Description

AI Prompting: Writing, Structuring and Stress-Testing Your Requests to Models

Move from a question asked at random to a well-built request that delivers an output you can use straight away

  • 1 day — 7 h
  • In-person or virtual
  • Foundation
  • Up to 6 participants

The same assistant gives one person a usable piece of text and another a vague, off-topic answer. The difference lies not in the tool but in the way the request is phrased: missing context, unspecified format, an implicit expectation that is never put into words.

This short format is devoted entirely to building requests. It sets out the elements that make up an effective prompt, the ways to have a weak answer corrected, and structuring techniques for long or repetitive tasks.

Learning objectives

  • Build a request that includes context, role, task, format and constraints
  • Provide examples that guide the form of the expected answer
  • Correct a weak answer through a targeted follow-up rather than starting again
  • Break a complex task down into successive request steps
  • Identify the elements in an answer that call for verification

What makes this programme different

Each technique is measured by comparing the output before and after rephrasing
Participants work on requests drawn from their own day-to-day activity
A library of template requests is built and shared at the end of the session

Programme

1Anatomy of an Effective Request

Saying what you actually expect

  • Context, role, task, format and explicit constraints
  • Effect of the level of detail on answer quality
  • Examples supplied as a model of the expected form
  • Common errors: requests that are too broad or instructions that contradict each other

2Steering the Exchange

Correcting rather than starting over

  • Targeted follow-up on the specific point to improve
  • Asking for an outline to be restated before drafting
  • Constraints on tone, length and vocabulary
  • Handling invented or overly assertive answers

3Structuring Repetitive Requests

Systematising what comes back every week

  • Breaking a long task into linked steps
  • Fill-in-the-blank request templates for regular use
  • Building and maintaining a personal library
  • Systematic checking of the facts and figures produced

Who is it for

Any employee using a generative assistant at work, whatever their role or level of technical skill.

Prerequisites

No prerequisites

Dates & locations

36 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.