Settings

Depending on the selected model, additional configuration options may be available.

Properties	Description	Supported Models
Connection	Defines the AI connection used by the agent. This must be configured before the agent can execute.	GPT-4, GPT-5 and Transcription
Model	Defines the model family (e.g. GPT-4, GPT-4 mini).	GPT-4, GPT-5 and Transcription
Is Chat	Enables chat-based interaction with the agent. When disabled, the agent only runs in execution mode.	GPT-4, GPT-5
Temperature	Controls response randomness. Lower values produce more deterministic results.	GPT-4
Verbosity	Tells the model what level of detail the final response should have.	GPT-5
Reasoning effort	Tells the model how many effort should be applied to reasoning, higher levels generally mean longer requests and more tokens used.	GPT-5
Image analysis	Tells the model what level of detail to use when processing and understanding images.	GPT-4, GPT-5
Max Tool calls	The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool.	GPT-4, GPT-5
Max file size	Sets the maximum combined size of files that will be handled in the request in MB.	GPT-4, GPT-5 and Transciption
Enable history	When enabled the agent will keep track of previous interactions. When set additional cleanup properties will be enabled.	GPT-4, GPT-5
Max Tool Size	Limits the size of tool input and output payloads.	GPT-4, GPT-5