On your task, not on an exercise
The one commodity topic we kept, because here you do it on your own material.
Prompting is the one thing every course covers. The difference here is that you are prompting against your own documents and your own quality bar from the first minute.
Prompting is the subject every free course covers, and most of them cover it competently. We have not tried to improve on the theory. What changes is the material: from the first minute you are briefing a model on your own report, your own policy document, your own spreadsheet, against your own quality bar rather than a worked example written by a course team.
The session that does not appear elsewhere is 2.3. General warnings about hallucination are easy to nod along to and hard to act on. Invented Kenyan and Nigerian case citations, an out-of-date KRA or FIRS rule, and a date quietly rendered American are specific enough to actually check for.
57 minutes in total, in sittings short enough to fit a working day. Each one ends with something in your hands.
What you do
A five-part structure — context, role, input, standard, format — that you can reuse for anything. Applied immediately to your anchor task.
You walk away holding
A reusable prompt structure
What you do
Feed the model your real material: a report, a policy, a spreadsheet, a set of meeting notes. Learn what to strip out before you do, and why.
You walk away holding
A working prompt that uses your files
What you do
Every course warns you about hallucination in the abstract. This one shows you the local failure surface: invented Kenyan and Nigerian case citations, out-of-date KRA, FIRS and SARS rules, fabricated national statistics, and currency and date formats quietly rendered American. Build a checking routine short enough to survive a deadline.
You walk away holding
A localised verification checklist
What you do
Run your anchor task end to end with AI for the first time. Time it. Compare against the figure from session 1.1.
You walk away holding
Version one, timed against your baseline
Four things you keep. They go into the AI Work Dossier you assemble in session 5.3.
A reusable prompt structure
From session 2.1
A working prompt that uses your files
From session 2.2
A localised verification checklist
From session 2.3
Version one, timed against your baseline
From session 2.4
All twenty sessions, no payment details, one real task from your own job. Register and the lessons come to you.