Skip to Main Content

Between Two Joels: AI Prompts Edition

We're back with another edition of Between Two Joels, and it's our most practical one yet. We're helping you write prompts that squeeze the most out of AI engines.

We're back with our AI experts for another practical learning session

Creating prompts for AI that elicit valuable (and truthful) responses involves more than meets the eye. You might be wondering, “What is the return on optimizing my prompts? Wouldn’t most prompts give me what I need?” But you’d be wrong. While creating prompts may seem simple, optimizing your prompts can be the difference between a somewhat helpful response from your AI engine and your new best friend.

In the session, the two Joels and Ian ran through our tried-and-true approaches to AI prompt creation. Then, the attendees took it away, asking thought-provoking questions that delved deep into prompt creation.

Here are some key insights from the session:

  • Importance of Prompt Libraries and Frameworks: Developing and using prompt libraries can significantly improve efficiency and consistency in AI interactions. Frameworks like the Co-star prompt help you to provide information to AI models, which lead to more accurate and useful outputs.

  • Application in Data Analysis: AI tools are being extensively used to analyze large volumes of unstructured data, such as open-ended responses from focus groups and surveys. These tools can efficiently summarize and filter data based on various themes and subgroups. However, the analysis of complex quantitative data with multiple filters remains a challenge, and there are ongoing efforts to improve AI capabilities in handling the data sets.

  • Addressing Prompt Limitations and Rejections: The session discussed strategies for dealing with situations where AI tools refuse to perform tasks that they are technically capable of. It is important to tweak prompts and provide specific roles or contexts to guide the AI effectively. For instance, specifying a role such as "travel guide" can yield more precise and relevant recommendations from the AI​​.

Our Presenters

Joel Anderson

Joel brings decades of experience in the market research and analytics industry to Dig Insights. In 2023, Joel completed his Master's in Applied Artificial Intelligence from the University of San Diego. As the EVP of Advanced Analytics, Joel's team leads advanced analytics, innovation R&D, and data science for our client services work.

Joel Anderson
Ian Ash

Ian Ash

Ian is one of the Co-Founders at Dig Insights. He has over 20 years of experience leading large scale and international market research projects across several different industries. He's currently President of Upsiide, Dig’s SaaS platform purpose-built for innovation insights.

Joel Armstrong

Joel is our in-house AI expert, having completed both a Master's in Applied Artificial Intelligence from the University of San Diego and a PhD in Psychology at Western University. In his role as Director of AI at Dig, Joel helps lead our R&D as it relates to AI and AI best practices.

Joel Armstrong