Start a conversation ↗

Description

Tailored Generative AI: Scoping Use Cases, Building Assistants and Measuring Gains

One day to move from isolated experiments to assistants configured on your own content

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

After a few months of unstructured use, results plateau. Everyone keeps their prompts in a corner of a file, answers vary from one person to another and nothing is captured for reuse. The tool helps with one-off tasks but knows neither your documents, nor your business rules, nor your house style.

This 7-hour day teaches participants how to build tailored solutions. Each participant selects a use case from their own department, builds an assistant fed with their own content, defines the expected quality criteria, then compares successive versions to retain the one that holds up in daily use.

Learning objectives

  • Describe a use case in terms of task, input and expected output
  • Build a configured assistant from your own content
  • Formulate quality criteria for judging an output
  • Compare several versions of an instruction to retain the most stable one
  • Organise the sharing of prompts and assistants within a team

What makes this programme different

An assistant configured and tested during the session on a real case brought by the participant
A version-comparison method to make instruction choices objective
A template sheet to document and hand over a use case to your team

Programme

1From Need to Use Case

Scoping before configuring

  • Framing the need as task, input and expected output
  • Identifying high-volume repetitive tasks
  • Estimating the expected gain and the associated risk
  • Choosing the right level of automation

2Building a Tailored Assistant

Feeding the tool with your context

  • Standing instructions: role, tone, scope and exclusions
  • Adding reference documents and internal templates
  • Providing examples to fix the output format
  • Handling edge cases and responses in situations of doubt

3Evaluate, Improve and Roll Out

What separates an experiment from a working practice

  • Defining quality criteria for an output
  • Test sets and comparison of successive versions
  • Correcting drifts observed in use
  • Documentation and sharing within the team
  • Tracking the gains achieved

Who is it for

Users already familiar with generative AI, digital champions and department heads wishing to scale up their usage.

Prerequisites

Prior use of a generative AI tool in a professional setting.

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.