AI Feature Library Settings
Configuration > AI > Feature Library
This configuration area contains various features that use the generative AI connection (not embeddings).
Runbook Features
| Field | Type | Description |
Integration Runbooks | Button | Click here to create/view integration runbooks, these can be used to trigger an AI Ability or Process Agent and process the response given. |
| AI Abilities | Button | Click here to configure/view AI Abilities. An AI Ability allows you to configure a prompt to be sent to an AI model to instruct AI to evaluate the data provided and generate a response. |
| Process Agents | Button | Click here to configure/view Process Agents. Process Agents allow you to send a custom set of instructions to an AI model to generate a response and perform certain tasks. The AI Agent can execute requests in your own instance via the API, such as adding actions to tickets. |
| OpenAI Methods | Button | Only applicable when using the Azure OpenAI or OpenAI connection. Click here to configure new custom integration methods for the Azure OpenAI integration. This allows you to send custom requests to Azure OpenAI endpoints (deployments). |
AI Insights
| Field | Type | Description |
Enable AI insights | Checkbox | Only available to edit when embeddings are disabled. - Checking this with Louis If embeddings are enabled this setting will be locked on as embeddings rely on insights (regardless of the "AI Embedding Field" you are using). If embeddings are disabled you can use this setting to enable/disable AI insights. AI Insights use AI to give further insights into the ticket, such as customer tonality, summarise the Ticket conversation, create a search term and suggest a priority. For more information see our guide here. |
AI Insights Context | Free Text | Here you can give the AI model the context in which it is working, this improves the accuracy of the insights it returns. |
| AI Insights Field | Single Select | This determines the ticket field AI insights are based on, data from this field will be sent to the AI integration to run the evaluation. You can either use the 'Details' ticket field or customise what fields this is based on using $- variables. If customising with $-variables a free text box will appear next to this setting, here you can enter the $-variables for the fields you would like the insights to be based on. |
| Allow AI Insights to summarise the conversation | Checkbox | When checked, AI insights will be able to provide a summary of the conversation on the ticket. Once enabled you will be able to specify what ticket data is sent to the AI integration for it to summarise using $-variables. |
| Enable AI suggestions for Category values | Checkbox | When enabled AI insights will suggest a category separately from suggestions based on matched Tickets. When the "AI Suggested Category" Field is added a Ticket Type, a Category can populate when insights are run. |
| Category field for AI suggestions | Single Select | Only applicable when "Enable AI suggestions for Category values" is enabled. Here, choose which Category Field AI suggestions are generated for. |
Knowledge Base
| Field | Type | Description |
Generate an AI summary of knowledge base Articles | Checkbox | When enabled, AI will be used in to generate summaries of articles in your Knowledge Base. Useful for providing Agents a concise summary of content, helping them identify the article they need. For more information on this checkout our guide here. |
| Create knowledge base articles using AI | Checkbox | When enabled, you can create knowledge base articles using AI based on ticket content. For more information on this checkout our guide here. |
Actions
| Field | Type | Description |
Action Config | Button | Click here to configure/view Actions. AI can be used to write an automatic reply on an actions/improve a reply. For more information on this checkout our guide here. |
Sentiment Analysis
| Field | Type | Description |
Use AI to detect the emotions of a User's messages | Checkbox | When checked, sentiment analysis can be used to provide a sentiment analysis of the ticket and a user satisfaction rating. The runbook will need to be triggered (using an action/workflow automation) the AI will analyse user correspondence and populate 'AI Sentiment analysis' and 'AI Satisfaction level' fields. These fields must be on the ticket type. For more information on sentiment analysis checkout our guide here. |
| Sentiment Analysis Runbook | Button | Here, you can configure the runbook to run sentiment analysis. |
Customer Profiling
| Field | Type | Description |
Enable AI Customer profiling analysis | Button | When enabled, AI can be used to analyse a customer's recent ticket information to formulate a summary of their recent experience. This summary will then be uploaded to the customer's profile as a CRM note. Allowing you to automate the monitoring of your clients' experience using your services. For more information on this checkout our guide here. |
| Evaluation frequency | Single Select | Only available when "Enable AI Customer profiling analysis" is enabled. Here choose how often you would like AI customer profiling to take place, the frequency at which AI analyses customers' ticket information. |
| Evaluation prompt | Free Text | Only available when "Enable AI Customer profiling analysis" is enabled. Here, set the prompt that is sent to AI to instruct it how to evaluate a customer's ticket data and provide a summary of the customer's experience. A default prompt is provided but customise this to fit your business needs/context. |
Surveys
| Field | Type | Description |
Use AI to survey User satisfaction | Button | When enabled AI will analyse the ticket, giving a user satisfaction score an a justification for why it has given this score. This information can be populated in the 'AI satisfaction level' and 'Satisfaction Comment' ticket fields, these fields must be added to the ticket type. This survey runs when the ticket is closed. |
| Percentage of Tickets to Survey | Integer | Only available when "Use AI to survey User satisfaction" is enabled. This determines the percentage of tickets that are surveyed. |
| Don't create negative feedback Tickets from AI surveys | Checkbox | (v2.250+) When enabled, negative feedback from AI Surveys will not create a Ticket. This setting will only be available if a Ticket Type has been selected in the "Ticket Type for Negative Feedback" field in Configuration > Tickets > Surveys. |
Thank You Detection
| Field | Type | Description |
Enable AI 'Thank you' email detection on closed/pending closure Tickets | Checkbox | When checked, AI will check incoming emails to a closed/pending closure ticket, if the incoming email is determined to just be the user thanking the agent (no further action needed) the email will not update the ticket. If the incoming email is determined to be more than the user thanking the agent the email will update the ticket. For more information checkout our guide here. |
Statement of Work
| Field | Type | Description |
Custom Field to Extract Statement of Work | Single Select | This determines which field on an opportunity (ticket) contains your statement of work and is used to generate project tasks for you when a project is created off the back of a sales order linked to this opportunity. Allowing you to use AI to generate project tasks for you based on your statement of work for a project. Only rich text custom fields will show here as the statement of work must be formatted using bullet points for generation to be successful. |
Reporting
| Field | Type | Description |
Enable AI Report Analysis | Checkbox | When enabled, you will have an option against each of your reports to have AI analyse the data returned by the report and provide a summary of this. For more information on this checkout our guide here. |
| Max Data Size (KB) | Integer | Only available when "Enable AI Report Analysis" is enabled. This controls the maximum amount of report data AI can analyse, used to mitigate the amount of tokens used when analysing report data. Report rows will be truncated from the Report data until the data size is less than this value. By default, it will be set to the maximum, 1000KB, but this can be lowered if you wish. |