Skip to content
  • Official
  • Beginner
  • English
  • 9 steps · 2 quizzes

ChatGPT for Data Analysis: A Hands-On Workshop

ChatGPT for data analysis training: describe your data, strip personal data, read the code and recount the AI's numbers on a sample export.

  • Free
  • No account needed
  • Stop any time, pick up where you left off
Workshopy.io

WorkshopyOfficial

78 lessons · used by 2 teachers

For teachers

Teaching this? Run it live with your class.

  • Students join with a code — no accounts
  • See who’s done and who’s stuck, step by step
  • It’s your copy — change anything before class

Sign in to copy it to your workspace. It’s free.

Your path

9 steps · 2 quizzes · open any step, or read it here

  1. ChatGPT for data analysis: what this workshop practisesStart hereIn this hands-on workshop you practise ChatGPT for data analysis the safe way: what to tell it about your data, what to ask for, and how to check its numbers before anyone acts on them.InteractiveHands-on
    Read this step

    In this hands-on workshop you practise ChatGPT for data analysis the safe way: what to tell it about your data, what to ask for, and how to check its numbers before anyone acts on them. You work on one small support-ticket export and audit the assistant's answers yourself, row by row.

    Here is the whole idea in one answer. The assistant gives a number that sounds right. Press Recount and watch where it went wrong.

    Interactive · Check the assistant's number: a recount in four moves — try it in the lesson

    In this lesson you'll:

    • describe your data so the assistant doesn't have to guess, and strip what should never be pasted,
    • ask for the method and the code, and read them,
    • recount the assistant's numbers with a quick independent check,
    • catch the common errors: blanks read as zero, the wrong period, the wrong denominator, averages of averages, invented columns and causes the data can't show,
    • turn a checked finding into a chart and a short note with caveats.

    It takes about an hour. Every AI reply here is a simulated example, written to show the mistakes real assistants make.

    Takeaway: an assistant's number is a claim, not a result. It becomes a result once you've checked it.

  2. Describe the data before you askChat assistants are fast with data. Some only read what you paste; others (ChatGPT's data analysis is one) can open a file you upload and run code on it, usually Python. Either way they start knowing nothing about your file except what is in it.InteractiveHands-on
    Read this step

    Chat assistants are fast with data. Some only read what you paste; others (ChatGPT's data analysis is one) can open a file you upload and run code on it, usually Python. Either way they start knowing nothing about your file except what is in it.

    A column called hours could be hours or days. A blank could mean zero, unknown or "not yet". Your period might be a quarter while the export starts a few days early. When the prompt doesn't say, the assistant guesses, and it doesn't tell you it guessed.

    So before the question, give four facts:

    1. What one row is (a ticket, an order, a customer, a day).
    2. The units and scales (hours or minutes, euros or dollars, a 1–5 score).
    3. The period you mean, with dates.
    4. What a blank means (still open, not asked, zero).

    Try it: add facts to the prompt. Each one removes a guess, and the simulated reply changes with it.

    Interactive · Build a prompt that describes the data — try it in the lesson

    Notice how the reply changed once it knew the period and the blanks: same file, a different number, and it now says what it left out.

    Takeaway: one row, the units, the period, the blanks. Four sentences that turn a guess into a calculation.

  3. Strip the export before you paste itAn export from a work system carries more than your question needs: customer names, emails, phone numbers in free-text notes, staff names.InteractiveHands-on
    Read this step

    An export from a work system carries more than your question needs: customer names, emails, phone numbers in free-text notes, staff names. None of that helps the assistant answer "how fast did we resolve tickets", and all of it is data your company is responsible for.

    The habit is to decide column by column, before anything leaves your computer:

    • Keep what the question needs.
    • Drop what it doesn't, above all anything that identifies a person.
    • Replace with a code (C-07 instead of a name) when you need to tell rows apart but not who they are. Keep the key at your end.

    Free-text columns (notes, comments, descriptions) are the trap: they look harmless and hide phone numbers, names and account details. Drop them, or replace them with a category.

    Never paste passwords, API keys or other secrets, whatever the tool. And use the AI tool your company has approved, under its data policy: that decides where your data goes and who may see it. These are habits, not legal advice; your policy says what applies to you.

    Try it: decide for each column. Every choice tells you why.

    Interactive · Strip the export before you paste it — try it in the lesson

    Takeaway: paste the smallest table that answers the question. If a column names a person, it almost never needs to leave.

  4. Ask for the method and the code, not just the numberA bare number can't be checked. A number with its method can: you can read what the assistant did, step by step, and see the choice that changed the answer. So ask for both, every time: What was our average time to resolve a ticket in Q3 2026?InteractiveHands-on
    Read this step

    A bare number can't be checked. A number with its method can: you can read what the assistant did, step by step, and see the choice that changed the answer.

    So ask for both, every time:

    What was our average time to resolve a ticket in Q3 2026? Show the code or formula you used, say how many rows you used, and list any rows you left out and why.

    An assistant that runs code (like ChatGPT's data analysis) can show you the code it ran, often Python with the pandas library. One that only reads your paste can give you a spreadsheet formula to run yourself, for example =AVERAGEIFS(H:H, B:B, ">="&DATE(2026,7,1), B:B, "<="&DATE(2026,9,30)) with the dates in column B and the hours in column H; it skips blank cells. You don't need to write either, only to read it line by line and ask: which rows does this keep, and what does it do with blanks?

    Try it: run the assistant's code one line at a time and watch the hours column. Flag the two lines you'd question.

    Interactive · Read the assistant's code, one line at a time — try it in the lesson

    The giveaway was in plain sight: a start date of 28 June for a quarter that starts on 1 July, and a line that turns "still open" into "0 hours". Asking for the code made both visible.

    Takeaway: ask for the method, the code and the row count. Then read which rows it kept and what it did with blanks.

  5. Check the numbers with a quick recountReading the code is one check. The other is to work the number out yourself, independently, with the simplest tool you have: a filter and a count, a sum, an average in a spreadsheet. You don't recount everything.InteractiveHands-on
    Read this step

    Reading the code is one check. The other is to work the number out yourself, independently, with the simplest tool you have: a filter and a count, a sum, an average in a spreadsheet.

    You don't recount everything. Recount the numbers someone will act on: the headline figure, a total, the group that "handled the most". A quick recount takes a minute and catches most errors, because most errors are about which rows were counted.

    When your number differs, don't stop at "it's wrong". Ask which rows would give the assistant's number. That tells you what it did, and what to tell it.

    Try it: the assistant summarised the quarter in three numbers. Use the filters to recount each one and type what you get.

    Interactive · Recount the assistant's three numbers — try it in the lesson

    All three wrong numbers came from two slips: the assistant used all 20 rows of the file, two of them from June, and read three blanks as zeros. Describing the period and the blanks (step 2) would have prevented both.

    Check your work · Recount one more yourself: in the tool above, how many Q3 2026 tickets came in by Chat? Paste the number. — check it in the lesson

    Takeaway: recount the numbers people will act on. When yours differs, find the rows that give the assistant's number.

  6. Check: asking well and recountingQuiz · 4 questions
    Read the questions

    Question 1. You ask for the average order value from a sales export. Which fact about the data helps the assistant most?

    • "Please double-check your maths."
    • "Each row is one order line, not one order: an order can have several rows."
    • "This is very important for our quarterly review."
    • "You are an expert data analyst."

    Question 2. Your export has columns order_id, date, customer_name, customer_email, product, amount, notes. You want total sales by product. What do you paste?

    • All seven columns, so the assistant has the full picture
    • Everything except the email column
    • order_id, date, product and amount
    • Only customer_name and amount

    Question 3. The assistant answers "Average delivery time: 3.2 days." What should you ask next?

    • "Are you sure?"
    • "Show the formula or code you used, how many rows you used, and any rows you left out."
    • "Round it to one day."
    • Nothing: 3.2 days sounds about right

    Question 4. The assistant says 240 orders in March. Your filter on March gives 226. What is the most useful next step?

    • Trust the assistant: it read the whole file
    • Average the two numbers
    • Find which rows would give 240, for example a wider date range or duplicate rows
    • Ask the same question again until the numbers match
  7. What you divide by: percentages and averages of averagesTwo errors hide in the last line of a calculation, the division. The denominator. "47% of tickets were resolved within 4 hours" depends on what "tickets" means: all rows, the quarter's tickets, or only the resolved ones.InteractiveHands-on
    Read this step

    Two errors hide in the last line of a calculation, the division.

    The denominator. "47% of tickets were resolved within 4 hours" depends on what "tickets" means: all rows, the quarter's tickets, or only the resolved ones. Each is a different, true percentage of a different thing. The error is to compute one and say another. Ask: out of how many?

    Averages of averages. If Email averaged 7.4 hours over 5 tickets and Chat 2.0 hours over 6, the overall average is not the middle of 7.4 and 2.0. Averaging the averages gives every group the same weight, however many tickets it has. The overall average is the total of all hours divided by all tickets. The bigger the groups differ in size, the further apart the two numbers get.

    Try it: pick a denominator and see which one gives the assistant's 47%. Then switch to An average and drag the slider.

    Interactive · What you divide by: percentages and averages of averages — try it in the lesson

    Both errors give a clean, plausible number, so neither looks wrong. The only defence is to ask what was divided by what.

    Takeaway: every percentage needs "out of how many", and an overall average is the total divided by the count, not the mean of group means.

  8. Invented columns and causes the data can't showSome claims in an AI's analysis come from nowhere. Asked for "insights", an assistant may state things no column could show: an escalation rate when there is no escalation column, a first-reply time when only closing time was recorded.InteractiveHands-on
    Read this step

    Some claims in an AI's analysis come from nowhere. Asked for "insights", an assistant may state things no column could show: an escalation rate when there is no escalation column, a first-reply time when only closing time was recorded. They read like the rest of the answer.

    Others are built on something real and then go one step too far. In these tickets, longer waits do go with lower scores. But "so answering faster will raise satisfaction" is a cause, and the data only shows that the two move together. Hard problems take longer and annoy customers; the difficulty could be behind both. Patterns are worth reporting; causes need more than a spreadsheet, such as a test or a deeper look.

    For each claim, ask two questions:

    1. Which column shows this? If none, it's invented. Cut it or ask where it came from.
    2. Does it say why? Words like "because", "so", "drives" and "leads to" claim a cause. Say "goes with" unless you can show more.

    Try it: sort the assistant's four insights. The columns you pasted light up for the claims they can check.

    Interactive · In the data, not in the data, or a cause the data can't show? — try it in the lesson

    Takeaway: tie every claim to a column. If it says "because", check whether the data can really say that.

  9. Practice: recount and spot the errorThese exercises use the Q3 2026 tickets (1 July – 30 September) from the lesson. A blank in hours means the ticket is still open; a blank in csat means no survey reply. All data is illustrative.Practice · 6 exercises
    Read this step

    These exercises use the Q3 2026 tickets (1 July – 30 September) from the lesson. A blank in hours means the ticket is still open; a blank in csat means no survey reply. All data is illustrative.

    ticket opened region channel hours csat
    T-103 2026-07-02 North Phone 8 3
    T-104 2026-07-06 South Email 12 2
    T-105 2026-07-09 West Chat 1 5
    T-106 2026-07-14 West Email 6 4
    T-107 2026-07-21 South Phone 9
    T-108 2026-07-28 North Chat 3 5
    T-109 2026-08-03 West Phone 7 3
    T-110 2026-08-11 South Chat 2 4
    T-111 2026-08-17 North Email
    T-112 2026-08-24 West Email 10 2
    T-113 2026-08-31 South Email 4 4
    T-114 2026-09-04 North Phone 6
    T-115 2026-09-10 West Chat 2 5
    T-116 2026-09-15 South Phone
    T-117 2026-09-21 West Chat 1 4
    T-118 2026-09-23 North Email 5 3
    T-119 2026-09-28 West Phone
    T-120 2026-09-29 South Chat 3 5

    The two June tickets in the full export were T-101 (North, Email, 5 hours, csat 4) and T-102 (West, Chat, 2 hours, csat 5).

    How many Q3 tickets came in by Email?

    What was the average csat in Q3, counting only tickets with a score? Give two decimals.

    The assistant says West's average time to resolve in Q3 was 3.9 hours. What is the right figure, in hours?

    What percentage of Q3 tickets are still open? Give one decimal, without the % sign.

    The assistant writes: "North averaged 5.5 h, South 6.0 h and West 4.5 h, so the overall average is 5.33 h." What went wrong?

    • It averaged the three averages
    • It counted open tickets as 0
    • It used the wrong date range
    • Nothing: 5.33 is right

    The assistant says "47% of tickets were resolved within 4 hours." Seven Q3 tickets took 4 hours or less. What did it divide by?

    • All 20 rows of the file
    • The 18 Q3 tickets
    • The 15 resolved Q3 tickets
    • The 7 fast tickets
  10. From finding to chart and note, with caveatsA checked number still needs to travel well. Most findings go to someone as a chart and a few sentences, and that is where the caveats get lost.InteractiveHands-on
    Read this step

    A checked number still needs to travel well. Most findings go to someone as a chart and a few sentences, and that is where the caveats get lost.

    Pick the chart for the comparison you're making:

    • Bars compare separate groups on one scale (channels, regions, products).
    • A line shows change over an ordered axis, usually time.
    • A pie shows parts of one whole that add up to 100%. Averages, rates and scores never add up to a whole, so they never go in a pie.

    Then the note: the finding, plus what a reader needs to trust it. The period and the count. What was left out and why. Where the number is shaky (a small group). How it was checked. And no cause the data can't show.

    Assistants are good at drafting both. Ask for the chart and a draft note, then check the note against this list before it goes out.

    Try it: fix the assistant's chart, then build the note from the sentences offered.

    Interactive · Turn the finding into a chart and a note with caveats — try it in the lesson

    Takeaway: bars to compare, lines for time, pies only for parts of a whole. A note carries the period, the count, what was left out and where it's shaky.

Comments

You’ll sign in with Google before it’s posted.Comments are public — don’t name your students.
0 / 1,500

No comments yet. Be the first to say how it went.

Using it

Workshopy shares this lesson under CC BY 4.0. Anyone may use and change it, with credit to you. Anyone can learn it here, free. A copy in your workspace is yours to change and run live; your students never need an account.

Versions

  1. 1

    Version 1Current

    · First published

Copies are made from the current version. A copy you already have doesn’t change.

More from Workshopy

All 78 lessons
All 21 Data & AI lessons