Start a conversation ↗

Description

Data Analysis with Generative AI: Preparing, Querying and Verifying

Getting usable data analysis from generative AI rather than commentary that merely sounds plausible

  • 0.43 days — 3 h
  • In-person or virtual
  • Intermediate
  • Up to 6 participants

A file is uploaded to a conversational assistant and an analysis appears within seconds. It reads well, but nobody knows whether the totals are correct, whether blank rows were excluded, or which column the calculation actually used. The real risk is not the visible error: it is the wrong figure presented with confidence in an executive meeting.

This short programme shows how to prepare a dataset before handing it to generative AI, how to frame requests that constrain the calculation, and how to check the result obtained. Every step is reproducible on the participant's own files.

Learning objectives

  • Prepare a dataset so that it can be processed reliably by a generative AI assistant
  • Frame an analysis request specifying the scope, the expected calculation and the output format
  • Produce a quantified summary and verify its results through cross-checking
  • Recognise situations where generative AI returns a plausible but incorrect result
  • Identify the data that must not be sent to an external tool

What makes this programme different

Every AI-generated analysis is cross-checked against a control calculation in the spreadsheet
The standard requests built during the session can be reused on other files
Handling of sensitive data is settled before any manipulation begins

Programme

1Preparing the data

What is decided before the first question

  • Expected structure of a table that is genuinely usable
  • Handling duplicates, missing values and inconsistent formats
  • Choosing the scope and describing the columns
  • Data to anonymise or remove before any transfer

2Querying generative AI

Framing requests that return a calculation, not a commentary

  • Essential components of an analysis request
  • Breaking a complex question down into successive steps
  • Explicitly requesting the calculation method applied
  • Obtaining a results table rather than a block of text
  • Useful follow-up prompts when the answer remains vague

3Verifying and using the output

Publish only what has been checked

  • Cross-checking results against a control calculation in the spreadsheet
  • Warning signs of a fabricated answer or one outside the requested scope
  • Formatting a summary intended to support decision-making
  • Traceability of requests and of file versions

Who is it for

Analysts and management controllers, together with operational managers responsible for reporting and advanced spreadsheet users.

Prerequisites

Confident use of a spreadsheet and the ability to build a PivotTable.

Dates & locations

12 scheduled dates between November 2026 and December 2027. Seats are confirmed in the order enquiries are received.

November 2026

December 2026

January 2027

February 2027

March 2027

April 2027

May 2027

June 2027

September 2027

October 2027

November 2027

December 2027

None of these dates suit you? We open additional sessions on request, and any programme can be run privately for your team.

Practical details

Before the programme
Online positioning questionnaire. Your development objectives are shared with the trainer, who tailors the practical case studies to your context.
Teaching methods
Theoretical input, workshops and practical case studies. Digital course materials and method sheets provided.
Assessment
Multiple-choice tests and role-play exercises. Assessment of learning at the start and end of the programme, with immediate and 60-day follow-up evaluations.
After the programme
One year of access to the e-learning platform. Self-assessment of the skills acquired and a 30-day follow-up session with your trainer.
How to register
Registration online or on the basis of a quotation.
Lead time
11 working days after confirmation of registration.
Accessibility
Accessible to people of determination. Contact our accessibility coordinator to design a suitable solution: contact@mpf-academy.ae
Start dates
Rolling intake: in addition to the scheduled sessions, this programme can start on request.