Working on prompts for an AI agent feels like teaching a kid at times. For example, just told the bot it can decline engaging further if someone keeps pushing on something it doesn't want to do

Co-founder @bountycaster (bountycaster.xyz). Co-producer @ethereumfilm. Previously co-founder of Scalar Capital and product at Coinbase

bringing memes to retail @bolide | shitcoins trader | passionate about UX 👩‍💻 

@pirosb3 did all the heavy lifting getting it set up but I find prompts to be pretty straightfoward since just like talking to it and I use gpt regularly

was it hard for you to understand how prompts work?

Strat/art/design. Thoughts: /user-steen Director: /enjoy Guild: /metaliminal Zora: zora.co/@usersteen

You might enjoy this vid: https://youtu.be/T9aRN5JkmL8?si=mQB5fgVfHe_ngesn

confirmed that I just had this conversation with my 4 year old last week.

the best part of the agent frameworks is this is all done with natural language. it literally feels like teaching a kid. and it also means non-technical people can help you teach your kid too!

user feedback: "i wish the agent responded to me when I did X"
update prompt: "respond to people when they do X"

lol i see many are trying to get bounty to deploy clanker tokens

Not gonna lie, agent dev is one of the most mind-blowing things I've ever worked on in my entire life for this very reason

I feel like I'm learning just as much as much as my bot is - maybe more