Intermediate · 4 lessons · about 30 min · free certificate

AI for data analysts

A practical course on using AI to clean data, write queries, build charts and explain findings, while keeping the analysis honest and checkable. For analysts and people moving into analysis.

For: Analysts, reporting specialists and spreadsheet-heavy workers who want faster, more reliable analysis.

Start lesson 1

When you finish

  • You can sort analysis tasks into what AI drafts, what it assists, and what stays with you.
  • You can prompt AI for queries, formulas, cleaning steps and chart ideas, and test each one.
  • You can catch wrong joins, silent errors and made-up numbers before they reach a report.
  • You can protect personal and company data when using AI tools.
  • You can follow a 30-day plan and describe AI skills on a resume honestly.

Lessons

Final exam and certificate

8 questions. Score 7 or more for a free certificate of completion you can share and add to LinkedIn. Unlimited tries.

Take the final exam

Prompts you can use today

Copy one, replace the [brackets] with your details, and paste it into the AI tool you use. Leave out anything private.

Write a SQL query from a plain request

I use [database type]. Table orders has columns [list columns and types]. Table customers has columns [list]. Write a query that answers: [question in plain words]. Explain each join and filter in one line, and tell me one way the result could be wrong.

Explain a formula

Explain this spreadsheet formula in plain words, piece by piece. Then tell me what would break it, such as blanks, text in number cells or dates stored as text. [paste formula]

Plan a data cleaning pass

Here are the column names and five invented sample rows from my dataset: [paste]. List the cleaning checks I should run before analysis, such as duplicates, inconsistent spellings, impossible dates and missing values. For each, give a way to detect it in [tool].

Check my logic

I plan to calculate [metric] by [method]. Look for flaws: double counting, wrong denominators, survivorship, time-window mismatches. List up to five risks and a quick test for each.

Choose a chart

I want to show [message] to [audience]. My data has these fields: [list]. Suggest two chart types, say which you would pick and why, and name one way each could mislead the viewer.

Summarize findings for a manager

Turn these results into a half-page summary for a busy manager. Lead with the answer, give three supporting points, state one limitation, and end with a suggested next step. Use only the numbers I provide. [paste results]

Draft a data dictionary

From these column names and sample values, draft a data dictionary with columns: field, plain-language meaning, data type, allowed values, and questions I should ask the data owner. Mark any guesses clearly. [paste]

Review my notebook

Review this analysis code for mistakes in filtering, joins, grouping, rounding and date handling. Do not rewrite it. List problems with the line involved and a check I can run. [paste code]

Ask the AI tutor

Ask anything about this course, in any language. The tutor is an AI: it can be wrong, and it never needs your personal details.

AI-drafted. Checked by an automated validator and a separate AI reviewer; a person has not read every lesson. Translations and tutor answers are AI-made. Found a mistake? Tell us. Tool facts last checked November 2026; features change, so check the product's own help pages. AI can be wrong. General information, not professional advice. Product names identify the tools taught; no affiliation or endorsement. Current University is not accredited; certificates of completion are not degrees, credit or licenses.