FREE STARTER LESSON · WRITTEN GUIDE

Before you build,
know your numbers.

A good AI project starts with a clear brief and a result you can check. Let’s prepare both using a fictional coffee shop.

No paid tools needed for this starter lesson. You’ll inspect sample data and write a project brief; the full workshop covers setup and the build.

1. Open the sample transactions

Download the CSV and open it in your spreadsheet app. It contains 24 fictional transactions across January–June 2026. The four columns are date, description, category, and amount.

Download sample CSV ↓

Positive amounts are cash received. Negative amounts are payments. Each month includes sales, payroll, supplies, and rent. These are simplified training data, not a complete accounting ledger.

2. Establish the numbers before asking AI

Sum positive values to find receipts. Add negative values and take their absolute value to find payments. Sum all amounts for net cash flow.

Money in$48,250

Money out$32,840

Net cash flow$15,410

For June alone, the totals are $9,800 in, $6,800 out, and $3,000 net. Your app should reproduce these values. Cash flow is not profit: this dataset does not model accruals, depreciation, or unpaid invoices.

3. Write a focused project brief

Describe what the tool should do, how the data is structured, and how you’ll check the result. Here is a starting point to adapt:

YOUR FIRST PROMPT

Build a cash flow dashboard for a fictional coffee shop.

The CSV columns are date, description, category, and amount.
Positive amounts are cash received; negative amounts are payments.

Start with three summary cards: money in, money out, and net cash flow.
Add a monthly chart, a transaction table, and a period filter.
Use USD and make the interface readable on a phone.

For the full sample, expected receipts are $48,250,
payments are $32,840, and net cash flow is $15,410.
For June alone, expected net cash flow is $3,000.

Explain your proposed approach before making changes.
Use only the fictional sample. Do not connect external accounts.
Flag ambiguous data instead of guessing.

4. Check one change at a time

In the interactive demo, open CSV import and add the three supplied rows. Receipts increase by $450, payments by $150, and net cash flow by $300, reaching $15,710. A repeated import must not count those same rows again.

That checking habit is the skill to keep: know the expected change, ask for a small step, and verify the result before adding more.

Before using work data

Use fictional data while learning. A locally running app and an AI service are different things: sending prompts or files to AI can transmit information outside your computer. Follow your employer’s policies.

READY FOR THE BUILD?

Turn the brief into a working app.

The full workshop takes you through setup, the dashboard, CSV import, and debugging.

See the six lessons — $69 →

Before you build,know your numbers.