Turn an unwieldy spreadsheet into a clear dashboard.
A spreadsheet can hold the answers and still make them hard to see. Turn it into an interactive dashboard that brings the important patterns forward and lets you click into the details.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Investigate the workbook’s numbers, formulas, relationships, and data issues.
- Propose and build an interactive dashboard, then check its figures, controls, and readability against the spreadsheet.
What to have ready
- The spreadsheet as a file or accessible link; the AI can help find a usable export.
- Context about the audience and decisions the dashboard should support, where the workbook cannot explain them.
Where you come in
- Clarify consequential gaps and confirm or change the proposed design before building.
- Try the dashboard and share what feels confusing or missing; take any required opening or hosting step the AI identifies.
What you'll get
A working interactive dashboard with useful detail views and instructions for opening it and refreshing its data, with completed checks and any remaining setup or verification limits identified.
You're done when
You have a working interactive dashboard that makes the spreadsheet easier to understand, lets you explore relevant details, and has been checked against its source numbers, with a clear way to open it and keep its data current.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Turn this spreadsheet into a clear, visually compelling, interactive dashboard. Investigate the workbook, propose a design suited to its information, then build a working artifact or web app. Make it engaging to explore and easier to understand than the spreadsheet. Ask one focused question at a time when you need my input. ### 1. Read the spreadsheet and understand its numbers. If I haven’t supplied it, ask for the file or an accessible link. Try your available tools to open it. If you cannot read it, investigate a usable export and offer to walk me through providing it. Preserve the original workbook while you work. - Inspect the relevant sheets, headers, row types, formulas, units, date ranges, and existing notes or charts. - Determine what the spreadsheet describes, what one row represents, and how its sheets relate. - Trace key displayed numbers to their underlying entries, formulas, or linked sources. - Distinguish recorded observations, manual inputs, calculated values, targets, and forecasts where present. - Identify the key variables, useful comparisons, and relationships that explain the information. Check for issues that would affect the dashboard: missing values, duplicated entries, mixed units or currencies, subtotal rows that could be counted twice, formula errors, or unavailable external links. Resolve what you can from the workbook and accessible supporting sources. Ask me only about gaps that affect interpretation or design. Don’t silently replace missing values with zeros or invent the origins of numbers you cannot trace. Give me a brief account of what the spreadsheet is showing, where its numbers come from, and which variables matter. Establish who the dashboard is for and what they most need to understand, compare, or decide. Use context I’ve already provided and ask about anything essential that remains unclear. ### 2. Propose a dashboard that makes the information inviting to explore. Inspect your capabilities for building an interactive artifact or web app and decide on a workable format. Propose a concise dashboard plan grounded in the actual data and audience. Explain what someone sees first, the main questions each view answers, and what they can click, filter, or compare. Use distinct modules when the spreadsheet contains different aspects that deserve their own treatment. Where it fits the data, propose a clear view of individual units or items—such as projects, locations, products, or accounts—that people can click to reveal key information visually. Give the detail view enough context to understand an item against its history, peers, or target when the workbook supports those comparisons. Have fun with the visual presentation. Consider charts, timelines, maps, graphs, waveforms, or other displays when they make a real feature of the data easier to grasp. Choose the visual form for the question it answers: a trend over time, a comparison between items, a composition, or a relationship between variables. Use exact numbers where they are the clearest answer. Explain your proposed visual choices in ordinary language. Include only interactions that serve the information. Filters might narrow a period or category; clicking an item might reveal its trajectory or composition. If changing an input would use actual workbook formulas, explain which calculations the dashboard will reproduce. Distinguish that from filtering existing results. State whether this will use a snapshot of the spreadsheet or an available connection for updates, and what that means for keeping it current. Present the plan and wait for my confirmation or changes. Resolve those, then build it. ### 3. Build the working dashboard. Use the actual spreadsheet data and preserve the meaning of its calculations. Create the agreed overview, modules, item views, and interactions in a working artifact or web app. Make the main point easy to see when it opens. Use readable labels, clear units, purposeful color, and enough space for the information to breathe. Make clicks and filters easy to discover, and provide a clear way back from detail views. - Show which period and source the dashboard represents. - Let someone see the exact values behind a visual and identify the relevant source sheet or range where useful. - Handle missing data and empty filter results clearly. - If a connection cannot update the data automatically, implement a practical way to replace or reload the spreadsheet where feasible and explain the actual refresh behavior. If a capability is unavailable, investigate a workable alternative that preserves the interactive goal, such as a downloadable HTML dashboard. If completing the artifact requires an action or different environment from me, produce what you can and identify the exact remaining step. A written dashboard plan alone is not the completed result. ### 4. Check the numbers and the experience, then deliver it. - Open and operate the dashboard yourself wherever your tools allow. - Reconcile its key totals and calculations with the workbook, including representative item details and filtered views. - Test the actual controls, navigation, and any editable inputs. - Check that aggregation, percentages, units, and time ranges retain their original meaning and that charts do not suggest comparisons the data cannot support. - Fix discrepancies before delivery. Inspect the rendered result for readability and whether its first view makes the important information clear. If separate agents are available and useful, have one independently check selected figures against the source spreadsheet and another review the displayed dashboard for clarity and working interactions. Give them the relevant artifact and source data, reconcile their findings, and check your fixes. Otherwise perform those checks yourself. Distinguish checks actually performed from anything you could not verify. Give me the working dashboard as an accessible artifact, file, or link, with brief instructions for opening and exploring it and for refreshing its data. If hosting requires a choice or action from me, prepare and check the dashboard first, then explain the specific remaining step. Invite me to try it and tell you what feels confusing or missing; use that feedback to improve it. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Turn an unwieldy spreadsheet into a clear dashboard.
What the AI will do
- Investigate the workbook’s numbers, formulas, relationships, and data issues.
- Propose and build an interactive dashboard, then check its figures, controls, and readability against the spreadsheet.
What you can provide
- The spreadsheet as a file or accessible link; the AI can help find a usable export.
- Context about the audience and decisions the dashboard should support, where the workbook cannot explain them.
Where you'll take part
- Clarify consequential gaps and confirm or change the proposed design before building.
- Try the dashboard and share what feels confusing or missing; take any required opening or hosting step the AI identifies.
What you'll get
A working interactive dashboard with useful detail views and instructions for opening it and refreshing its data, with completed checks and any remaining setup or verification limits identified.
Activity context
A spreadsheet can hold the answers and still make them hard to see. Turn it into an interactive dashboard that brings the important patterns forward and lets you click into the details.
For the user
Give your AI the spreadsheet as a file or an accessible link, then paste the prompt below. It will investigate what the workbook shows, where its numbers come from, and which variables matter.
You’ll clarify anything the workbook cannot explain and review a proposed dashboard. The AI will then build and check an interactive artifact or web app, with visual displays and ways to explore individual items.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Turn this spreadsheet into a clear, visually compelling, interactive dashboard. Investigate the workbook, propose a design suited to its information, then build a working artifact or web app. Make it engaging to explore and easier to understand than the spreadsheet. Ask one focused question at a time when you need my input.
1. Read the spreadsheet and understand its numbers.
If I haven’t supplied it, ask for the file or an accessible link. Try your available tools to open it. If you cannot read it, investigate a usable export and offer to walk me through providing it. Preserve the original workbook while you work.
- Inspect the relevant sheets, headers, row types, formulas, units, date ranges, and existing notes or charts.
- Determine what the spreadsheet describes, what one row represents, and how its sheets relate.
- Trace key displayed numbers to their underlying entries, formulas, or linked sources.
- Distinguish recorded observations, manual inputs, calculated values, targets, and forecasts where present.
- Identify the key variables, useful comparisons, and relationships that explain the information.
Check for issues that would affect the dashboard: missing values, duplicated entries, mixed units or currencies, subtotal rows that could be counted twice, formula errors, or unavailable external links. Resolve what you can from the workbook and accessible supporting sources. Ask me only about gaps that affect interpretation or design. Don’t silently replace missing values with zeros or invent the origins of numbers you cannot trace.
Give me a brief account of what the spreadsheet is showing, where its numbers come from, and which variables matter. Establish who the dashboard is for and what they most need to understand, compare, or decide. Use context I’ve already provided and ask about anything essential that remains unclear.
2. Propose a dashboard that makes the information inviting to explore.
Inspect your capabilities for building an interactive artifact or web app and decide on a workable format. Propose a concise dashboard plan grounded in the actual data and audience. Explain what someone sees first, the main questions each view answers, and what they can click, filter, or compare.
Use distinct modules when the spreadsheet contains different aspects that deserve their own treatment. Where it fits the data, propose a clear view of individual units or items—such as projects, locations, products, or accounts—that people can click to reveal key information visually. Give the detail view enough context to understand an item against its history, peers, or target when the workbook supports those comparisons.
Have fun with the visual presentation. Consider charts, timelines, maps, graphs, waveforms, or other displays when they make a real feature of the data easier to grasp. Choose the visual form for the question it answers: a trend over time, a comparison between items, a composition, or a relationship between variables. Use exact numbers where they are the clearest answer. Explain your proposed visual choices in ordinary language.
Include only interactions that serve the information. Filters might narrow a period or category; clicking an item might reveal its trajectory or composition. If changing an input would use actual workbook formulas, explain which calculations the dashboard will reproduce. Distinguish that from filtering existing results. State whether this will use a snapshot of the spreadsheet or an available connection for updates, and what that means for keeping it current.
Present the plan and wait for my confirmation or changes. Resolve those, then build it.
3. Build the working dashboard.
Use the actual spreadsheet data and preserve the meaning of its calculations. Create the agreed overview, modules, item views, and interactions in a working artifact or web app. Make the main point easy to see when it opens. Use readable labels, clear units, purposeful color, and enough space for the information to breathe. Make clicks and filters easy to discover, and provide a clear way back from detail views.
- Show which period and source the dashboard represents.
- Let someone see the exact values behind a visual and identify the relevant source sheet or range where useful.
- Handle missing data and empty filter results clearly.
- If a connection cannot update the data automatically, implement a practical way to replace or reload the spreadsheet where feasible and explain the actual refresh behavior.
If a capability is unavailable, investigate a workable alternative that preserves the interactive goal, such as a downloadable HTML dashboard. If completing the artifact requires an action or different environment from me, produce what you can and identify the exact remaining step. A written dashboard plan alone is not the completed result.
4. Check the numbers and the experience, then deliver it.
- Open and operate the dashboard yourself wherever your tools allow.
- Reconcile its key totals and calculations with the workbook, including representative item details and filtered views.
- Test the actual controls, navigation, and any editable inputs.
- Check that aggregation, percentages, units, and time ranges retain their original meaning and that charts do not suggest comparisons the data cannot support.
- Fix discrepancies before delivery.
Inspect the rendered result for readability and whether its first view makes the important information clear. If separate agents are available and useful, have one independently check selected figures against the source spreadsheet and another review the displayed dashboard for clarity and working interactions. Give them the relevant artifact and source data, reconcile their findings, and check your fixes. Otherwise perform those checks yourself. Distinguish checks actually performed from anything you could not verify.
Give me the working dashboard as an accessible artifact, file, or link, with brief instructions for opening and exploring it and for refreshing its data. If hosting requires a choice or action from me, prepare and check the dashboard first, then explain the specific remaining step. Invite me to try it and tell you what feels confusing or missing; use that feedback to improve it.
Done when
You have a working interactive dashboard that makes the spreadsheet easier to understand, lets you explore relevant details, and has been checked against its source numbers, with a clear way to open it and keep its data current.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.