Creating an AI “mentor” in mentorAI requires users to carefully craft a set of prompts. While using an LLM like ChatGPT, Claude, or Gemini to create these prompts is a valid shortcut, it is beneficial to understand some of the basics of prompt engineering in order to effectively evaluate and adjust prompts in order to get to a working mentor model.
Keys to crafting a strong prompt:
Be clear and specific: What exactly should the chatbot do?
Define the mentor’s persona: What tone and role should the chatbot adopt with students?
Include Examples: Show what good output looks like
Set Boundaries: What should the chatbot avoid or not do?
Note - it’s important to frame boundaries positively! Chatbots don’t always respond to being told not to do something. See for more information & examples.
Plan for Student Misuse or Misunderstanding: How might students game the system or get confused?
Prompt engineering resources:
This article by OpenAI offers a succinct guide to prompt engineering, with concrete examples of each principle.