Real Agent Cases

Build a cohort retention table in Excel with Copilot Agent Mode

Posted
by Josef Waples (DataCamp)
Last checked
Method:
How we verify

Evidence: Article or interviewA newsletter, journalist or interview account of what happened.

Outcome

Given a long table of customers by period, Excel's Copilot Agent Mode built a color-coded cohort retention table that DataCamp's reviewer found accurate to the data; it also added a useless chart he had to delete.

Agent

Microsoft Copilot Agent Mode (Excel)

Prompt Recreated prompt

The source didn't share its exact prompt, so we wrote this from what it describes.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Turn my customer activity table into a cohort retention table.

Quick-check questions: Which columns are customer ID, signup date and activity date, and monthly or weekly cohorts?

What I need from you:
- The table in Excel
- Cohort period (month or week)
- Which sheet holds the data

Rules:
- Group users by signup period, count active users in each later period and divide by period 0.
- Put the result on a new sheet; don't overwrite my data.
- Show the formulas so I can check them.
- Skip charts unless I ask.
- If a customer appears in more than one cohort, use their first signup date.

Output: A triangular retention table with percentages and a short note on the method.

If my answers leave a gap, make a sensible choice, say what you assumed, and keep going.

You'll know it worked when: each row starts at 100% and the counts match the raw data.

Source

https://www.datacamp.com/blog/agent-mode-in-excel

Related cases

  • Build a credit risk scorecard in Excel with Claude in ExcelImproved promptEvidence: Shown on videoPartial

    Given a credit risk dataset and a brief for an Excel-native scorecard, Claude in Excel built a polished 28-sheet workbook but skipped the variable clustering, ran the model in JavaScript and reported 0.706 AUC on training data with no split; ChatGPT followed the method and got 0.627 on test data.

    Claude (Excel) · Data · Source date:

  • Fill missing industry details in a customer sheet with Zapier AgentsRecreated promptEvidence: Company case study

    UK energy company egg set up a Zapier Agent that finds customers with missing industry details in a HubSpot-fed Google Sheet, searches for the information and updates the sheet; Zapier says it now takes about five minutes and egg no longer pays a contractor for it.

    Poster says:About 5 minutes; contractor no longer needed

    Zapier Agents · Data · Source date:

  • Merge provider price CSVs into one comparison table with Claude CodeRecreated promptEvidence: Described by poster

    Claude Code read several local CSVs of model prices from different providers and produced one organized comparison table grouped by provider.

    Claude Code · Data · Source date: