The Scenario
A streetwear brand in Johannesburg is launching an AI chatbot to handle basic return queries. They want the bot to sound "cool, respectful, and helpful" but absolutely NOT use slang that feels forced or cringey. If it doesn't know the answer, it must escalate to a human.
The Brief
Write the System Prompt that will govern the chatbot's behaviour.
Deliverables
- The core persona definition (Who is the bot? What is its goal?)
- Tone guidelines (What to do, and explicitly what NOT to do regarding slang)
- The "Escalation Trigger" instructions (exactly how and when to tell the user they are being transferred to a human)
Submission Guidance
System prompts live behind the scenes and dictate the "soul" of the AI. Use strong, imperative verbs ("You are...", "You must never..."). Give the AI examples of good vs. bad tone.
Submit Your Work
Your submission is graded against the rubric on the right. If you pass, you get a public Badge URL you can share on LinkedIn. There is no draft save, so work offline first and paste your finished response here.