Start a conversation ↗

Description

Prompt Writing: Framing, Structuring and Refining Your AI Requests

Three hours to obtain usable output from generative AI instead of hollow text you have to rewrite

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

The assistant's first answer is often flat, approximate or off-topic. You rephrase at random, then give up, concluding that the tool is not suited to real work. The issue rarely lies with the tool and usually with the request addressed to it.

Three hours online to learn how to frame a request that produces a usable result. You structure your instructions by specifying the role, the context, the expected format and the constraints. You learn to correct a disappointing answer through targeted follow-up prompts and to keep the wording that works so you can reuse it. You work on your own professional cases.

Learning objectives

  • Structure a request by specifying the role, the context and the expected format
  • Formulate constraints that frame length, tone and level of detail
  • Correct an inadequate answer through targeted follow-up prompts rather than complete rewording
  • Build a library of reusable requests for recurring tasks

What makes this programme different

Each participant works on three tasks drawn from their own role
Live comparison of the answers obtained from a raw request and a structured request
A personal library of requests built during the session

Programme

1What Makes a Request Effective

Understanding why the answer disappoints

  • How a conversational assistant works in general terms and the practical consequences
  • Missing elements that produce generic answers
  • The role of the context provided and of the examples attached
  • Known limitations and systematic verification of factual elements

2Structuring Your Request

Role, context, format and constraints

  • Assigning a role and a point of view to the assistant
  • Describing the professional context and the end reader
  • Specifying the expected format and length
  • Adding examples to set the tone and register

3Refining and Capitalising

Dialogue rather than a single command

  • Corrective follow-up prompts addressing one aspect at a time
  • Requesting variants and choosing between them with clear reasoning
  • Reusing a partial result and developing it further
  • Saving and organising the requests that work

Who is it for

Employees from all departments who use a conversational assistant in their daily work without prior training in how to formulate requests.

Prerequisites

Access to a generative artificial intelligence assistant during the session

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.