The COPILOT function in Excel put AI prompts inside worksheet formulas, but it only ever ran as a preview. Microsoft retired it on 14 September 2026, so you now do the same summarising and classifying in the Copilot pane. The review habits below still apply to that output.
The Complete Excel Course with AI Integration
From formulas and pivot tables to Power Query, DAX, VBA and AI with Copilot, ChatGPT and Claude — hands-on from the first lesson.
By Sagnik Bhattacharya and Virginia Thorn, Primetime Emmy Award winner
Buy nowPutting AI prompts inside formulas was powerful, but it also changed the review burden. A side-panel answer is easy to question. A cell result can disappear into a model very quickly if you do not build the right checking habits.
Note: As of 25 September 2026, the COPILOT worksheet function is no longer available in Excel. It only ever shipped as a preview to the Frontier and Microsoft 365 Insider programmes, and since 14 September 2026 any cell that still calls it returns #NAME? when it recalculates; results that were already calculated stay in the workbook as cached values. Microsoft’s replacement is the Copilot pane in Excel, where you describe the same summarising, classifying, or web lookup task in your own words, so the review habits below now apply to whatever you bring back from there.
What was the COPILOT function in Excel for?
The COPILOT function was useful for bounded AI assistance inside worksheet logic, especially when you wanted a result in a cell rather than a side conversation. It was never a substitute for deterministic formulas in any workflow that must be fully auditable or reproducible, and since its retirement the same test applies to AI output you bring in from the Copilot pane.
- You need AI assistance directly in worksheet output.
- The task is advisory, classificatory, or interpretive rather than purely deterministic.
- You can review and document where the AI-derived values are being used.
Where did the COPILOT function help most?
The COPILOT function helped most with interpretive tasks where traditional formulas are awkward, such as classifying free-text comments, drafting a short summary, or converting an informal request into a structured answer.
Why does reviewing AI cell output matter more than syntax?
Reviewing matters more than syntax because an AI-produced value can feed a metric, a filter, or a business rule while nobody knows where it came from or how trustworthy it is.
Label the column clearly, sample the output, and use a manual review pass before the results affect dashboards or decisions.
- Label AI-derived columns clearly.
- Review a sample before filling the function down a whole table.
- Keep the prompt objective and specific enough to reduce drift.
The Complete Excel Course with AI Integration
From formulas and pivot tables to Power Query, DAX, VBA and AI with Copilot, ChatGPT and Claude — hands-on from the first lesson.
By Sagnik Bhattacharya and Virginia Thorn, Primetime Emmy Award winner
Buy nowWhat are the risks of AI-generated cell values?
The main risk of the COPILOT function was false confidence: a neat result in a cell feels more official than a paragraph in chat. Teams can accidentally treat it like a normal formula even when it behaves differently.
If you want to build these skills with an instructor, try The Complete Excel Course with AI Integration on Coding Liquids.
Worked example: classifying support comments
A support team has 1,200 comments from a customer survey. They want a quick first-pass label for each row: billing, delivery, product quality, or account issue.
The COPILOT function could create that first label column; with the function retired, the team now asks the Copilot pane to do it, but should still sample the outputs and avoid treating the result as final without review.
If you want help applying this to your own workbooks, I offer a one-to-one AI consultation.
Common mistakes
- Using AI-derived cell values in a model without labelling them clearly.
- Replacing deterministic logic with the COPILOT function simply because it feels faster.
- Ignoring availability and rollout caveats in team documentation.
When to use something else
If you need a formula written for you, single-cell formula generation is the better topic. If you need a broader comparison of AI tools for spreadsheet work, go to the 2026 comparison guide.
The Complete Excel Course with AI Integration
From formulas and pivot tables to Power Query, DAX, VBA and AI with Copilot, ChatGPT and Claude — hands-on from the first lesson.
By Sagnik Bhattacharya and Virginia Thorn, Primetime Emmy Award winner
Buy nowFrequently asked questions
What is the COPILOT function for?
It was for bounded AI assistance inside worksheet logic, giving you a result in a cell rather than in a side chat. Microsoft retired it on 14 September 2026, so you now do those tasks in the Copilot pane in Excel. Neither is a replacement for deterministic formulas in anything that must be fully auditable or reproducible.
Where does it genuinely help?
It helped with tasks that are awkward for formulas or need interpretation, such as classifying free-text comments, drafting a short summary, and turning an informal request into a structured answer. Since its retirement you do those tasks in the Copilot pane, and you still sample the output before relying on it, because the result is a first pass rather than a checked figure.
Why does review matter more than syntax?
Because an AI-produced value can feed a metric, a filter, or a business rule, and someone must know where it came from and how trustworthy it is. The syntax is the easy part. Label the column clearly, sample the output, and run a manual review pass before the results affect dashboards or decisions.
What is the real risk?
The real risk is false confidence. A neat value in a cell feels more official than a paragraph in chat, so teams treat it like a normal formula even though it can behave non-deterministically. Label AI-derived columns, review a sample before filling down a table, and keep the prompt specific.
Is the COPILOT function deterministic?
Do not assume so. AI outputs can vary and depend on context, unlike SUM or XLOOKUP. Avoid AI-derived cells wherever the result must recompute identically every time for audit or reconciliation, and use a deterministic formula there. Treat any AI output you bring in from the Copilot pane the same way.
When should I avoid it?
Avoid it in auditable or reproducible workflows such as financial reconciliation or compliance figures. Use deterministic formulas there, and reserve AI help for interpretive, lower-stakes helper cells. The COPILOT function itself is retired, so for those helper cells you now use the Copilot pane and still review what it returns.
Related guides on this site
If you want to keep going without opening dead ends, these are the most useful next reads from this site.
- The Complete Excel Guide 2026: Formulas, AI Copilot, and Modern M365
- Generate Single-Cell Formulas With Copilot in Excel: Fast Wins and Failure Modes
- How to Review AI-Generated Excel Formulas Before You Trust Them
- ChatGPT vs Claude vs Copilot vs Gemini for Excel in 2026
- How to Use Copilot in Excel to Analyse Data
Official references
These official references are useful if you need the product or framework documentation alongside this guide.
