Action execution¶
The execution
parameter in the act()
function allows you to adjust and fine-tune the Agentic Interface behavior. You can use this parameter to define:
Tasks the Agentic Interface must perform based on user queries
How the Agentic Interface must query data corpuses to retrieve information
How the Agentic Interface must formulate its responses
To modify the Agentic Interface’s behavior, add the act()
function to the dialog script. In the execution
parameter, specify the transform that provides instructions on how the Agentic Interface must act in specific situations.
act({
execution: transforms.act_execute
});
Example of use¶
Assume you are building an Agentic Interface that provides information on medications. When a user asks about medication usage, the Agentic Interface should recommend consulting a healthcare professional. To achieve this:
To the dialog script, add data corpuses that provide information about medications:
Dialog script¶corpus({ title: `Cleveland Clinic`, urls: [`https://my.clevelandclinic.org/health/treatments/penicillin`], depth: 1, maxPages: 1 }); corpus({ title: `Health Direct`, urls: [`https://www.healthdirect.gov.au/penicillin`], depth: 1, maxPages: 1 });
In the Debugging Chat, ask a question about medication usage and check the response.
Under Transforms, create the
act_execute
transform with the following instructions:Dialog script¶If a user asks about medications, give a general response and advise them to consult a healthcare professional for accurate and safe medical advice.
To the dialog script, add the
act()
function with theexecution
parameter:Dialog script¶act({ execution: transforms.act_execute });
In the Debugging Chat, ask a question about medication usage once again and check the response.
