# Settings

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

<table><thead><tr><th width="156">Properties</th><th width="441">Description</th></tr></thead><tbody><tr><td><strong>Connection</strong></td><td>Defines the AI connection used by the agent. This must be configured before the agent can execute. See <a href="../connections">Connections</a>.</td></tr><tr><td><strong>Model</strong></td><td>Defines the model family (e.g. GPT-4, GPT-4 mini). See <a href="model">Model</a></td></tr><tr><td></td><td></td></tr><tr><td><strong>Is Chat</strong></td><td>Enables chat-based interaction with the agent. When disabled, the agent only runs in execution mode.</td></tr><tr><td><strong>Verbosity</strong></td><td>Tells the model what level of detail the final response should have.</td></tr><tr><td><strong>Reasoning effort</strong></td><td>Tells the model how many effort should be applied to reasoning, higher levels generally mean longer requests and more tokens used.</td></tr><tr><td><strong>Image analysis</strong></td><td>Tells the model what level of detail to use when processing and understanding images.</td></tr><tr><td><strong>Max tool calls</strong></td><td>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.</td></tr><tr><td><strong>Max file size</strong></td><td>Sets the maximum combined size of files that will be handled in the request in MB.</td></tr><tr><td></td><td></td></tr><tr><td><strong>Enable history</strong></td><td>When enabled the agent will keep track of previous interactions. When set additional cleanup properties will be enabled. See <a href="history">History</a>.</td></tr></tbody></table>