Innovation Profs - 6/13/2025

Your guide to getting the most out of generative AI tools

Welcome to Gen AI Summer School

We’re spending the summer teaching you the essentials you need to succeed in an AI-forward world.

Here’s the plan:

  • May 30: Intro to large language models

  • June 6: Multimedia tools

  • Today: Guide to prompting

  • June 20: Building a prompt library

  • June 27: Building Custom GPTs

  • July 11: Intro to reasoning models

  • July 18: Intro to deep research

  • July 26: AI ethics

  • Aug. 1: Implementing Gen AI in your job

  • Aug. 8: Implementing Gen AI at your company

  • Aug. 15: The road to Artificial General Intelligence

  • Aug. 22: Where Gen AI is headed

Guide to prompting

If you perform a Google search for “prompting is the new,” you get results like:

  • “prompting is the new coding”

  • “prompting is the new literacy”

  • “prompting is the new scripting”

  • “prompting is the new power skill”

Although prompting is the process for obtaining outputs such as text, images, audio, video, and code across a range of generative AI tools, let’s focus here on prompting large language models. What exactly is involved in LLM prompting (hereafter, just “prompting”)? And what counts as a good prompt?

Snider and I have combed through a gaggle of prompting frameworks in search of an easy-to-understand yet comprehensive scheme for prompting, but eventually we arrived at one of our own: BRIEF.

The BRIEF Approach to Prompting

When you craft your prompts, it is helpful to include the following ingredients:

B — Background

The more relevant background information you can provide, the better the response will be. Example: Audience, goals, context.

R — Role

Specify the role you want the model to assume. Example: Act as a marketing expert, teacher, editor, coach.

I — Instructions

Give clear instructions. These can be simple or complex depending on your task. Example: “Summarize this article in 3 bullet points.”

E — Examples

Provide examples of the kind of output you want. Example: “Here’s a sample social post for reference.”

F — Format

State how you want the output delivered. Example: “Table format, bullet points, short paragraph, script.”

There may be some overlap between these categories, but they still provide a useful heuristic for us. In addition, not all of these ingredients are required for an effective prompt.

An Example

Here’s an example that puts all of these ingredients together:

  • Background: Drake University is a private liberal arts university in Des Moines, Iowa. Known for its strong programs in journalism, business, pharmacy, and the arts and sciences, Drake emphasizes student-faculty collaboration, experiential learning, and a global perspective. It offers a range of study abroad opportunities that support its mission of preparing students for meaningful personal lives, professional accomplishments, and responsible global citizenship.

  • Role: You are a friendly and knowledgeable admissions counselor at Drake University. Your job is to respond to prospective student inquiries in a warm, professional, and informative tone that reflects Drake’s values.

  • Instructions: Write a brief email response to a high school student named Jamie who asked about study abroad opportunities at Drake. Highlight the range of options, emphasize Drake’s support for global learning, and invite further questions.

  • Examples:
    “Hi Jamie, thanks for reaching out! Drake offers over 300 study abroad programs in more than 50 countries—from semester exchanges to short-term travel seminars. Our Global Engagement Office works closely with students to find the right fit for their interests and major…”
    “A popular option is our J-Term in Spain, where students immerse themselves in Spanish language and culture while living with local families. It’s one of many ways Drake helps students gain global perspective…”

  • Format:
    The output should be a concise, friendly, and informative email message written in the first person. Aim for 100–150 words. Keep the tone welcoming and student-centered.

Conclusion

Good prompting helps AI generate higher quality, more relevant, and accurate responses with less trial and error. It allows users to control tone, format, and depth, making AI outputs more useful and aligned to specific goals. Ultimately, strong prompts turn AI into a powerful collaborator rather than just a tool.