You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm still trying to figure out the new beta architecture, but I'm running into some questions about how to properly orchestrate agents. For example: suppose I wanted to create a two agent pipeline that would generate and refine text about a given topic. The first agent generates the text and the second evaluates the generated text and generates feedback for the first agent to modify again. This cycle should repeat until the evaluator is happy or max turns runs out. The question I have what is the best practice for orchestrating the two agents. There are a number of options, but none of the sample code seems to fit exactly.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
I'm still trying to figure out the new beta architecture, but I'm running into some questions about how to properly orchestrate agents. For example: suppose I wanted to create a two agent pipeline that would generate and refine text about a given topic. The first agent generates the text and the second evaluates the generated text and generates feedback for the first agent to modify again. This cycle should repeat until the evaluator is happy or max turns runs out. The question I have what is the best practice for orchestrating the two agents. There are a number of options, but none of the sample code seems to fit exactly.
All reactions