File: revenue_q4_2025_q1_2026.csv
Rows: 18 | Columns: 8
Period: October 2025 – March 2026
Segments: SMB, Mid-Market, Enterprise
Currency: USD

| Month   | Segment     | New MRR | Expansion MRR | Churned MRR | Net New MRR | Active Customers | Avg MRR per Customer |
|---------|-------------|---------|---------------|-------------|-------------|------------------|----------------------|
| 2025-10 | SMB         | 45,000  | 8,000         | 30,000      | 23,000      | 1,240            | 245                  |
| 2025-11 | SMB         | 48,000  | 9,000         | 32,000      | 25,000      | 1,255            | 247                  |
| 2025-12 | SMB         | 50,000  | 7,000         | 38,000      | 19,000      | 1,268            | 246                  |
| 2026-01 | SMB         | 47,000  | 6,000         | 51,000      | 2,000       | 1,264            | 243                  |
| 2026-02 | SMB         | 44,000  | 5,000         | 62,000      | -13,000     | 1,248            | 238                  |
| 2026-03 | SMB         | 42,000  | 4,000         | 71,000      | -25,000     | 1,228            | 232                  |
| 2025-10 | Mid-Market  | 35,000  | 12,000        | 8,000       | 39,000      | 187              | 1,340                |
| 2025-11 | Mid-Market  | 38,000  | 14,000        | 9,000       | 43,000      | 192              | 1,370                |
| 2025-12 | Mid-Market  | 42,000  | 16,000        | 9,000       | 49,000      | 198              | 1,395                |
| 2026-01 | Mid-Market  | 45,000  | 18,000        | 10,000      | 53,000      | 204              | 1,430                |
| 2026-02 | Mid-Market  | 48,000  | 19,000        | 8,000       | 59,000      | 210              | 1,465                |
| 2026-03 | Mid-Market  | 52,000  | 22,000        | 9,000       | 65,000      | 217              | 1,505                |
| 2025-10 | Enterprise  | 80,000  | 25,000        | 15,000      | 90,000      | 42               | 11,500               |
| 2025-11 | Enterprise  | 60,000  | 30,000        | 12,000      | 78,000      | 44               | 11,700               |
| 2025-12 | Enterprise  | 120,000 | 22,000        | 18,000      | 124,000     | 46               | 12,100               |
| 2026-01 | Enterprise  | 95,000  | 45,000        | 14,000      | 126,000     | 48               | 12,400               |
| 2026-02 | Enterprise  | 75,000  | 38,000        | 16,000      | 97,000      | 50               | 12,650               |
| 2026-03 | Enterprise  | 110,000 | 52,000        | 18,000      | 144,000     | 52               | 12,950               |

Summary  
This chapter demonstrates how to design structured prompts that guide a language model to parse CSV data and extract specific findings, anomalies, and concrete recommendations with row- or column-level references.  

General domain of usage  
Business analytics

You can throw a CSV at Claude and get back "revenue is up overall." Useless. Same CSV, different system prompt, and you get a three-line read that names the segment in trouble, the month it started, and what to do about it.

Same data — different discipline.

## Why "Summarize This Spreadsheet" Fails

Asked to summarize, the model defaults to restating. "Revenue grew, churn varied, costs steady" — all true, all useless.

This lab's system prompt forces three moves:

| Move | What It Demands |
|---|---|
| **Top 3 Findings** | Specific numbers, cited to row or column |
| **One Anomaly** | Something a fast reader would miss |
| **One Recommendation** | A concrete action, not a platitude |

Structured demands beat structured data. Otherwise the model politely describes the spreadsheet back to you.

>## Task
>
>Send Claude:
>
>><b>What's the most important thing in this spreadsheet that I should bring to next week's leadership meeting?
>
>Then push the read in three different directions:
>
>><b>Drill into SMB. What's driving the churn jump?
>
>><b>What happens to total MRR if SMB keeps trending this way?
>
>><b>Which segment should we double down on for Q3?
>
>Each follow-up uses the same loaded data. Same numbers, different lens.
>
>Done when you have a finding worth bringing to a meeting — with the row or column it came from.

Example Spreadsheet

A hands-on course for non-technical managers and operators who need to turn raw business data into decisions, not summaries. You'll learn how to frame analytical questions sharply, read spreadsheets and internal docs through AI, combine internal numbers with market context, and build your own analyst agent that produces decision-ready briefs end-to-end.

Introduction to business analytics through the lens of AI — why raw data doesn't make decisions, the three layers of analytical questions, and where an AI assistant actually fits in the workflow.



Train the framing reflex. Turn vague business questions into sharp ones, pick the metric that actually matters, and lock down time windows, segments, and comparisons before touching any data.



Hands-on labs with the three sources every operator hits: sales spreadsheets, strategy docs in Notion, and market context from the web. Single-tool labs first, then a combined investigation.



Move from running labs to building your own. Write the persona, wire up the tools, and create an agent that delivers weekly KPI briefs and pre-meeting decision packs — finishing with a capstone Quarterly Business Review.

