Check what AI gives you in three steps
To know whether the AI got it right, you don't need to know more Excel. What you already know about your numbers is enough.
You go at your own pace, with your Maestro beside you, 1:1, through the whole course: ask it anything, and it asks you questions too.
8 skills · 2 modules
What will you be able to do?
Each box is a skill. The base is at the bottom, recognizing and explaining, and you work your way up to building something of your own and judging what works and why. Hover over a box to see what it builds on. Click it to see where I teach it and how your Maestro checks it.
- Analyze
- Apply
- Understand
- Remember
Analyze
Reconcile a result with an independent number you already trust, and explain any difference
Where I teach it: Three steps to check a formula · Reconcile with a number you already know
Builds on:
- Check a result against what you expect: order of magnitude, totals, ranges, and published references
Your Maestro asks you to break a problem down with it and saves it as evidence when you do.
Apply
Spot-check a result by recomputing a few rows by hand, spread across the start, middle, and end
Where I teach it: Three steps to check a formula · Check a few rows by hand
Your Maestro asks you to use it on a new case and saves it as evidence when you do.
Test a formula, query, or code with a case whose answer you already know, including an edge case such as a value that isn't there
Where I teach it: Three steps to check a formula · Try to make it fail
Your Maestro asks you to use it on a new case and saves it as evidence when you do.
Check a result against what you expect: order of magnitude, totals, ranges, and published references
Where I teach it: Three steps to check a formula · Reconcile with a number you already know
Your Maestro asks you to use it on a new case and saves it as evidence when you do.
Understand
Understand why checking AI's work takes the same expertise as the work it automates
Where I teach it: From the formula to the agent · You already do data engineering
Builds on:
- Understand AI in data work as an extension of your expertise, where you answer for the result
Your Maestro asks you to explain it in your own words and saves it as evidence when you do.
Understand AI in data work as an extension of your expertise, where you answer for the result
Where I teach it: From the formula to the agent · You already do data engineering
Your Maestro asks you to explain it in your own words and saves it as evidence when you do.
Recognize that much of your expertise is tacit: standards and habits you apply without stating them
Where I teach it: From the formula to the agent · Ask for the test up front
Your Maestro asks you to explain it in your own words and saves it as evidence when you do.
Remember
Know the ways an AI's answer with data can drift from what you need: decisions you didn't ask for, results that look right and count something else, and made-up values
Where I teach it: Three steps to check a formula · An erratum
Your Maestro asks you to recognize and recall it and saves it as evidence when you do.
Who is this course for?
For anyone who gets an Excel formula, a query or an agent-made table from AI and needs to know whether it's right before using it. You don't need to know more Excel: what you already know about your numbers is enough. You practice with a bakery's sales sheet in Excel or Google Sheets.
Ask your Maestro
Your Maestro is an AI that knows this course. Ask it about the first page and it answers right here, free.
You: Where do I start?
Your Maestro: From what you already know. Tell me what you've done with data, and I'll start this page from there.
Asking about: Answers from the page "How do you know it's right?"
Only this browser keeps what you ask here. How it works
What we'll cover
Three steps to check a formula
From the formula to the agent
How long does it take?
30 minutes to 1 hour
A guide: you go at your own pace, and the course waits where you left off.
Common questions
- How do I know if the formula or result an AI gave me is right?
- In three steps. First, pull a few rows by hand, from the start, the middle and the end, and recalculate them. Second, try to make it fail with an edge case, like a value that is not there. Third, reconcile the result with an independent number you already trust. If something does not match, explain the gap.
- Why does AI code well but get data analysis wrong?
- When you program, tests warn you when something breaks. With data, nothing does: the AI assumes what a row is, which rows to drop or what to divide by, and the number looks fine even when it is wrong. So you ask it what it decided without being asked, and check it yourself with your three steps.
- Do I need to know more Excel to check the AI?
- No. To know whether the AI got it right, you do not need more formulas. What you already know about your numbers is enough: roughly what the result should be, which total you know by heart, and which odd cases exist in your work. That knowledge is the checking tool.
- Do these steps work when an AI agent did the work?
- Yes. The same three steps work on an Excel formula and on a table an agent produced. The second module shows you how to ask for the answer with its proof included, and what to check when an agent did it. You take away a prompt that asks the AI for the result and the check together.
- Do I need a course, or can I learn this on my own?
- You can learn it on your own, and many people do. A course gives you the order: what to practice first, ready-to-use data, and exercises that show where you go wrong before it happens at work. This course is free, and your Maestro answers questions as you go. If you prefer going solo, the method still works.
- Is the course free, and do I need an account?
- It is free. You can read every page without an account. If you sign in with your email, your Maestro goes with you through the whole course. Without an account, your Maestro answers a few questions on each page. There are 2 modules and 9 pages, and you practice with a bakery's sales sheet in Excel or Google Sheets.
How do I check what AI does? I teach it in Your AI and Your Data: Don't Let It Make Up the Number.
What you get
- 2 modules and 9 pages, open whenever you want them.
- Videos inside the lessons.
Open to everyone: read all of it, and your Maestro, an AI, answers your questions on every page.
With a free account: your Maestro for the whole course, always on the page you're on, and the exercises run with nothing to install.
Who's teaching you
Sergio Sánchez
At my first job, at PPIC, we published a table with the numbers computed correctly but in the wrong row. It went past four people and nobody saw it. What made me mad was that nothing warned me at the time. Today AI gives you formulas and tables that run without a single error, and the question is the same: how do you know it's right? These three steps are my answer, and you already do them, even if you don't call them that.
I'm Sergio, chekos online. I'm a data architect, and I've spent more than ten years working with data in the Bay Area, mostly at mission-driven organizations: policy research first, then education, and now early childhood services. I grew up in Tijuana. In 2018 I started tacosdedatos to share what I was learning, and since then it's been a blog, a podcast, courses, guides, and a community. These days I spend a lot of my time building with AI agents and writing about how I organize my work around them. I share what I've learned; you take what's useful and make it yours.
See you in the course
Check what AI gives you in three steps