Discussion about the "Human input and execution" implementation

CrewAI Community Support
, , , ,
1

There is a very big issue with the “Human Input and Execution” implementation. overall implementation is fine the problem is that with this that it ask for the human feedback that is totally annoying part of it.

=====                                                                                                                                                                 
## HUMAN FEEDBACK: Provide feedback on the Final Result and Agent's actions.                                                                                          
Please follow these guidelines:                                                                                                                                       
 - If you are happy with the result, simply hit Enter without typing anything.                                                                                        
 - Otherwise, provide specific improvement requests.                                                                                                                  
 - You can provide multiple rounds of feedback until satisfied.                                                                                                       
=====

This is the log that I’ve mentioned above.
I don’t want it in my Human interaction implementation because it creating a in appropriate behaviour.

2

so the guiding instructions is the annoying part if am understanding correctly?

if yes, that should be an easy fix on our end.

also, what would you like for it to say instead?

3

Yes, I’m agree with the annoying part that it is very annoying because it is breaking my flow.

let me explain you on what approach I’m working on.
basically we are working on collector agent that collect input field’s values on the basis of given form fields schema by asking question for the fields one by one.

So everything is sort with the “Human input and execution implementation” that collecting input very well from the user input, but there is a catch in the mid of collecting values that it is giving unwanted assumption with it’s own even after defining in the agent’s backstory or task’s description and also it is giving that HUMAN FEEDBACK MESSAGE suggestions that i don’t want in my flow of collecting values for the form fields.

let me clear one more thing that we are marking true human input key in the TASK that I’m defining “human_input=True”, that making our work easy but with the HUMAN FEEDBACK MESSAGE catch.

I’ll be very greatfull if this problem can be resolved by the Crewai Team.