Raw Data Is Sacred
The quality of every later step depends on this one. Copilot works best with one row per observation, clear headers, consistent dates, numbers stored as numbers, no merged cells in the data, no blank rows breaking the range.
Lesson 2
Find problems, fix on a copy.
Two passes: Copilot finds problems on the raw sheet without modifying it, then writes fixes to a new Clean Data sheet with a list of every change.
Core principles
- Never let Copilot edit your source sheet — all cleaning happens on copies.
- Review Clean Data against Raw Data before you trust it — auto-cleaning can drop rows or reformat values silently.
- A single text entry in a number column breaks every calculation downstream.
- Setup checkpoint: you need Raw Data (untouched), Clean Data, and soon Copilot Brief — do not analyze until all three exist.
- Weak or missing data gets flagged, not buried — make Copilot state how much data backs each finding.
Check yourself
Where should Copilot write cleaned data?
Raw data is your audit trail. Clean on a copy so you can always retrace what changed — and catch when Copilot silently dropped a row or misread a column.
Do this in Copilot
Run quality check and clean prompts on your workbook. Review the change log before moving on.
Paste this into Copilot Chat and work through it before moving on.
Quality check (report only)
Check this data for quality issues: missing values, duplicate columns, inconsistent date formats, text inside numeric columns, merged cells, and blank rows. List what you find and where. Do not modify the source sheet — just report.
- Constraints
- Then run:
- Now fix the issues you found and write the cleaned version to a new sheet called Clean Data. Leave the raw data sheet untouched. List every change you made so I can review it.
Did you run this in Copilot? Mark complete when you have tried it.
RecordedNext lesson: Build the Copilot Brief Sheet →
Navigate: press j for next lesson, k for previous.