Summary  
This chapter covers enforcing input validation by requiring both a precise time window and a baseline reference before processing a metric.  

General domain of usage  
business metrics reporting

A locked metric is half the work. The other half is when you're measuring it and versus what.

"MRR is up 4%" means nothing without a window and a baseline. Up 4% this week or this quarter? Versus last week, versus plan, versus last year?

In this lab, Claude refuses to interpret any number until both are pinned.

## Window and Baseline Go Together

| Question | Why It Matters |
|---|---|
| **Window** — which exact dates | Same metric reads differently over 7 days vs 90 days |
| **Baseline** — versus what | Up 4% vs last year is great; vs plan is a miss; vs last week is noise |

A number without a window is a guess. A number without a baseline is decoration.

>## Task
>
>Bring Claude any business observation:
>
>><b>Our conversion rate dropped this month.
>
>Claude will refuse to engage until you say both the exact dates and what you're comparing against. Try to escape with "you know, recently" — it won't let you.
>
>Done when you've stated both: a precise window and a stated baseline.

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.

