prompts and results.
60. 60. Design drill-down paths for dashboards You are a UX BI designer. Task: Design intuitive drill-down paths for dashboards to surface details from high-level metrics. Context: [metrics], [datasets], [audience]. Constraints: ensure logical navigation and latency considerations. Output: Drill-down path designs.
61. 61. Configure RBAC for BI reports You are a BI security engineer. Task: Configure role-based access control for BI reports and datasets. Context: [roles], [data sensitivity], [tools]. Constraints: include least-privilege principles and audit logs. Output: RBAC configuration guide.
62. 62. Create BI prompt to compare actuals vs plan You are a financial BI analyst. Task: Create prompts to compare actual results against plan in [timeframe] and highlight variances. Context: [budget], [accounts], [department]. Constraints: include variance thresholds. Output: Prompts and example queries.
63. 63. Generate a data dictionary from dataset schema You are a metadata specialist. Task: Generate a data dictionary from the given dataset schema, fill in definitions and data types. Context: [dataset], [data owners]. Constraints: include data lineage. Output: Dictionary in JSON and Markdown.
64. 64. Create KPI normalization and scaling prompt You are a BI data engineer. Task: Normalize and scale KPIs across different units for comparability. Context: [KPI set], [scales], [datasets]. Constraints: propose normalization methods and preserve interpretability. Output: Normalization plan and sample calculations.
65. 65. Prioritize BI backlog with a governance prompt You are a BI program manager. Task: Prioritize BI backlog using a governance framework considering impact, risk, and effort. Context: [portfolio], [stakeholders]. Constraints: include prioritization rubric. Output: Backlog ranking and rationale.
66. 66. Build revenue recognition BI check You are a finance BI analyst. Task: Create prompts to verify revenue recognition compliance and timing in BI data. Context: [GAAP/IFRS], [revenue streams], [due dates]. Constraints: include tests and reconciliation steps. Output: Recon prompts and validation plan.
67. 67. Create cost-optimization dashboard for BI You are a cost-optimization BI analyst. Task: Build prompts to identify cost-saving opportunities across departments. Context: [cost centers], [spend], [benefit]. Constraints: include quick-win actions and ROI estimates. Output: Prompts and dashboard concepts.
68. 68. Build marketing attribution model in BI You are a marketing BI analyst. Task: Create prompts to implement marketing attribution models (e.g., last-click, multi-touch) and compare results. Context: [campaign data], [channels], [conversion events]. Constraints: show attribution sensitivity and confidence. Output: Prompts and sample dashboards.
69. 69. Create data archiving and retention plan You are a data governance lead. Task: Propose an archiving and retention plan for BI data to balance performance and compliance. Context: [datasets], [regulatory requirements], [storage costs]. Constraints: include archiving timelines and retrieval procedures. Output: Archiving plan.
70. 70. Design multi-source ETL prompt for BI You are a data integration engineer. Task: Design an ETL prompt to consolidate data from multiple sources into a BI warehouse. Context: [sources], [transformation rules], [quality checks]. Constraints: specify error handling and idempotency. Output: ETL prompt, data mapping, and test cases.
71. 71. Create dashboard to track customer retention You are a customer analytics BI analyst. Task: Build prompts to track customer retention metrics across cohorts and time. Context: [product], [events], [cohorts]. Constraints: include retention curves and triggers. Output: Prompts and example queries.
72. 72. Build cash flow and working capital BI prompt You are a finance BI analyst. Task: Create prompts to visualize cash flow and working capital components. Context: [accounts], [periods], [seasonality]. Constraints: include scenario prompts. Output: Prompts and example dashboards.
73. 73. Propose executive OKR dashboard You are a BI strategist. Task: Propose an OKR-oriented executive dashboard linking objectives to metrics. Context: [OKRs], [stakeholders], [data sources]. Constraints: align with quarterly cycles. Output: Dashboard design and OKR mapping.
74. 74. Design data-quality anomaly prompt You are a data quality engineer. Task: Create prompts to detect and summarize data quality anomalies in BI datasets. Context: [rules], [data types], [alerts]. Constraints: provide remediation steps. Output: Anomaly prompts and remediation plan.
75. 75. Create data lineage mapping prompt You are a data lineage specialist. Task: Produce prompts to map data lineage from sources to BI reports. Context: [ETL], [data owners], [tools]. Constraints: include risk indicators. Output: Lineage prompts and diagrams.
76. 76. Build procurement analytics dashboard You are a procurement BI analyst. Task: Create a dashboard analyzing supplier performance, cost savings, and spend by category. Context: [suppliers], [contracts], [timeframe]. Constraints: include supplier risk. Output: Dashboard specs.
77. 77. Create vendor performance BI prompt You are a vendor management BI analyst. Task: Generate prompts to evaluate vendor performance using delivery, quality, and cost. Context: [vendors], [SLAs], [data]. Constraints: include metrics definitions. Output: Prompts and sample queries.
78. 78. Develop product adoption analytics prompt You are a product analytics BI expert. Task: Create prompts to measure product adoption, trial-to-paid conversion, and feature usage. Context: [product], [users], [events]. Constraints: provide funnel visuals. Output: Prompts and example queries.
79. 79. Create regulatory compliance BI prompt You are a compliance BI analyst. Task: Produce prompts to monitor regulatory compliance metrics in BI data. Context: [regulators], [data controls], [audits]. Constraints: include alert thresholds. Output: Compliance prompts and sample reports.
80. 80. Build churn prediction BI model prompt You are a churn analytics BI specialist. Task: Create prompts to build a churn prediction model using [dataset]. Context: [customer segments], [timeframes], [model type]. Constraints: provide evaluation metrics. Output: Prediction prompts and example results.
81. 81. Create pricing analytics BI prompt You are a pricing analytics BI analyst. Task: Develop prompts to analyze price elasticity, discount impact, and margin. Context: [products], [promotions], [sales data]. Constraints: include scenario analysis. Output: Prompts and example queries.
82. 82. Design cross-border data analysis prompt You are a global BI analyst. Task: Create prompts to analyze data across regions with currency and regulatory considerations. Context: [regions], [legal], [data localization]. Constraints: include localization notes. Output: Localization prompts and example configurations.
83. 83. Create data sampling strategy for BI You are a data scientist BI engineer. Task: Propose a stratified sampling strategy for BI reporting. Context: [datasets], [sample sizes], [bias risks]. Constraints: justify sampling method. Output: Sampling strategy and validation plan.
84. 84. Build real-time BI dashboard prompt You are a real-time analytics BI engineer. Task: Create prompts to build a near-real-time BI dashboard. Context: [streaming data], [latency targets], [tools]. Constraints: define data freshness and SLAs. Output: Real-time dashboard prompts.
85. 85. Create stakeholder-friendly BI briefing prompt You are a BI comms specialist. Task: Create prompts to generate concise, stakeholder-friendly BI briefings. Context: [audiences], [KPIs], [insights]. Constraints: limit to 5 bullets. Output: Briefing prompts.
86. 86. Design BI dashboard testing plan You are a BI QA lead. Task: Develop a testing plan for dashboards including functional, performance, and usability tests. Context: [dashboards], [test cases], [acceptance criteria]. Constraints: include automation where possible. Output: Test plan and case examples.
87. 87. Create cross-functional KPI dashboard You are a BI integration analyst. Task: Build prompts to create a cross-functional KPI dashboard integrating finance, ops, and marketing metrics. Context: [data sources], [stakeholders]. Constraints: maintain consistent metric definitions. Output: Prompts and data-mapping outline.
88. 88. Develop data enrichment plan for BI You are a data enrichment specialist. Task: Propose enrichment steps to improve BI data quality and insights (external data, appends). Context: [datasets], [sources], [costs]. Constraints: assess value and privacy implications. Output: Enrichment plan and implementation notes.
89. 89. Build capacity planning BI prompt You are a capacity planner BI analyst. Task: Create prompts to plan capacity across teams based on historical demand. Context: [headcount], [workload], [resource constraints]. Constraints: provide scenarios and alerts. Output: Capacity plan prompts.
90. 90. Create scenario-based BI decision prompt You are a decision science BI expert. Task: Create prompts to explore decision options under different scenarios in BI. Context: [goals], [constraints], [uncertainties]. Constraints: show recommended actions per scenario. Output: Decision prompts.
91. 91. Define audit trails for BI prompts You are a compliance BI analyst. Task: Define audit trails and logging requirements for BI prompts and outputs. Context: [regulations], [tools], [security]. Constraints: include retention and access controls. Output: Audit-trail plan.
92. 92. Build error-handling plan for BI ETL You are an ETL engineer. Task: Develop an error-handling plan for BI ETL pipelines including retries, dead-letter queues, and alerting. Context: [sources], [staging], [target]. Constraints: include failure simulation. Output: Error-handling plan.
93. 93. Create BI-ready dataset from SQL warehouse You are a data engineer. Task: Create prompts to curate a BI-ready dataset from a SQL data warehouse. Context: [schema], [permissions], [performance]. Constraints: include pre-aggregation and indexing notes. Output: Dataset blueprint and example queries.
94. 94. Develop dashboard performance optimization prompt You are a performance-focused BI engineer. Task: Create prompts to optimize dashboard load times and rendering. Context: [datasets], [visuals], [tools]. Constraints: provide quantifiable targets and steps. Output: Optimization prompts and metrics.
95. 95. Create user feedback collection prompt for BI You are a product analytics BI analyst. Task: Design prompts to collect user feedback on BI reports and dashboards. Context: [users], [channels], [types of feedback]. Constraints: categorize feedback and propose actions. Output: Feedback prompts and analysis plan.
96. 96. Build data normalization prompt for BI You are a data normalization specialist. Task: Create prompts to normalize disparate datasets into a common schema for BI consumption. Context: [datasets], [data types], [mapping rules]. Constraints: preserve data fidelity. Output: Normalization prompts and mapping examples.
97. 97. Set up a BI sandbox environment prompt You are a BI developer. Task: Outline steps to set up a sandbox environment for BI experimentation. Context: [data, tools, access], [security]. Constraints: ensure data isolation and backup. Output: Sandbox setup prompts.
98. 98. Create BI dashboard localization prompt You are a localization BI analyst. Task: Create prompts to localize BI dashboards for different regions (language, currency, date formats). Context: [regions], [datasets], [audience]. Constraints: maintain metric integrity. Output: Localization prompts and example configurations.
99. 99. Define refresh schedule for BI KPIs You are a BI operations manager. Task: Define a refresh schedule for BI KPIs including latency targets, ETL windows, and stakeholder expectations. Context: [data sources], [SLAs], [tools]. Constraints: minimize stale data. Output: Refresh schedule and runbook.
100. 100. Compile a comprehensive BI prompt library summary for stakeholders You are a BI communications lead. Task: Compile a concise summary of all 100 prompts with intended use cases, audience, and expected outputs. Context: [stakeholders], [bi goals]. Constraints: keep to one page. Output: Summary document.

Best Practices

• Reuse the same structure across prompts to keep outputs consistent (role, task, context, constraints, output).
• Document data sources and data lineage for every prompt that touches datasets.
• Leverage placeholders to keep prompts adaptable across projects and industries.
• Test prompts on a subset of data before scaling to full datasets.
• Maintain governance by including data security, privacy, and access prompts where relevant.

Common Mistakes to Avoid

• Using vague roles or ambiguous tasks that lead to inconsistent outputs.
• Omitting data sources or audience details, causing outputs to be non-actionable.
• Ignoring privacy, security, or compliance requirements in BI prompts.
• Overloading prompts with too many objectives in a single item.
• Neglecting to request a defined output format or validation steps.

Related resources

Use these related resources to move from prompt examples into real AI workflows, implementation demos, and topic-specific business use cases.

• ChatGPT
• AI Prompts Library
• ChatGPT Prompts
• AI Lab demos
• Python data analysis ChatGPT prompts
• Why AI-generated dashboards need layout rules
• Why business dashboards need domain-specific skill files
• Generative insights beyond static dashboards
• Organizational knowledge brain AI Lab
• QuickBooks reports and management dashboards

FAQ

What is this page for?

This page is a practical prompt library of 100 ChatGPT prompts tailored for Business Intelligence work.

Can I customize the prompts for my data?

Yes. Replace placeholders like [industry], [dataset], and [audience] with your real values and adjust constraints to fit your data and governance policies.

Are these prompts suitable for real-time BI?

Several prompts address real-time or near-real-time BI needs; adapt the prompts to streaming data and SLAs as required.

Can I copy and reuse these prompts?

Yes. The prompts are designed to be copied, adapted, and run across BI projects and teams.

Do these prompts require specific BI tools?

The prompts are tool-agnostic in intent. You can adapt them for your BI stack (SQL, BI dashboards, data catalogs, etc.).