Prompt to build an Excel Power Query transformation
A Power Query prompt for Excel: the source (files in a folder, a table, a database or an API), the transformation steps in order, the M code where needed, parameters, refresh behavior and how to keep query folding.
Open in the builder →Part of the workflow automation prompts collection: Power Automate, Logic Apps, Power Apps, Office Scripts, VBA, PowerShell, Copilot Studio, Zapier, Make and n8n. Writing your own? Read the automation prompt guide.
Ready-to-use prompt
# Role You are an experienced workflow-automation architect who designs reliable, maintainable automations on the platform in use: a precise trigger, exact connector and action names, explicit conditions, error handling, and a test plan. # Context Build an Excel Power Query that combines all monthly CSV files in a folder, cleans the headers, unpivots the month columns, and loads a summary table. # Task Design the automation described in the context above for the stated platform: the trigger, each action in order with exact connector or action names, the conditions and approvals, error handling and retries, and how to test it before it goes live. # How to approach this Work the problem internally, then give only the result. Do not narrate your reasoning unless it is part of the deliverable. - Lay the automation out in order: trigger, each action, the conditions and branches, error handling, then a test plan. Before you finalize, verify that the trigger fires on exactly the intended event and nothing else; every action names the real connector, action, or command for the stated platform; the first failure has a handling path: retry, notify, or stop; the test plan covers the main path and that first failure. # Constraints - Do not invent connector, action, or command names. If unsure one exists, say so and use the closest real alternative. - Follow the requested format exactly. Default to clean markdown. Be concise — no filler, no restating the question. - Deliver the single best answer rather than hedging across several. - When uncertain about a fact, API method, library name, or function signature, say so explicitly. Do not produce a plausible guess. - Do not invent citations, URLs, or package names. If you don't know one, omit it or flag that you don't. - Deliver the result directly — no apologies or meta-commentary about the prompt itself. # Output format Return only the requested output. If multiple distinct variants would clearly help, label them (e.g., "Option A", "Option B"). # Done when - the output fully answers the goal in the Context section with no missing parts
Tuned for your model
Get a version optimized for the AI you actually use:
- ChatGPTConcise instructions, strict format adherence, no preamble.
- ClaudeExplicit step-by-step thinking and clearly delimited output sections.
- GeminiPrecise phrasing with brief reasoning cues where they improve accuracy.
- CopilotOffice-ready output that pastes cleanly into Word, Outlook, and Excel, with tables and numbered steps.
Why this prompt works
Power Query is a sequence of applied steps, so the prompt asks for the transformation in order and produces steps a user can follow or M code they can paste.
Combining files from a folder and unpivoting are where most people get stuck. The prompt asks for the shape of the source and the shape of the result.
Refresh matters for automation. The prompt asks how the query is refreshed and notes that scheduled refresh needs Power Automate or an Office Script.
Questions, answered
- What is Power Query in Excel?
- The Get and Transform tool on the Data tab. It imports data from files, folders, databases and web sources, records each transformation as a step, and refreshes on demand.
- Can Power Query refresh on a schedule?
- Not by itself in desktop Excel. Use an Office Script that refreshes all data connections, run from a Power Automate flow on a schedule, or move the data to Power BI.
- Should I write M code or use the ribbon?
- Use the ribbon for standard steps and M code for anything the ribbon cannot express, such as custom functions. The prompt returns both when useful.