This article outlines the configuration setup and usage of the Agent AI Assist feature. This feature allows for the creation of generated responses utililizing a custom Chat GPT bot. This allows agents to generate responses based on guest input mid-chat and referencing of knowledge base content (FAQs) for streamlined responses.

Configuration

To configure this feature configuration page navigate from the Admin menu to Chime Settings > Agent AI Chat Assist. This is were custom Chat GPT bot parameters can be set as well as cognitive search (the searching of indexed FAQ content).

Parameters

• System Message Prompt - This will instruct the AI about how it should respond to the user.
• Number of Previous Messages to Include - Number of previous messages to send as context for the AI to use in its response.

Advanced Settings

• Choice Count - Number of alternates responses to return for a prompt
• Max Tokens - Maximum number of tokens to generate in the response
• Temperature - Sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic
• Top P - Controls randomness of response. Lower values are more deterministic.
• Frequency Penalty - Controls repetition in response. Positive values will make tokens less likely to appear as their frequency increases and decrease the model's likelihood of repeating the same statements verbatim.
• Precense Penalty - Controls repetition in response. Positive values will make tokens less likely to appear when they already exist and increase the model's likelihood to output new topics.

Knowledge Base Search Extension Settings - Options for Knowledge Base Integration

• Use Cognitive Search - Allow chatbot to access indexed knowledge base resources (FAQs, etc) to enrich responses
• Restrict Bot Responses to Knowledge Base - When enabled, the chatbot will only suggest responses based on information recovered from knowledge base resources (FAQs, etc). If it cannot find any relevant resources, it will inform the user. When disabled, the chatbot will suggest responses based on information recovered from knowledge base resources (FAQs, etc) but can also respond using data from its base model if no relevant information is found. NOTE: Information generated may not always be correct.
• Strictness - Strictness controls how closely the chatbot will match searched documents to the user's query. Raising the value means a higher threshold for relevance and filters out less-relevant documents for responses. Setting this value too high might cause the model to fail to generate responses due to limited available documents.
• Maximum Retrieved Documents - The maximum number of top-scoring documents to provide the chatbot as background to generate a response. Increasing this value may improve the quality of responses if there are many short documents in the knowledge base.
• Search Query Type - Users can choose between 'Simple' and 'Semantic' search query types.
• FAQ Citation Link Options - Users can opt to display cited documents as footnotes, where URLs are included at the end of the message, inline within the response, or choose not to link the source documents at all.

Agent Experience

1. As an Agent, upon connecting to a chat navigate to the 'AI Assist' tab of the agent context window
2. Select the 'Suggest Response' button to prompt the Chat GPT bot to create a response or multiple responses
3. After the responses are generated, the agent has the ability to edit them before sending. If multiple responses are generated the agent can pick which one answers the query best or has the most accurate reference content

Guest Experience

On the Guest side the AI Assist response will match the settings that were configured on the Admin menu (maximum retrieved documents, FAQ citation link options, etc.) which will change how it is displayed.