Advanced Agent Settings

This document provides an overview of configuring Agent settings in HALO. Customising these settings allows you to tailor Agents to meet specific operational needs effectively.

Advanced Agent Settings

Next to the general Agent Name and Behaviour description, some advanced settings for your Agent are also available for you. These Advanced Agent Settings are powerful options to optimise how you want your Agent to function.

To begin, select the Agent you wish to configure and click on "Settings" in the lower bar. This menu provides various options for customising the Agent's functionality.

The following is the list of Advanced Agent Settings:

Handover Only

Turning on this setting means the current Agent can only handover the conversation to other Agents, and cannot respond to user queries directly. This functionality is powerful if you have a Multi-Agent system, where you have different Agents for different purposes, and you want to decide which Agent to use the start of a conversation.

Creating a Root Agent that describes the conditions under which it should handover to the different Agents, and setting this Agent to Handover Only is a powerful way to ensure this Agent handles the first routing of the conversation, while making sure it doesn’t unnecessarily interact with the user.

Available in MSC

Toggling this setting enables you to configure whether you want this Agent to be available to be directly selectable from within Mobile Service Cloud.

Turning off the “Available in MSC” setting for a specific Agent only means that the specific Agent cannot be called directly from within Mobile Service Cloud. If another Agent decides to handover to this specific Agent, the Agent will still handle the query, even if it turned off in this setting.

Custom Guardrails

Guardrails are mechanism around HALO that make sure the output of HALO is consistent, correct and safe. Several of these guardrails are in HALO by default, but Custom Guardrails are settings that allow you set Custom Guardrails. In this setting, you can write out specific rules for how the Agent can handle specific user inputs. Note that your Custom Guardrail prompt is always performed before the process you have described in your Agent Behaviour.

There are three commands you can configure within custom guardrails:

Stop allows you to write out the conditions under which the current Agent should not handle the user query. When an input is classified as Stop, the Agent will not try to answer the query, but rather the Fallback Answer will be generated immediately. The stop functionality should always be configured together with the Continue functionality:

Continue allows you to configure the conditions under which the current Agent should continue with its process and handle the user query regularly. Note that this is the exact opposite of the Stop functionality.

An example of how to properly configure Stop/Continue Custom Guardrails can be the following: “If the request is about Medical Advice, stop . In all other cases, continue”. This will make sure requests about Medical Advice will not be answered, while all other requests will be answered.

Rewrite allows you to rewrite the input that gets send to the Agent under specific rules. It allows you to optionally provide different input to the Agent, so the Agent itself can focus on its core functionalities.

Apply Answer Style

You can toggle whether you want Answer Style to be enabled for when this Agent answers. Answer Style handles two tasks for rewriting the answer HALO gives: it applies the Tone of Voice you have configured under Style and translates the HALO answer using the detected language. Note that this Answer Style prompt is always carried out to rewrite the answer the Agent has given. It is therefore always applied after the Agent prompt.

Apply Feedback

You can toggle whether you want Feedback to be applied to the answers your Agent gives using the Feedback Mechanism. Feedback can be given when reviewing a specific conversation. Note that if relevant Feedback is found, it is always applied as the very last step in HALO, even after Answer Style.

Anonymise PII

This setting allows you to toggle whether you want Personally Identifiable Information (PII) to be anonymised or not. By default it is turned on, which means any information that can be connected to an actual person is anonymised. But there may be reasons you do not want data to be anonymised, for example if you want let an Agent be able to handle and reason over phone numbers.

Creativity Settings

The creativity settings allow you to control how your Agent generates responses. These settings work together to balance creativity, predictability, and focus in your Agent's outputs.

The Creativity Slider adjusts the overall response style of your Agent. Moving this slider also automatically adjusts the Temperature and Top P values to create different response profiles:

Lower settings: More focused, consistent responses

Middle settings: Balanced approach

Higher settings: More creative, varied responses

You can also manually adjust the Temperature and Top P settings individually, this implies a "Custom" creativity setting to indicate you've created your own unique configuration.

Temperature controls how random or predictable responses are - lower values make responses more consistent, higher values introduce more variety. Top P determines how focused the responses are - lower values make the Agent stick to the most likely options, higher values allow for more exploration of different possibilities.

E-learning Video

For further guidance, watch our e-learning video on Agent Settings in HALO.