The past eight months at TrueHorizon AI have been a wild ride. We came out of the gates hot, closing 10 deals in a matter of weeks, only to find ourselves drowning in work and missing deadlines shortly after. Two months later, we made the tough call to shut our doors temporarily so we could fix our internal systems before taking on any new discovery calls. Looking back, I’m actually grateful for those couple of months of chaos. The stress, sleepless nights, and constant pressure forced us to grow. We came out of it with a stronger mindset and a deeper appreciation for good systems, good processes, and good people. In this podcast, my co-founders and I sat down for an hour and a half to reflect on the journey so far. Some moments are lighthearted, others carry real lessons, and throughout we share both the wins and the failures that shaped us. My hope is that you’ll be able to take away some nuggets that help you avoid the same mistakes. Give it a listen, and let me know what you think. Cheers, Nate

i've been using a free llm model (nvidia/nemotron-nano-9b-v2:free) when using openRouter that is decent for training. You can also use it for any project you want but you might need to give him some specific prompt. Just as an example it took me a few tries to prompt for the agent in this simple workflow to get him to talk with the database but now it is working fine. Have fun learning