BoodleBox

I’m excited to share my latest work with BoodleBox! Last week, I had the opportunity to present to Phi Delta Epsilon, a medical fraternity at UofSC, about how BoodleBox uniquely supports Pre-Med and STEM students. I also highlighted some key features, including our Beginner Bots, which help new users get familiar with AI through simple, easy-to-use prompts. Additionally, I shared our Bot-Builder, which allows students to create, customize, and integrate AI into their workflow—showcasing that BoodleBox is built for every level of AI user. Beyond presentations, I’ve been collaborating with peers and filming a series of short videos on student perspectives on AI. If you’re interested, I’d love to hear your thoughts—just shoot me a message! A huge thank you to the PhiDE Brotherhood for the opportunity and to Zach Kinzler for his guidance and mentorship.

The value of Humans + AI collaboration in the real world: an academic study of 776 R&D professionals at Procter & Gamble revealed not just substantial performance gains from AI, but a host of other gains, including in emotional state. Some of the stand out insights from the research paper (link in comments): ?? AI + teams unlock top-tier innovation. Teams using AI were 9.2 percentage points more likely to produce top 10% solutions compared to the 5.8% baseline—making them about three times more likely to generate standout ideas. This effect was not seen for individuals using AI, highlighting a unique benefit in combining AI with human collaboration. ?? AI makes work faster and more detailed. Individuals with AI completed their work 16.4% faster, and teams with AI were 12.7% faster than their non-AI counterparts. At the same time, AI-enabled groups produced significantly longer and more detailed solutions, with higher average quality scores. ?? AI dissolves functional silos. Without AI, Commercial and R&D professionals proposed solutions aligned with their functional backgrounds—market-oriented vs. technical. With AI, this gap disappeared: both groups generated more balanced ideas, regardless of their original specialization. This pattern held across individuals and teams. ?? AI lifts less experienced employees to team-level performance. Employees whose core job did not include product development performed significantly worse in the control conditions. However, when these non-core employees worked with AI, their performance matched that of teams containing core-role employees. ?? AI improves emotional states during work. Participants using AI reported significantly higher increases in positive emotions—such as excitement, energy, and enthusiasm—and lower increases in negative emotions like anxiety and frustration. Individuals with AI experienced a 0.457 standard deviation increase in positive emotions, and AI-enabled teams saw an even larger 0.635 boost. ?? AI challenges traditional assumptions about team structures. The study found that individuals with AI performed as well as human teams without AI, while AI-enabled teams were significantly more likely to produce top-decile solutions. The authors conclude that this challenges long-standing assumptions about the necessity and structure of collaboration. They suggest organizations may need to rethink how they compose teams and allocate expertise in an AI-integrated environment.

Simulation Meta Prompting?is a great use for a reasoning or deep research model. I've been creating bots and was thinking about a template for this, but AI can do this with meta-prompting. Here is my sim meta prompt template (which I have added to my prompting page https://lnkd.in/gbKyakr6 ) I want to create a simulation to help my students [describe] learn about event/period A and historical controversy B where they play the role of C. Start by researching academic books, journals and sites and produce a list of historical, scholarly and source documents that can service as knowledge base for the game. Provide this list of citations and links so I can verify these sources. Also give me an outline that describes the game play (what students will do and learn). The game should take about D minutes to play and will take place in context E. Then write an?internal, developer-facing prompt that an AI chatbot can use to build the simulation. This prompt is not intended for student view but will guide the chatbot's behavior when simulating the game where they will get to assume the role of C. Here is a specific example for a Thomas Cromwell Game I want to create a simulation to help my second-year college students in an English history class learn more about Tudor England and the court politics of Henry VIII, where they play the role of Thomas Cromwell. The learning goals are to understand court politics and discover how Christian morality might or might not have guided potential actions in this historical period. Start by researching academic books, journals and sites and produce a list of historical, scholarly and source documents that can service as knowledge base for the game. Provide this list of citations and links so I can verify these sources. Also give me an outline that describes the game play (where students playing the role of Cromwell will win if they can avoid death but must also abide by contemporary morality). The game should take about 15 minutes to play and will used in a college classroom to serve as the basis for further discussion. Then write an?internal, developer-facing prompt that an AI chatbot can use to build the simulation. This prompt is not intended for student view but will guide the chatbot's behavior when simulating the game where students get to assume the role of?Cromwell, playing a game where the goal is to stay alive while still abiding by the rules, morality and etiquette of the time period. I copied the output and you can play the game here https://lnkd.in/giUB8hYQ France Q. Hoang ChatGPT reasoning gave me a good bibliography and a simple prompt. Claude provided a more sophisticated approach to the game by tracking three hidden metrics: Royal Favor (RF), Moral Standing (MS), and Noble Support (NS); Execution triggers if any metric falls below 30/100. "Victory" occurs if the player reaches 1540 with all metrics above threshold."

I spend every day talking about AI with professors, students, faculty, staff, family, and friends. It is all around me. But this weekend was different. I went to the Spring Arts Festival at Kennesaw State University. I saw the incredible power of art. Hand crafted. Sculpted. Watercolor, Oil on canvas. Chalk. Glass blown. Welded. Screen printed. Music. Mechanically engineered. Photographed. You name it. And nothing was AI generated. The irony is I was invited to this event because of the human connection made during one of my many talks about AI with a BoodleBox AI Campus Council member. Art will always be needed. Art will always draw emotion. Art will always connect. And being human will always be the number one skill any of us can bring to the table. Thank you Sean Amaso for the invitation, for reminding me and everyone of the beauty of the arts, human connection, and the place for AI. Connecting with students who desire to share and learn is the beauty of what we have in this world. While AI is here to transform, and at BoodleBox, it does incredibly well, the human in the mix is always a necessity. #HumanConnection #Arts #AIInEducation #BoodleBox