Learn AI fundamentalsModule 2 of 4 · 0 done
Prompting that works first time
A simple structure — role, task, context, constraints, examples, format — and how to iterate when the output misses.
By the end you’ll be able to
- Write structured prompts
- Use examples (few-shot) to set quality and tone
- Iterate with specific feedback instead of starting over
The six parts of a strong prompt
Role (who it should act as), task (one clear verb), context (audience, purpose, background), constraints (length, tone, must/must-not), examples (what good looks like) and format (bullets, table, JSON). You rarely need all six, but missing context is the usual reason for generic output.
- Be specific about the audience
- Give the model the source material
- Ask for the format you’ll paste into
Show, don’t just tell
One or two examples of the output you want (few-shot prompting) communicate tone, length and structure better than adjectives. “Write it like this:” followed by a sample beats “make it punchy”.
Iterate like an editor
When output misses, give targeted feedback: “Shorter — 3 bullets, each under 12 words, lead with the number.” Ask the model to list its assumptions or questions before writing on complex tasks. Save prompts that work as templates.
Build a reusable prompt template
Choose one of the three tasks from your task map.
Deliverable: A before/after comparison and a reusable template. Add it to your skills passport as a project when it’s done.
Check your understanding
Answer 3 scenario questions. Get 2 or more right to complete the module.
See how your prompting scores
A free test adds Prompting to your skill report and shows how close you are to the 75% job-ready target.