What's actually hard once you get past the tutorial is the tool schema, not the agent loop. Every weird model call traces back to a description that made sense to me and not to the model. I now write tool descriptions the way I'd explain the tool to a new hire who can't ask follow-up questions.
Bookmarking this! Transitioning from basic prompting to building structured, autonomous features is the exact technical hurdle I'm working through right now.
Esse tipo de conteúdo sempre pula a parte chata: o que fazer quando o agente trava esperando uma resposta que nunca vem. Vale um capítulo só pra tratamento de erro.
Quick thought, since managing the agents becomes your actual work in the future because something will break, are the use cases strong enough to justify the fixing that agents require?
I am saying is building agents saving enough time or is that saved time going into debugging and fixing agents.
Cause currently i cant seem to find good use-cases of ai agents in my company, but i wanted to know if agents are worth trying. I run a Cookware brand.
Very interesting article. I'm actually in the middle of building my own AI agent as well, so a lot of the points you mentioned really resonated with me. Thanks for sharing your experience and lessons learned. Best regards!
Jarvis has always been my fantasy. (Still is) Drive connector went haywire for me. initially I should have payed attention. Nope 3 weeks kicked my ass.
What's actually hard once you get past the tutorial is the tool schema, not the agent loop. Every weird model call traces back to a description that made sense to me and not to the model. I now write tool descriptions the way I'd explain the tool to a new hire who can't ask follow-up questions.
This is a great walk-through. Thank you for this and your thoughts behind building agents. Seriously keep up the great work.
Thank you :)
Bookmarking this! Transitioning from basic prompting to building structured, autonomous features is the exact technical hurdle I'm working through right now.
Thx! Good luck!
Esse tipo de conteúdo sempre pula a parte chata: o que fazer quando o agente trava esperando uma resposta que nunca vem. Vale um capítulo só pra tratamento de erro.
Building Agent is easy but Building useful that actually work is the main factor.
100% true. You can build an Agent that sends you “hi” on iMessage quick. The trick is to make is do something more useful(and complex).
Yeah, you’ll see this is happening very soon but its not easy for every one to build the agent.
Quick thought, since managing the agents becomes your actual work in the future because something will break, are the use cases strong enough to justify the fixing that agents require?
I am saying is building agents saving enough time or is that saved time going into debugging and fixing agents.
Cause currently i cant seem to find good use-cases of ai agents in my company, but i wanted to know if agents are worth trying. I run a Cookware brand.
You mean - let’s thow away broken one and exchange!
Very interesting article. I'm actually in the middle of building my own AI agent as well, so a lot of the points you mentioned really resonated with me. Thanks for sharing your experience and lessons learned. Best regards!
Thanks for comment! Happy building!
Wow this guy writes awesome
Hah, thanks for that! I have to take time to write v2 :D
Bueno
AI agents are going to become as common as websites. The real advantage won't be building one it'll be knowing where they create the most leverage.
I heart you, man!
Jarvis has always been my fantasy. (Still is) Drive connector went haywire for me. initially I should have payed attention. Nope 3 weeks kicked my ass.
Popculture had broken us all xD
Just don’t feed the BOWKYs personal info.
Just found this today. New follower 😊 Provided a ton of clarity!
Thank you! Sorry for such late reply, but my humble substack growth is crazy past 2 months :D
Thanks for your guide
I'm a beginner and this helps me to understand what to do and don't
i wish i get to know about this earlier 😭
Thank you for putting in the effort to make this actually helpful.
Thanks for comment - I was trying my best!
Thanks a lot!