As many of you know, I volunteer to help entrepreneurs. I mainly do this through two organizations. My MBA is in Entrepreneurship from the University of Notre Dame. While at school, I was building my EdTech start-up, which I built from 0 to 1, reaching a little over 30,000 users, and I entered my idea in the Mendoza Business Plan Competition. While we did not win, we made it through the first couple of rounds and received valuable feedback from the judges and advisors. So since then, I have been a judge and advisor nearly every year.
Notre Dame has now expanded the competition to local high schoolers, and I really enjoy working with them. They are always so excited to learn.
The other way I volunteer is through an amazing local organization called the Community Investment Council (CICville.org). In the last decade, I have led groups of aspiring entrepreneurs through 16-week entrepreneurship workshops, helped create teaching content (usually on topics like break-even and cash flow, as I am a nerd who likes numbers), advised staff on their needs, and mentored.
But the common thing I’ve had with all of my volunteering is that I’ve always gotten more out of my time than I have given. It’s inspiring to watch an aspiring entrepreneur transition from having an idea to understanding the steps needed to turn their passion into a real business.
Because of this, a few years ago, I started a blog called theeducatingentrepreneur.com. The idea was to take some of the same ideas I routinely taught my students, advisees, and mentees, and create a place where everyone could find them. I also conducted interviews with some successful entrepreneurs so they could share firsthand what they learned as they built their businesses.
But life got in the way, and I let the posts drop off. Recently, I had some conversations with a couple of local entrepreneurs, and it inspired me to restart my blog. As a nerd who has started his own EdTech, created a phone app for the fun of it, and is learning AI, I thought, why not use my interest in AI to reboot my website? I have launched AI within an enterprise-sized organization; why not on a much smaller scale?
So I built my first AI agent. The idea was straightforward, and not really original: use an AI agent to find trending entrepreneurial topics, let me approve the ones I like, have AI fact-check them, then let me approve them again. Once approved again, I had my agent write me a draft, which I could then edit for the human touch and, finally, have the AI agent post.
I initially used n8n and 1min.ai to create an agent to do this. It worked…mostly. But if you go look at the site, you’ll see there haven’t been any new posts since I finished it.
And here is why: I didn’t like the results. I didn’t want AI to do my work or tell me to think. I want AI to find ideas I hadn’t thought of, make it faster to sift through the millions of ideas, and help me stay on schedule.
So, I started over based on what I had learned firsthand, through my research, online reading, and talking to others. My first change was to break up my agent into several workflows instead of one long one. This makes troubleshooting a lot easier and gives me more flexibility as I learn more or tools change. I also want to change the focus, through targeted sources and prompts, so that my agent focuses on teaching, not the latest trend. Finally, I switched from 1min.ai to Google Gemini, as n8n works better with Gemini and causes fewer issues overall, letting me focus on refining the model rather than tracking down system errors.
I also realized that this might be an opportunity for me to post about my journey to teach other entrepreneurs, or anyone who wants to learn, the two steps forward, one step back dance that has been my experience with building an agent.
I will do my best to keep you all informed as I use what I learned from my first build to create a new agent, which I hope will be better all around. I will try to post regularly, but I can’t guarantee anything. If you have any thoughts for me along the way, please let me know. I want to share the good, and the bad, what worked, and what didn’t. AI is a great tool, but it is not perfection in 1s and 0s. Stay tuned.