HaloPSA Guides
Documentation to assist with the setup and configuration of the HaloPSA platform
AI
Setup
| Field | Type | Description |
Default AI Connection | Radio List | This determines which AI connection is used. You will need to enter credentials if using Azure/Own OpenAI. (On premise customers will not have the option to use the 'Default Halo Connection'). |
AI Ticket Matching
| Field | Type | Description |
Create Embedding Scores for Tickets | Checkbox | When checked, this will create an embedding score, providing a numerical value to demonstrate how similar this ticket is to existing/previous tickets. This score can be used for AI suggestions against tickets, suggesting field values/solutions based on previous tickets. Once enabled this will create an embedding score for all new ticket made. |
Ticket matching and AI insights method | Single Select | This determines what ticket matching and AI insights are based on. The integration runbooks option allows for more customisation but it is not advised unless you already have an extensive knowledge of runbooks. |
Vector search database | Radio List | This determines the database used when vector search takes place for ticket matching. The search process involves comparing the embedding scores of the tickets, but the similarity of the scores will differ based on the database used. If using the Azure AI Search (recommended) option you will need to enter your Azure credentials. |
AI Embedding Field | Single Select | This determines what ticket field the embedding score is based on, this field will be passed to the AI integration. This field must be present on ticket types you would like AI ticket matching to take place on. |
Ticket Types with AI embeddings and insights enabled | Multi-Select | This determines which ticket types AI insights and embeddings can be used on. |
Determine whether a Ticket is indexed based on Ticket rules | Checkbox | When checked, ticket rules can be used to control which tickets are indexed (new tickets only). Ticket rules will have a new outcome option 'indexable', only tickets that match the criteria of a rule that has this outcome will be indexed. |
Minimum vector match score (Tickets) | Integer | This determines what the minimum vector score between two tickets must be in order for them to 'match'. A higher vector score indicates greater similarity between the tickets. |
| Ticket types that link AI matched Tickets | Multi-Select | (v2.192.1+) This determines which ticket types will automatically link AI matched tickets as either child or related tickets. |
| Method of linking AI matched Tickets | Single Select | (v2.192.1+) This determines whether the ticket types set above will have the AI matched tickets linked as either child tickets or related tickets. |
| Enable AI Search by default on search screens | Single Select | (v2.195+) When enabled, all search screens will use AI search by default. AI search can still be disabled manually against each screen upon search. |
Configure AI suggestions | Button | Here, you can configure what AI suggestions can be made such as priority/category suggestions. |
AI suggestion notification | Single Select | Here you can determine if a notification displays when an AI suggestion is available, and if so, what type of notification. |
Additional filters for ticket indexing | Table | Here, you can add criteria that tickets must meet in order to be indexed. This only applies when indexing historical/existing ticket data, only tickets that meet the criteria here (along with ticket type criteria) will be indexed. |
Index Tickets | Button | Here, you can schedule tickets to be indexed. Indexing tickets will re-generate embedding scores for tickets already in the system. It is recommended this is completed when first enabling embedding scores as this will improve initial matching. It is also recommended to do this after changing the matching method, vector database or embedding field used. |
AI Knowledge Search
| Field | Type | Description |
Vector search database | Radio List | This determines the database used when vector search takes place for AI knowledge search. The search process involves comparing the embedding scores of the tickets, but the similarity of the scores will differ based on the database used. functionality is only available using 'Azure AI Search' database, for this you will need to enter your Azure credentials. |
Chunk Size | Button | This determines the chunk size that is searched. |
Chunk Overlap | Button | This determines the overlap of chunk size that is searched. |
Minimum vector match score (Knowledge) | Button | This determines what the minimum vector score between an article and the search prompt must be in order for the article to be returned in the search. A higher vector score indicates greater similarity between the search prompt and the article. |
Enable AI Article Suggestions | Checkbox | When checked, AI will create a search term when a ticket is logged (based on the ticket information) which will search indexed knowledge base articles. A vector search will be performed and closest matches (based on minimum vector match score) are recorded and are shown in the Problem/Resolution finder on the ticket details screen. |
Restrict which Articles can be indexed based on their FAQ List | Checkbox | When checked, you will be able to restrict which articles can be indexed based on their FAQ list. An additional option will appear against each FAQ list to determine if articles in this FAQ list can be indexed. |
Index Articles | Button | Here, you can schedule articles to be indexed. Indexing articles will re-generate embedding scores for articles already in the system. It is recommended this is completed when first enabling article suggestions/knowledge search. |
Index Service Catalogue | Button | Here, you can schedule services in the service catalogue to be indexed. Indexing services will re-generate embedding scores for services already in the system. It is recommended this is completed when first enabling article suggestions/knowledge search. |
AI Insights
| Field | Type | Description |
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 | Button | 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. |
Conversation AI Insights Data | Free text | Here, you can specify what ticket data is summarised by the AI, here you will need to enter $-variables. using the variable $-ALLACTIONS will result in all actions on the ticket being summarised, but different variables can be used to limit what actions are summarised, e.g. $ACTIONLISTPRIVATE will only summarise private actions. |
Knowledge Creation
| Field | Type | Description |
Create knowledge base articles using AI | Checkbox | When checked, knowledge base articles can be created using AI. A Runbook will need to be configured in order to do this. AI will process the correspondence between the user and the agent of the ticket and creates a description and resolution for the article and then either directly creates the article or creates an article draft ticket, depending on your Halo settings. The runbook to complete this process will need to be triggered using an action or an automation on a workflow. (The runbook can be customised to have another event trigger article creation e.g. ticket closed). |
Knowledge Base Runbook | Button | Here, you can configure the runbook to create knowledge base articles. |
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. |
Sentiment Analysis Runbook | Button | Here, you can configure the runbook to run sentiment analysis. |
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. |
Surveys
| Field | Type | Description |
Use AI to survey User satisfaction | Checkbox | 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 | This determines the percentage of tickets that are surveyed. |
Actions
| Field | Type | Description |
Action Config | Button | This takes you to the actions configuration page. AI can be used to write an automatic reply on an actions/improve a reply. |
Virtual Agent
| Field | Type | Description |
Chat Profiles | Button | Takes you to the chat profiles configuration page. |
Virtual Agents | Button | Takes you to the configuration page for AI virtual agent chatbots. |
Custom Integrations
| Field | Type | Description |
Custom Integrations | Button | Takes you to the custom integrations page. |
OpenAI Methods | Button | Takes you to the runbook configuration page for the Azure OpenAI runbooks. |
Logs
| Field | Type | Description |
Open AI | Button | Shows the request/response logs for calls made to OpenAI. |
Azure Open AI | Button | Shows the request/response logs for calls made to Azure OpenAI. |
Azure AI Search | Button | Shows the request/response logs for Azure AI Searches. |
Popular Guides
- Asset Import - CSV/XLS/Spreadsheet Method
- Call Management
- Creating a New Application for API Connections
- Creating Agents and Editing Agent Details
- Departments and Teams
- Halo Integrator
- Importing Data
- Multiple New Portals with different branding for one customer [Hosted]
- NHServer Deprecation User Guide
- Organisation Basics
- Organising Teams of Agents
- Step-by-Step Configuration Walk Through
