A common mistake is to think of AI as the **analyst**. It's not. It's the assistant that compresses the slow parts of analysis. The judgment stays with you.

## The Four Steps of Any Analytical Task

Every business question — from "are sales good?" to "should we kill this feature?" — runs through the same four steps:





Without AI, steps 2 and 4 eat 80% of the time. With AI, they collapse to minutes — leaving more energy for the steps that actually need a human.

## Where AI Is Genuinely Bad

Pretending AI is good at everything is the fastest way to get burned.

* AI is **bad at choosing which question matters** — it has no business context;
* AI is **bad at noticing it's wrong** — hallucinations sound as confident as facts;
* AI is **bad at numbers it computed itself** — it can write correct-looking calculations that are silently wrong;
* AI is **bad at judgment calls** — "is this anomaly worth investigating" is a human decision.

The rule: AI handles fetching and drafting. You handle framing and verifying.

## The Tools You'll Use in This Course

Across the next three sections, you'll work with four tools that map to a real workflow:



Reads tabular data — revenue, sales, churn;

Reads internal docs — OKRs, strategy notes, meeting notes;

Pulls external context — market, competitors, benchmarks;

Each tool changes what Claude can see. Without them, Claude only knows training data. With them, Claude becomes an assistant that can actually open your spreadsheet.

**Takeaway:** Section 2 sharpens your framing. Section 3 puts the tools in your hands. Section 4 wires it all into an agent that runs the whole loop.

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.



Where AI Fits in the Analytics Loop

The Four Steps of Any Analytical Task

Where AI Is Genuinely Bad

The Tools You'll Use in This Course