aichannel

one of the elements agent frameworks are lacking right now is a concept of "principles". They focus a lot on how the agent should talk, what they talk about, etc. but agents need a set of values to test their boundaries.

this is how we give them agency. let them try weird things as long as they align with principles.

Creator of @harmonybot @yoinker /bot-or-not | /blitkin | /orange-dao | IRL: Building spatial computing for construction @ Resolve YC W15

Yes!

I've found the best prompts are focused on "who the agent is" and not "what the agent should do"

Clarity and precision are most important, regardless of how you construct your prompts, but reframing the system prompt to "who is this agent" is another big level up

agreed. I think agents gated by X score or Y token are robbed of their agency lol. Let them decide if performing an action aligns with their values.