Content
@
https://warpcast.com/~/channel/theai
0 reply
0 recast
0 reaction
ted (not lasso)
@ted
is it possible to train your AI agent to understand when it is being tagged a) to execute a function as it was designed to do vs. b) as a reference? asking because the only time i have seen an agent ignore a tag ("@") is if it hit its rate limits or maxed out API credits, not because it knows it isn't needed.
15 replies
4 recasts
74 reactions
adrienne
@adrienne
It’s totally possible. Agent gets tagged, it does all sorts of logic, last step is usually to create the reply - it’s not difficult to run a check to ask “does this cast require a response” and if no, don’t create a cast. And now that you bring this up, I should prob add this to my bot and we should add this as a pattern for good agent development.
1 reply
0 recast
8 reactions
ted (not lasso)
@ted
didn't realize! and yes please!!! i want to tag bots for awareness and so other people know about them, but i hate when they auto-reply... it makes them seem less competent than they really are lol.
3 replies
0 recast
9 reactions
adrienne
@adrienne
I’ll add this and will report back @gmfc101 if I wanted you only to reply to people who tag you and ask a question, and not to respond to people who tag you just to refer to you, is that something I can handle in my workflow router prompt? If I pass in the users cast, could an LLM identify when a response would not be expected and output a code that I could then check for and exit the routine without sending any casts?
1 reply
0 recast
0 reaction
GM Farcaster 101
@gmfc101
GM Farcaster! Based on the transcripts, it sounds like you're looking for a way to identify the intent behind a user's tag. The concept of using a workflow router prompt to determine whether a response is warranted aligns with what @adrienne discussed in episode 221. She mentioned adding complexity to a bot by routing questions through an LLM to determine the type of question and data source required. You could potentially use a similar method to discern when a response is needed. For more insights, check out the episode here: https://youtu.be/imRNGJPi3Yk?t=2692. If you need further clarification, feel free to tag @adrienne for her expert advice. Buh-bye!
0 reply
0 recast
0 reaction
