🤖 How to Make AI Your Best Work Buddy: Mastering Structured Prompting 🤖

• 🤔 Unstructured prompting leads to mixed results with AI.

• 💪 Structured prompting can significantly enhance AI performance.

• 🧠 The CIDI framework is a practical method to implement structured prompting.

• 💡 Who: L&D professionals and anyone using generative AI tools.

• 💡 What: Learning to use structured prompting to improve AI outputs.

• 💡 When: Right now, as generative AI becomes increasingly prevalent.

• 💡 Where: In various professional settings, particularly within L&D.

• 💡 Why: To optimize the effectiveness and efficiency of AI tools in professional workflows.

Ever felt like your AI assistant is more of a toddler with crayons than a savvy sidekick? 🖍️ Let’s turn that around!

One thing I’ve learned along the way is that an increasing number of Learning and Development (L&D) professionals are using generative AI in their day-to-day work.

However, what’s also clear is that they’re using it with mixed results.

The real game-changers are those who've mastered the art of communicating effectively with AI systems – aka those who have ventured into the world of structured prompting.

In this post, I'll share some reflections on how to use structured prompting to optimize your AI skills.

Ready to make your AI as efficient as a seasoned pro? Let’s dive in!

Most generative AI tools operate like chatbots, which means we tend to interact with them conversationally, as if they’re another person.

This is both a strength and a risk: the point of entry for using it is basically zero, but it encourages us to interact in ways that aren’t optimal.

Over the last couple of weeks, I’ve observed L&D professionals and educators in action.

Imagine you are a Professor in marketing in a B School. How do you write a prompt to prepare your learning objectives for your students?

Let's see the example:

Write me some learning objectives for a marketing topic for management students on the 4 P’s of marketing in the business context 

• 😲 Woah, that’s a LOT of objectives. ChatGPT is very eager to please. You need to talk to it like an apprentice and give it clear direction.
  If you don’t, it will get carried away.

• 🔀 The objectives aren’t well sequenced. Generally, the objectives are pretty well-written; they each have a clear purpose by making good use of verbs like define, explain, analyze, etc.
  However, they jump around from low-level “illustrate” and “propose” objectives to higher-level “discuss” and “evaluate” objectives and then back again. As a learning experience, this isn’t optimal for either motivation or mastery.

• 🚀 They’re not optimized for learner motivation. Research shows that when we direct objectives at the learner and include a statement of the “why” (e.g., by including “so that you can [real-world impact]”), it helps to optimize the experience for both motivation and mastery. Because this isn’t standard or typical practice, however, AI doesn’t do it.

The TL;DR is that unstructured, conversational prompting is not the optimal way to work with AI.

As the name suggests, structured prompting is a method of giving AI very intentionally structured and worded prompts to (we hope) optimize the quality of its output.

Since AI isn’t really built to do this, it will take experimentation and effort to make a structured prompt work consistently (it is very hard to reach 100% consistency), but there are helpful frameworks to get you started.

The one I’ve been experimenting with over the last couple of weeks is the CIDI framework. It goes like this:

1. Context: Define AI’s role and objective. For example, “You are an instructional designer assisting in X.”

2. Approach: Provide step-by-step tasks. E.g., “First do X, then Y.”

3. Action Details: Set parameters like “The course should be online and no longer than X hours.”

4. Input: Incorporate relevant data or documents.

Context: You are a senior professor of marketing with 15 plus years of industry experience in marketing who is expert in teaching the 4 P’s of marketing to management students.

Approach These learning objectives will guide B School management students through understanding, analyzing, and applying the 4 P’s of marketing in a business context. 

The objectives should increase in complexity, from basic understanding to strategic application, and should be directed at the learner to enhance motivation and focus on implementation.

Actions: Every learning objective must:

1. Be project-based.
2. Increase in complexity from most simple to most complex.
3. Be directed at the learner, starting with "You will."
4. Provide 3 relevant examples “Application of 4 P’s of Marketing”
5. Motivate the learner by stating the why, e.g., "You will XYZ so that you can [something of real-world value]."
6. All be achievable within a 3-hour session.

Input:
LEARNER: B School management student
TOPIC: 4 P's in Marketing
GOAL: Understand the fundamental concepts of the 4 P's (Product, Price, Place, and Promotion) and how they are applied in marketing strategies.
Topic Flow: Basic knowledge of marketing principles. The learner's goal is to gain a deeper understanding and practical application of the 4 P's in marketing."

You can see how much more specific the AI’s output is with structured prompting.

Structured prompting doesn’t produce perfect results, but it can have a significant positive impact on the quality of AI’s outputs.

Think of AI as an apprentice. Assume it knows nothing. Give it very clear instructions on what to do, how to do it, and in what sequence. If there are common errors you’re trying to avoid, tell it what it must NOT do as well as what it must do.

AI needs you! You are the source of the context, approach, action details, and input that AI needs to produce its best possible work.

• 🧠 Understand AI's capabilities: Know what your AI tool can and cannot do.

• 📝 Use structured prompts: Implement the CIDI framework for clear and effective communication with AI.

• 🔄 Experiment and refine: Keep tweaking your prompts to find what works best.

• 🗣️ Be clear and detailed: Provide comprehensive and precise instructions to your AI.

• ⏳ Stay patient: Perfecting AI interaction takes time and practice.

Now go forth and make your AI work like the pro it was meant to be! 🚀

1. 📧 WGMI - Start an AI Software Business in 10 weeks

2. 📧 My Ask AI - AI Customer Support Assistant

3. 📧 Audio Pen - AI Voice Notes into Text

4. 📧 Exploding Topics - AI Trends on the Rise

5. 📧 Instagram University - Intro to Theme Pages

1. Global audiences suspicious of AI-powered newsrooms, report finds

2. Introducing 'Eye on AI': The Economic Times' brand new page on Artificial Intelligence

3. The rise and fall of AI at the McDonald’s drive-thru

4. Amazon pledges $230 million to boost generative AI startups

5. Meta unveils five AI models for multi-modal processing, music generation, and more

Empower Your Journey With Generative AI.

"You're at the forefront of innovation. Dive into a world where AI isn't just a tool, but a transformative journey. Whether you're a budding entrepreneur, a seasoned professional, or a curious learner, we're here to guide you."

Founded with a vision to democratize Generative AI knowledge,
 Think Ahead With AI is more than just a platform.

It's a movement.
It’s a commitment.
It’s a promise to bring AI within everyone's reach.

Together, we explore, innovate, and transform.

Our mission is to help marketers, coaches, professionals and business owners integrate Generative AI and use artificial intelligence to skyrocket their careers and businesses. 🚀

Joydeep Rakshit
Gen. AI Explorer
Co-Founder, Think Ahead With AI (TAWAI)