The model on its own only knows what's in its training data — frozen, generic, with no idea about your Q1 numbers, your strategy doc, or what your competitors raised last week.

Tools change that. They let Claude look at your specific data the moment you ask.

## The Three Sources You'll Actually Use


A table of numbers, text, or categories, typically in Excel or CSV format.

Quick calculations; trend analysis; financial and operational reporting; clean, structured data.

Unstructured notes; context behind numbers; anything not in a table.

A collaborative document or knowledge base page, often used for strategy, planning, or meeting notes.

Context, reasoning, qualitative analysis, plans, and explanations.

Numbers and calculations; structured datasets; large-scale data analysis.

Live results from the public internet, including news, competitor sites, and market data.

Recent events; competitive intelligence; external facts not in your files.

Internal data; confidential information; company-specific context.

Each one fails in a different way. The system prompt is what forces it to fail less.


## What Changes With Tools

Without tools, Claude guesses. With tools, Claude has facts — but guessing is still the default unless the system prompt explicitly forces it to read first and speak second.

The next three labs walk through each source. One spreadsheet, one strategy doc, then both combined with market context.

**Takeaway:** Tools give Claude eyes on your data. The system prompt gives it discipline.

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.



How AI Reads Real Business Data

The Three Sources You'll Actually Use

What Changes With Tools

What Changes With Tools