For Data Analysts

40 Questions Data Analysts Should Ask Before Trusting AI Outputs

When AI generates your analysis, you become responsible for logic you did not write. These questions help you verify the reasoning before your stakeholders act on the findings.

These are suggestions. Use the ones that fit your situation.

Download printable PDF

Questions About Data Selection and Filtering

1 Did the AI include or exclude any rows based on assumptions I did not state?
2 What date range did the AI use, and does it match the business period I need?
3 If the AI filtered for 'active customers', what rule did it apply and is it the same rule my organisation uses?
4 Did the AI handle null values by removing them, filling them, or ignoring them, and is that correct for this metric?
5 When the AI joined tables, which key did it use and could that key produce duplicates?
6 Did the AI apply any aggregation before the join that might have changed the row count?
7 If the AI selected 'top 10' or 'top N' items, what was the sort order and did I ask for that?
8 Are there any known data quality issues in the source table that the AI should have flagged?
9 Did the AI assume a 1-to-1 relationship between tables when a 1-to-many relationship exists?
10 When the AI ran the query, was it working from fresh data or cached results from earlier?

Questions About Statistical Logic and Calculations

11 If the AI calculated an average, did it use mean, median, or mode, and is that the right choice for this data?
12 When the AI showed a percentage change, did it use the correct baseline year or period?
13 Did the AI use a moving average or a simple average, and was that choice explicit or hidden?
14 If the AI flagged a trend as significant, what threshold or test did it use to decide?
15 When the AI calculated year-on-year growth, did it account for missing months or incomplete data in either year?
16 Did the AI apply any weighting to the values, or did it treat all rows as equal?
17 If the AI split data into groups, how many records are in the smallest group and is that sample size reliable?
18 When the AI calculated a ratio or rate, what denominator did it use and is it the standard denominator in your organisation?
19 Did the AI annualise figures that were only partial-year, and was the method disclosed?
20 If the AI identified an outlier, did it explain the threshold or just flag values that look unusual?

Questions About Visualisation Choices and Presentation

21 Why did the AI choose a bar chart instead of a line chart, or a scatter plot instead of a table?
22 What are the axis scales on this chart and could a different range make the pattern appear more or less dramatic?
23 If the AI sorted categories in a specific order, is that alphabetical, by value, or by my stated preference?
24 Did the AI truncate the axis to start at a value other than zero, and does that misrepresent the magnitude of change?
25 When the AI colour-coded segments, what threshold determines green versus red, and is it a meaningful threshold?
26 Does the chart show all the data, or did the AI filter or aggregate it without telling you?
27 If the AI combined multiple metrics into one chart, are they on the same scale or does the visualisation need a secondary axis?
28 Did the AI add a trendline or forecast line, and what statistical method did it use to generate it?
29 When Tableau AI or Databricks AI suggested a chart type, did you verify it against your organisation's reporting standards?
30 Are the labels on this chart clear enough that a stakeholder will understand what they are looking at without your explanation?

Questions About Assumptions and What You Did Not Ask

31 Did the AI make assumptions about what 'customer segment' means or what counts as 'active' in your business?
32 If the AI generated a summary statement, did it state the conditions or caveats that apply to that finding?
33 When you asked the AI to find 'why sales dropped', did it identify actual causation or just correlation?
34 Did the AI assume a linear relationship when a non-linear one might exist in your data?
35 If the AI said 'there are no anomalies', does that mean it looked for them or simply did not check?
36 When the AI provided a number without context, did you ask what the previous period was or what the target is?
37 Did the AI account for seasonality, and if so, what historical period did it use to define normal?
38 If the finding seems surprising, did you ask the AI to show its working or just accept the output?
39 When the AI said 'based on available data', what data was it actually allowed to see?
40 Did you verify the SQL or query logic that the AI wrote, or did you assume Code Interpreter got it right?

How to use these questions

Related reads

The Book — Out Now

Cognitive Sovereignty: How To Think For Yourself When AI Thinks For You

Read the first chapter free.

No spam. Unsubscribe anytime.