A researcher recently asked me, “How do you use ChatGPT?” It’s a common question, but my answer is always the same:
It’s not about learning how to use ChatGPT—it’s about understanding its capabilities and developing a framework for how you’ll use it.
Rather than focusing on step-by-step navigation, I encourage people to first grasp what ChatGPT can do and then build a personalized approach that fits their research needs.
Why the "Why" Comes Before the "How"
I’ve always learned best when I understand why something is being done before learning how to do it. Once I have the why, applying the how becomes much easier. And in the world of AI and prompt engineering, this approach is even more critical.
ChatGPT is massive—its potential applications are endless. If you focus too narrowly on learning one specific task, you miss the bigger picture:
👉 Why should AI verify its own outputs?
👉 Why does prompt structure impact accuracy?
👉 Why should research rely on human oversight instead of AI’s internal logic?
These bigger questions lead to a deeper understanding, allowing you to apply AI more effectively across research contexts.
This Approach is Especially Important for Researchers
Many researchers, professors, or institutions may not be interested in technical details—most often, they care more about the impact of AI on research rather than learning how to fine-tune prompts themselves. Often, it’s students, research assistants, or tech-savvy team members who work directly with the tools.
That’s why I encourage a zoomed-out approach first—understanding what AI can do, why it matters, and how it should be structured for reliability. Once that foundation is in place, learning how to execute tasks becomes much easier and more intuitive.
So instead of focusing only on how to use ChatGPT, I invite you to start by exploring why AI matters in research—and let that guide your approach.
My name is Nick, and I enjoy teaching and speaking about the intersection of research, ChatGPT, and prompt engineering. My work focuses on developing easy-to-use frameworks and strategies that ensure AI doesn’t just generate answers, but also verifies and checks itself—helping researchers use ChatGPT more effectively and responsibly. If you have questions, need help setting up, or want to improve your prompts, feel free to reach out—I’d love to help!