From table to insight
Listen to this lesson
Nigerian voice narration
Fictional training case. After cleaning the Lagos Depot register, Officer Bello has a clean 300-row table but her supervisor wants to know by 2pm what it means, not the table itself. This lesson covers converting a cleaned table into ranked, sized, labelled insights. Work through the example, identify the evidence needed and practise the method with cleared or synthetic inputs. Any additional figures in the explanation are separate practice examples, not claimed rows in a downloadable file.
Worked example
Bello pastes the cleaned table and asks AI for the 'top 5 patterns ranked by size' with supporting figures. AI returns, for example: 'Depot B sales fell 18% (₦2.1m to ₦1.722m) between January and February — the largest movement in the dataset.' For each pattern, Bello asks AI to add one plain sentence explaining what it might mean, explicitly marked 'possible cause — needs confirmation' rather than stated as fact. She cross-checks the ₦2.1m and ₦1.722m figures herself in a pivot table before including them in her note, since she has learned AI can misstate numbers even while describing a real pattern correctly.
The method
Always request causes as hedged hypotheses, never conclusions, and require the exact supporting numbers alongside each claimed pattern so they can be independently verified against the pivot table or source data.
Worked practice and common mistakes
From ₦2.1m to ₦1.722m, the decline is ₦378,000 or 18% of the starting value. Compare amount and percentage: a large percentage can have a tiny baseline. State period and coverage alongside the insight. A pattern can be verified in the table, while a proposed cause needs separate evidence rather than a story that sounds plausible.
Review before using the result
An insight equals pattern plus size plus meaning. Rank by size so the biggest finding leads. Treat AI's proposed cause as a hypothesis to test, never as settled fact.
Your workplace practice
Use the recommended free assistant with this lesson's fictional example. Here is my cleaned table. Give the top 5 patterns ranked by size with supporting figures, one plain-English sentence per pattern, and mark any cause as 'possible — needs confirmation'. Keep a copy of the input and draft. Compare the result with the verification steps above, record any correction, and retain placeholders where evidence is missing. The expected result is a checked draft for human review, not an automatically approved decision. Course examples and practice responses are fictional; amounts, dates, rules and thresholds are not official guidance or supplier quotations.
Open Google Gemini (free tier) and paste this prompt there. Explains measures from a small fictional table; verify denominators and calculations in your spreadsheet.
Here is my cleaned table. Give the top 5 patterns ranked by size with supporting figures, one plain-English sentence per pattern, and mark any cause as 'possible — needs confirmation'.
Why this tool: Explains measures from a small fictional table; verify denominators and calculations in your spreadsheet.
Hit a free limit? Switch to ChatGPT or Gemini and continue — the prompt works in any assistant.