Hi,
I was reading the Agent Studio documentation to understand how do we configure the output response of a particular plugin. Here’s what was mentioned:
Adding plugin result instructions clarifies how the AI Assistant should respond to users at the end of your plugin execution.
- (Recommended) By adding instructions as a key-value pair in your workflow's output mapper (e.g.
display_instructions_for_model: <YOUR-CUSTOM-INSTRUCTION-HERE>)
What is meant by “workflow’s output mapper” ? Where do I access it?
Do I have to create a data type? Or did it mean “Output Mapping” section in a conversational process? But then the given example throws DSL error.
Appreciate any help with this.
Thank you.