Workshop 1: AI Foundation
Discover how AI language models work and learn effective prompting with the 4 building blocks.
Workshop Toolkit
Copy a prompt and paste it into your AI tool.
1
Task to prompt
Turn my task into a clear prompt with: - A specific instruction - Relevant context - The desired result Ask 2 questions first if you need more information. My task: [describe in 1 sentence what you want to do]
2
Improve a prompt with the 4 building blocks
You are a prompt coach who helps me improve my prompts. Analyze my prompt and give me feedback based on the 4 building blocks: - TASK: Is it clear what needs to be done? - CONTEXT: Is there sufficient background information? - ROLE: Is a perspective or expertise defined? - FORMAT: Is the desired output format clear? For each building block, provide: 1. Score (present/partial/missing) 2. What's good 3. Concrete suggestion to improve it End with an improved version of my prompt. Here is my prompt: [PASTE YOUR PROMPT HERE]
Tips for after the workshop
- Try completing one concrete task with AI tomorrow. One is enough to get started.
- Never blindly trust AI output. Always check facts and sources yourself.
- Your first prompt is rarely the best. Refine based on what you get back.
- Separate your instruction from your content with brackets:
Improve this text: [paste text]. That way AI knows what the instruction is and where the input begins.
Frequently asked questions
Why does AI sometimes give wrong answers?
AI language models 'hallucinate': they generate text that sounds plausible but can be factually incorrect. How often depends on the subject and complexity of your question.
This happens because AI is not a database that looks up facts, but a model that predicts the most likely next word. That's why verification is always necessary.
This happens because AI is not a database that looks up facts, but a model that predicts the most likely next word. That's why verification is always necessary.
What's the difference between 'create' and 'write' in a prompt?
Word choice strongly influences output. 'Create a report' often produces a different structure than 'Write a report'.
Experiment with action verbs: analyze, summarize, compare, structure. Small changes to your prompt can make a big difference.
Experiment with action verbs: analyze, summarize, compare, structure. Small changes to your prompt can make a big difference.
How do I know if I can trust AI output?
Use the VAC-check:
Verifiable: check facts, numbers, and names against reliable sources
Accurate: check for calculation errors and logical inconsistencies
Consistent: compare with your own knowledge: would a colleague in the field say the same?
Always check critical output yourself, even when the answer sounds convincing.
Verifiable: check facts, numbers, and names against reliable sources
Accurate: check for calculation errors and logical inconsistencies
Consistent: compare with your own knowledge: would a colleague in the field say the same?
Always check critical output yourself, even when the answer sounds convincing.
How do I make my prompts better?
Two principles: iterate and be specific.
Don't expect the first prompt to be perfect: refine based on output. And add context: who is the audience, what is the goal, what format do you want?
The more specific your question, the more relevant the answer.
Don't expect the first prompt to be perfect: refine based on output. And add context: who is the audience, what is the goal, what format do you want?
The more specific your question, the more relevant the answer.