<style>p { margin: 0; }span.fr-emoticon.fr-emoticon-img { background-repeat: no-repeat !important; font-size: inherit; height: 1em; width: 1em; min-height: 20px; min-width: 20px; display: inline-block; margin: -0.1em 0.1em 0.1em; line-height: 1; vertical-align: middle; } span.fr-emoticon { font-weight: normal; font-family: "Apple Color Emoji", "Segoe UI Emoji", "NotoColorEmoji", "Segoe UI Symbol", "Android Emoji", "EmojiSymbols"; display: inline; line-height: 0; } blockquote { border-left: solid 2px #5e35b1; color: #5e35b1; margin-left:0; padding-left:5px;}blockquote blockquote{ border-color: #00bcd4; color: #00bcd4;}blockquote blockquote blockquote{ border-color: #43a047; color: #43a047;} table.grid{ border-collapse: collapse;} table.grid td, table.grid th { border: 1px solid #ddd;} .fr-fic.fr-dib{ display: block; margin: 5px auto;}.fr-fic.fr-dib.fr-fir{ text-align: right; margin: 5px 0 5px auto;}.fr-fic.fr-dib.fr-fil{ text-align: left; margin: 5px auto 5px 0;}.fr-fic.fr-dii{ float: none; margin: 5px auto;}.fr-fic.fr-dii.fr-fil{ float: left; margin: 5px auto;}.fr-fic.fr-dii.fr-fir{ float: right; margin: 5px auto;}img.fr-dib.fr-fir { margin-right: 0; text-align: right;}img.fr-dib.fr-fil { margin-left: 0; text-align: left;}img.fr-dib { margin: 5px auto; display: block; float: none;}img.fr-bordered { box-sizing: content-box; border: solid 5px #CCC;}img.fr-shadow { box-shadow: 10px 10px 5px 0px #cccccc;}img.fr-rounded { border-radius: 10px; -moz-border-radius: 10px; -webkit-border-radius: 10px; -moz-background-clip: padding; -webkit-background-clip: padding-box; background-clip: padding-box;}</style><style>
p {
margin: 0;
}
span.fr-emoticon.fr-emoticon-img {
background-repeat: no-repeat !important; font-size: inherit; height: 1em; width: 1em; min-height: 20px; min-width: 20px; display: inline-block; margin: -0.1em 0.1em 0.1em; line-height: 1; vertical-align: middle;
}
span.fr-emoticon {
font-weight: normal; font-family: "Apple Color Emoji", "Segoe UI Emoji", "NotoColorEmoji", "Segoe UI Symbol", "Android Emoji", "EmojiSymbols"; display: inline; line-height: 0;
}
blockquote {
border-left: solid 2px #5e35b1; color: #5e35b1; margin-left: 0; padding-left: 5px;
}
blockquote blockquote {
border-color: #00bcd4; color: #00bcd4;
}
blockquote blockquote blockquote {
border-color: #43a047; color: #43a047;
}
table.grid {
border-collapse: collapse;
}
table.grid td,
table.grid th {
border: 1px solid #ddd;
}
.fr-fic.fr-dib {
display: block; margin: 5px auto;
}
.fr-fic.fr-dib.fr-fir {
text-align: right; margin: 5px 0 5px auto;
}
.fr-fic.fr-dib.fr-fil {
text-align: left; margin: 5px auto 5px 0;
}
.fr-fic.fr-dii {
float: none; margin: 5px auto;
}
.fr-fic.fr-dii.fr-fil {
float: left; margin: 5px auto;
}
.fr-fic.fr-dii.fr-fir {
float: right; margin: 5px auto;
}
img.fr-dib.fr-fir {
margin-right: 0; text-align: right;
}
img.fr-dib.fr-fil {
margin-left: 0; text-align: left;
}
img.fr-dib {
margin: 5px auto; display: block; float: none;
}
img.fr-bordered {
box-sizing: content-box; border: solid 5px #CCC;
}
img.fr-shadow {
box-shadow: 10px 10px 5px 0px #cccccc;
}
img.fr-rounded {
border-radius: 10px; -moz-border-radius: 10px; -webkit-border-radius: 10px; -moz-background-clip: padding; -webkit-background-clip: padding-box; background-clip: padding-box;
}
</style><p><strong>In this guide we will cover:</strong></p><p><strong>- Ticket matching</strong></p><p><strong>- AI Ticket suggestions </strong></p><p><strong>- AI Article suggestions</strong></p><p><br></p><p><br></p><p>Before configuring AI functionality ensure you have first configured your AI connection, see our guide on how to do this <a data-fr-linked="true" href="https://usehalo.com/haloitsm/guides/2385" id="isPasted" target="_blank" rel="noopener noreferrer"><strong>here</strong></a>.</p><p><br></p><p>AI can be used to match a ticket to an existing ticket in your database and suggest values that should be applied to your current ticket based on historical ticket data. 'Matched tickets' allow you to see tickets that share similar properties to the current ticket, this can aid problem, incident and change management as it increases visibility of similar tickets to agents. For example, if a problem occurs as a result of a change made all, AI will detect the similarity of the issues and 'match' the incidents to the associated problem ticket. </p><p><br></p><p>Ticket suggestions can be used to automate ticket processing by making suggestions to agents on how certain ticket fields should be completed based on historically similar tickets. In this guide we will cover how to configure AI ticket matching and suggestions, and what these can be used for. </p><p><br></p><p>If you would like to use the ticket suggestions functionality without the use of AI check out <a data-fr-linked="true" href="https://usehalo.com/haloitsm/guides/2544/" id="isPasted" target="_blank" rel="noopener noreferrer">Ticket Suggestions- without the use of AI</a>.</p><p><br></p><p><strong><span style="font-size: 14pt;">Ticket Matching</span></strong></p><p>Before AI suggestions can be made ticket matching must first be configured so embeddings and embedding scores are created for ticket data. Tickets will be 'scored' on similarity and will then be assigned a numerical value (embedding score) based on how similar they are, the more similar two tickets are the higher the score will be. </p><p><br></p><p>Embedding scores are required to allow suggestions to be made, as suggestions will be given based on data from tickets that have a high embedding score with the new ticket. That is, if two tickets have a high embedding score suggestions will be made on the new ticket using data against the old ticket.</p><p><br></p><p>To set up ticket matching head to configuration > AI > ticket matching section. Here, enable 'Create Embedding Scores for Tickets'. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImJhZDM4OGNkLWIyYjYtNDQxOC1hZjE5LTUxZmU3YWJlY2EzYSJ9.YR-oU7BDSHrERhQQrNWo-u6hFYa412wJqX8k9u3yWF4" class="fr-fic fr-fil fr-dib" width="768" style="width: 770px; height: 569.442px;" height="569"></p><p><strong><span style="font-size: 10pt;">Fig 1. AI ticket matching</span></strong></p><p><br></p><p>Set the 'Ticket matching and AI insights method' field to be 'Built-in-functionality'. Then choose the <a data-fr-linked="true" href="https://usehalo.com/haloitsm/guides/2673" id="isPasted" target="_blank" rel="noopener noreferrer">vector search database</a> that will be used to store the vectors (ticket data), Azure AI search is recommended if you have connected using Azure OpenAI. </p><p><br></p><p><strong><em>Note: AI suggestions can only be used when 'Built-in-functionality' is selected. </em></strong></p><p><br></p><p>Now you can configure the embeddings.</p><p><br></p><p><strong><span style="font-size: 12pt;">Embeddings</span></strong></p><p>Use the 'AI Embedding Field' field to choose the field data that will be used to create an embedding. The data from this field will be passed to your AI connection to create the embedding. The field you choose here will be depend on the fields you use on your ticket types, the field selected must be present on the ticket types you would like AI suggestions to be used on. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImM0ODY2OTZhLTUyYzEtNDQ3Ni1hZTU0LWFmNWZmNGZiNjA3NiJ9.udO6H9aJaYLJ5y1MyiGlv5XjNgzC5VxnxiEwIta_a1U" class="fr-fic fr-fil fr-dib" width="657" height="152"></p><p><strong><span style="font-size: 10pt;">Fig 2. AI Embedding field </span></strong></p><p><br></p><p>Now choose the ticket types that embeddings will be created for in the 'Ticket Types with AI embeddings and insights enabled' field. Only the ticket types selected here will be able to have AI suggestions. </p><p><br></p><p>Set the 'Minimum vector match score (Tickets)', this will be the minimum embedding score two tickets will need to have in order to be deemed a 'match'. Only data from 'matched' tickets will be used in suggestions. </p><p><br></p><p>Historical ticket data can be indexed using the 'Index tickets' button. When used you will be able to choose which ticket types between which dates embeddings are created for and indexed.</p><p><br></p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjY5ZjVjMTI0LWI3MmItNGRmMS1iZjk3LTczYzk2OTNiMTQ3OSJ9.-JR5FGgvL7_I1lJUyklvxSVW65Pxr4HNEv__6l-GMD4" class="fr-fic fr-fil fr-dib" width="538" style="width: 540px; height: 330px;" height="330"></p><p><strong><span style="font-size: 10pt;">Fig 3. Creating embeddings for and indexing tickets</span></strong></p><p><br></p><p><span style="font-size: 11pt;">Embeddings will be created and indexed automatically each time a new ticket is created after the first index is run and if 'Create Embedding Scores for Tickets' is enabled. Before using AI functionality it is good practise to leave the embedding/indexing running for a while so suggestions are based on up to date accurate data.</span></p><p><br></p><p><span style="color: rgb(0, 0, 0); font-family: sans-serif; font-size: 12pt; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; float: none; display: inline !important;" id="isPasted"><strong>Determine which tickets are indexed</strong></span></p><p><span id="isPasted"><strong>Indexing Historical ticket data</strong></span></p><p>When indexing historical ticket data you can determine which tickets are indexed based on the following criteria:</p><ul><li><span style="box-sizing: inherit;">Ticket type of the ticket</span></li><li>Date/time the ticket was logged</li><li>Any other ticket fields</li></ul><p>Only the ticket types in the 'Ticket Types with AI embeddings and insights enabled' field will be indexed. If you would not like tickets of certain types to be indexed (have their data passed to AI), such as HR tickets, leave this ticket type out of this field.</p><p><br></p><p>To filter indexing based on when the ticket was logged, use the start/end date fields on the embedding pop-up. Here you can enter a start and end date and time, only tickets logged between this time period will be indexed, useful for excluding test ticket data from indexing. </p><p><br></p><p>To filter which tickets are indexed based on other ticket fields (including custom fields), you can make use of the 'Additional filters for ticket indexing' table. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6Ijk1NzQwNWJiLWVjNDMtNDIyMi1iOTE2LTM3MWI2NTljOWYyNCJ9.wx4SyzK3HEQsJaZpkAt3LuQ4aKxoBlTYWRLVpbO5p_Q" class="fr-fic fr-fil fr-dib" width="1658" style="width: 1660px; height: 212.662px;" height="213"></p><p><strong><span style="font-size: 10pt;">Fig 4. Additional filters for ticket indexing table</span></strong></p><p><br></p><p><strong><em>Note: Filters added to this table will only apply when indexing existing/historical records, not new records. </em></strong></p><p><br></p><p>Here, you can set criteria tickets must meet in order to be indexed when the 'Index tickets' button is used. In the figure x example, tickets that have the ITIL type 'Advice/other' will not be indexed, but all other tickets will. This can be utilised for further granularity/customisability in controlling which tickets get indexed. </p><p><br></p><p id="isPasted"><strong>Indexing New ticket Data</strong></p><p>When embedding scores are enabled ('Create Embedding Scores for Tickets') tickets will be indexed upon being logged. As long as they have a ticket type within the 'Ticket Types with AI embeddings and insights enabled' field. </p><p><br></p><p>You can also enable the ability to restrict which tickets are indexed using ticket rules. When this functionality is enabled you can set criteria (based on ticket fields) that tickets must meet in order to be indexed, allowing more control over which tickets are indexed. </p><p><br></p><p>To enable this functionality enable 'Determine whether a Ticket is indexed based on Ticket rules' under configuration > AI. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImQ0ZWJjNmE0LTcwYjktNDc2OS05MWIwLTdiMTc0NzRlZmQ1MSJ9.M5A1xZOIkz7hUXPT1SeIdYPMyuGbr2EjqGi3ntiI0-Y" class="fr-fic fr-fil fr-dib" width="433" style="width: 435px; height: 319.438px;" height="319"></p><p><strong><span style="font-size: 10pt;">Fig 5. Enable the use of rules for indexing</span></strong></p><p><br></p><p>You will need to set up a ticket rule(s) with the outcome "indexable", only tickets that meet the criteria in this rule will be indexed. </p><p><br></p><p>Head to configuration > tickets > ticket rules > new, to create a new rule. Here, set the criteria tickets need to meet to be indexed in the rule criteria table. Once set, enable the rule outcome 'indexable', this will mark any tickets that meet this rule as 'indexable' in the background. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjJlYmFiZDBiLTM0ZTUtNDg4YS1iM2UyLTljZWNlOTY5OTFlYyJ9.kPw5806hqectfx1lp5lp7plh3TdQalnhTcaiYpPl4f8" class="fr-fic fr-fil fr-dib" width="738" style="width: 740px; height: 539.025px;" height="539"></p><p><strong><span style="font-size: 10pt;">Fig 6. Rule to mark tickets as indexable</span></strong></p><p><br></p><p>Now, only tickets that meet this rule will be indexed. This will only apply to tickets logged after this rule is created, and will not apply when indexing historical ticket data. </p><p><br></p><p><strong><span style="font-size: 12pt;">Viewing matched Tickets</span></strong></p><p id="isPasted">Now ticket matching has been configured you will be able to see all the tickets that have 'matched' this one in the 'AI matched tickets' field, under the AI Insights tab. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImIwMzQwZjA3LTA2M2ItNDQwZS1hNjdkLWY5ZjM0YTc5MzI1ZSJ9.Uwbi4TZRU4TKUwEx9q_nY4IjVuNh3CTqVsVrYYjVf2I" class="fr-fic fr-fil fr-dib" style="width: 602px; height: 537.352px;" width="600" height="537"></p><p><strong><span style="font-size: 10pt;">Fig 7. Matched tickets</span></strong></p><p><br></p><p>By default this will show all matched tickets, however, you can have this table organise the matched tickets based on ITIL type. This can further improve problem, incident and change management as agents will be more readily able to see and link associated problem/incident and change tickets. This organisation can be enabled per ticket type using the setting 'Separate the AI matches into different tables based on ITIL type', found under the settings of each ticket type. </p><p><br></p><p data-pasted="true"><strong><span style="font-size: 12pt;">AI Case Clustering</span></strong></p><p>AI Case Clustering builds on top of ticket matching and embeddings to automatically group tickets into clusters based on their vector embeddings, using a KMeans algorithm to identify recurring themes across your ticket data. Each cluster is assigned an AI generated description and resolution, giving agents immediate context on the nature of the issue and how it has been resolved historically.</p><p><br></p><p>Clustering powers several of the capabilities covered in this guide. The AI matched tickets table, article suggestions, and KB gap detection suggestions all use cluster membership to determine relevance and similarity. Before enabling clustering, ensure ticket matching is configured and tickets have been indexed into your vector database as described in the Ticket Matching section above.</p><p><br></p><p>To enable clustering navigate to Configuration > AI and enable ticket clustering. Use the New Clustering Run button to schedule an automation that will group all indexed tickets into clusters. Once the run completes, newly logged tickets are automatically assigned to their nearest cluster as they are indexed, keeping cluster membership current without requiring another full run.</p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjZhMjIzODY2LTQ1ZDgtNDk1Zi05OTgwLTdhMDZiYjY1NDE0NSJ9.gXsb1RDlj6dUEj6ZlpvjIwUVizPwdzzBeDv3KuT1zzs" class="fr-fic fr-fil fr-dib" width="1047" style="width: 1049px; height: 399.905px;" height="400"></p><p><strong data-pasted="true"><span style="font-size: 10pt;">Fig 8. Enable Ticket Clustering</span></strong></p><p><br></p><p>Once a ticket has been assigned to a cluster, the AI Insights tab will show the cluster description and AI generated resolution associated with that cluster. To display all other tickets in the same cluster as the ticket you are currently viewing, enable the Cluster Matched Tickets tab on the ticket type. This gives agents visibility of related tickets within the same cluster, supporting incident correlation and problem management.</p><p><br></p><p><strong><span style="font-size: 14pt;">Configuring Ticket Suggestions</span></strong></p><p>Ticket suggestions are essentially a set of rules that are run after AI Insights and AI Matching. The matches are evaluated and if they contain similar values for fields like estimate, agent, and linked problem ticket, a prompt to set the fields to the same value will be shown, or they can be applied automatically. </p><p><br></p><p>To configure the suggestions that can be made hit the 'configure AI suggestions' button to take you the suggestions page. We have some suggestions configured out-of-the-box but these can be customised and new ones can be made. An example suggestion is shown in figure 5. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjNiYjY2Zjk2LWUwZDMtNDY5YS1hMTU2LWFjZGIwOTIzYmQ2ZiJ9.Le0CcDyIzcFPyZp2TQhMBphFZRxDqnOvqoboerS6CpQ" class="fr-fic fr-fil fr-dib" width="969" height="593"></p><p><strong><span style="font-size: 10pt;">Fig 9. Example suggestion - Assigned agent</span></strong></p><p><br></p><p id="isPasted">AI Suggestions have a precedence, only one of each type of suggestion that matches can apply. Suggestions will be checked in order of precedence, once a ticket meets criteria for a suggestion type this suggestion will be made/applied, no further suggestions of this type will be made. </p><p><br></p><p id="isPasted">The following types of suggestion are available:</p><p><br></p><ul><li><strong>Set Estimate to the Estimate of matched tickets:</strong> This will allow you to set the estimate of the ticket based on the average, maximum or minimum estimate on the matching tickets.</li><li><strong>Set the assigned Agent based on matched tickets:</strong> This will allow you to assign the ticket to the same agent as the matched tickets based on the agent's default team if multiple of the matching tickets are assigned to the same agent.</li><li><strong>Set Category based on matched tickets:</strong> This will allow you to set the category (1, 2, 3 or 4) of the ticket if the matches have a frequently used category.</li><li><strong>Set Priority based on matched tickets:</strong> This will allow you to set the priority of the ticket if the matches share a similar priority level.</li><li><strong>Set Priority to the AI suggested priority:</strong> This will allow you to set the priority to what the AI interprets the priority as.</li><li id="isPasted"><strong>Set Urgency based on matched tickets:</strong> This will allow you to set the urgency of the ticket if the matches share a similar urgency level.</li><li><strong>Set Urgency to the AI suggested urgency:</strong> This will allow you to set the urgency to what the AI interprets the urgency as.</li><li id="isPasted"><strong>Set Impact based on matched tickets:</strong> This will allow you to set the impact of the ticket if the matches share a similar impact level.</li><li><strong>Set Impact to the AI suggested impact:</strong> This will allow you to set the impact to what the AI interprets the impact as.</li><li><strong>Run an automation if AI suggests the ticket is an incident:</strong> This will allow you to trigger an action automation if the AI evaluates the ticket as an incident, allowing you to triage it as such.</li><li><strong>Run an automation if AI suggests the ticket is a request:</strong> This will allow you to trigger an action automation if the AI evaluates the ticket as a request, allowing you to triage it as such.</li><li><strong>Create a problem ticket for incident matches:</strong> If the matching tickets are incidents that are not linked to a problem, you can set a threshold to automatically create a problem ticket and link them to it.</li><li><strong>Link to an existing problem ticket based on the problem ticket of incident matches:</strong> Similar to creating a problem ticket, if the majority of matches are linked to the same problem already, it will identify that the current ticket should be linked to the problem ticket as well.</li><li><strong>Run an automation if there are Ticket matches:</strong> If there are any ticket matches above a certain match score, run an action automation.</li><li><strong>Run an automation if there are Articles matches:</strong> If there are any article matches above a certain match score, run an action automation. Link this to action that can write a response using the article suggestions from the recently added AI Knowledge matching feature to easily generate a response based on the matched articles.</li></ul><p><br></p><p>In the 'Suggestion Information' field you will need to set what you would like to appear in the suggestion information field, this tells the agent what the suggestion is for. You will need to include $-SUGGESTEDVALUE here to ensure the field is populated with the value that is being suggested. </p><p><br></p><p>You can also set conditions against each suggestion, these restrict when this suggestion will be made. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjE1ODY4YjRlLWI1ZTEtNDZhNy1hOWJhLTVhNzliN2E0ZjhmYSJ9.x51Gnoq6HKNrVHEGKPey3qcCQiEUknsyRyaqsVz-Mto" class="fr-fic fr-fil fr-dib" width="994" style="width: 996px; height: 575.924px;" height="576"></p><p><strong><span style="font-size: 10pt;">Fig 10. Suggestion conditions</span></strong></p><p><br></p><p>Suggestions can be restricted by ticket type, end user of the ticket and strength of match. With Ticket Type groups enabled, you will also be able to allow specific groups here. This is useful if you have lots of ticket types you would like to allow, as instead of having to list them all you can specify the group they belong to. </p><p><br></p><p>You can also restrict suggestions to tickets that contain the same fields using the field 'The following Field(s) must match'. When used this suggestion will only be made when the ticket matches a ticket that has the same value in the field chosen here. Allowing you to restrict suggestions to tickets that are for the same customer, site, user or asset.</p><p><br></p><p>The field 'Include Open/Closed/All Tickets' is used to determine what ticket data will be used for the suggestion. If 'All tickets' is selected suggestions can be made based on data from both open and closed tickets. If you are including closed tickets in your suggestion database you can also set which closed tickets will be used based on when they were closed, allowing you to filter out ticket data that is outdated. </p><p><br></p><p>You can also restrict suggestions to recent tickets, opened/closed in the last x days using the field 'Tickets Opened/Closed within the last X days'. If a value is entered here, only tickets opened/closed in the last x days will be used to make a suggestion, allowing suggestions to only be made based on recent data. You can enter decimals in this field, allowing you to set a restriction in hours (0.5 = 12 hours). </p><p><br></p><p>These conditions are especially useful when the setting 'Automatically apply this suggestion' is enabled. As this ensures suggestions are only applied automatically when strict criteria are met, such has having a very high minimum score and high number of matches.</p><p><br></p><p><strong><span style="font-size: 14pt;">Using AI Ticket Suggestions</span></strong></p><p>Once AI ticket suggestions are configured you will need to add the "AI Suggestions" field to all ticket types you would like suggestions to show on. By default this field will show in the ticket details so ensure you move it to the "AI Insights" tab, or another tab of your choice. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImEwOGExNDdhLTM4ZDgtNDI4My1hOTVkLWMxM2E5ZWZkNWRkMyJ9.Wd6BQINTqrtw7Khh_My1PpSPAirwtGlQ4SRozFKi5hI" class="fr-fic fr-fil fr-dib" width="1255" style="width: 1257px; height: 762.443px;" height="762"></p><p><strong><span style="font-size: 10pt;">Fig 11. AI Insights tab against ticket</span></strong></p><p><br></p><p>In addition to this tab, if a ticket has AI suggestions a pop-up notification will appear at the bottom of the ticket, when this notification is selected you will be taken to the AI insights tab. If you would rather not have a pop-up notification and instead have notifications available in the problem/resolution finder, head to configuration > AI and toggle the 'AI suggestion notification' setting. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImY1NGRlZjFkLTQ3YzktNGRjOC05M2FhLWQ0Mzc0MmZmOTA2OSJ9.ISs2VJ0mLLLdgAoY716MwlgRYPGaSE-rQFZT0OETuEs" class="fr-fic fr-fil fr-dib" width="641" height="194"></p><p><strong><span style="font-size: 10pt;">Fig 12. AI suggestion notification</span></strong></p><p><br></p><p>The AI insights tab will contain all the suggestions that can be made for the ticket. The 'Apply suggestion' button is used to apply the suggestion to the ticket. Once a suggestion is applied the date/time the suggestion was applied will show. </p><p><br></p><p><strong><span style="font-size: 12pt;">Applying suggestions at action level</span></strong></p><p>Halo AI suggestions can also be applied to fields that are updated via an action. This allows agents to use AI suggestions at action level, useful for fields that are populated at a certain stage of a ticket's workflow, such as when the ticket is triaged. Agents can process the ticket as usual, with AI suggestions being given to them along the way.</p><p><br></p><p>To do this enable the setting 'Show AI suggestions on context hints' against each action you would like suggestions to be given on. Keep in mind suggestions will only be given for fields in the action's field list that have a suggestion configured. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjkwYmQwNGViLTU5YzctNGJiNi05ZjM3LWU0MTdmYTkwNTA4MCJ9.4Gm8vAzA6YsUKWMrS_h6j8z_LTn2yCwJt5lPXScgCj8" class="fr-fic fr-fil fr-dib" width="371" style="width: 373px; height: 311.8px;" height="312"></p><p><strong><span style="font-size: 10pt;">Fig 13. Enable AI suggestions to be given as a hint for an action</span></strong></p><p><br></p><p>You will need to enable this against each setting you would like field suggestions to be given for. </p><p><br></p><p>When enabled, the AI suggestion for the field will appear as a 'context hint'. Rather than the field populating automatically, agents can hover over the AI icon next to the field to see what the AI suggestion for the field is. Then the field can be selected to apply the suggestion. </p><p><img data-fr-image-pasted="true" src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6Ijk3YTEwOWI3LWIzMjItNDdiZS1hOGM4LTlhMmNkM2ZlZWQyYiJ9.xKVkShF2mdtG6BxjUG25RYODbW36nH2QSDTqwR2x8Uo" width="595" height="131" style="box-sizing: inherit; border-style: none; cursor: pointer; padding: 0px 1px; user-select: none; max-width: none; text-align: left; color: rgb(0, 0, 0); font-family: sans-serif; font-size: 14px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; height: 130.621px; background-color: rgb(255, 255, 255); width: 597px;" id="isPasted" class="fr-fil fr-dib"></p><p><strong><span style="font-size: 10pt;">Fig 14. AI suggestions given as field hints</span></strong></p><p><br></p><p><br></p><p><strong><span style="font-size: 14pt;">Article Suggestions</span></strong></p><p>AI can be used to suggest relevant knowledge base articles for tickets. This can assist agents in resolving tickets, saving them having to find relevant articles themselves to read/send to users. </p><p><br></p><p>Article suggestions require Azure AI search to be enabled and configured due to the way article suggestions are returned. When a ticket is logged a search term is created based off the matched tickets, this search term is used to perform a vector search on indexed knowledge base articles.</p><p><br></p><p>In order to use this functionality:</p><ul><li id="isPasted">Ticket matching and AI insights method must be set to "Built-in functionality"</li><li>AI knowledge search - Vector search database must be set to "Azure AI Search"</li></ul><p><br></p><p>To set this up head to configuration > AI > AI Knowledge search section. Set the 'Vector search database' to be 'Azure AI Search', you will need to configure an Azure AI search connection for this. Details on how to obtain connection details from Azure can be found <a data-fr-linked="true" href="https://learn.microsoft.com/en-us/azure/search/search-create-service-portal" target="_blank" rel="noopener noreferrer">here</a>. Now ensure 'Enable AI Article Suggestions' is enabled. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjRmZDVkMjRhLWE4NGMtNDg5MC04NGExLTg0MWU3ZWJiMjkwZSJ9.SpjxLHp_9If2ptK9hXAGQjNu3DMmjNYx2ZUvZq5LpI0" class="fr-fic fr-fil fr-dib" width="768" height="522"></p><p><strong><span style="font-size: 10pt;">Fig 15. AI knowledge search settings</span></strong></p><p><br></p><p>If you would like to restrict which articles can be indexed based on their FAQ list enable this setting, a field will then appear against each FAQ list to determine if this FAQ list can be indexed. This allows you to exclude certain articles from the index so they do not affect the index data, such as internal articles. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjczZWZkYWE2LTNjY2YtNDU3Yy04Njk0LWY5YTBkMjY0OWU0MyJ9.L3DEiSDDBrfcqIjvDjPJXdSQ2UH1epEw9MpM-gtGi30" class="fr-fic fr-fil fr-dib" width="840" style="width: 842px; height: 666.263px;" height="666"></p><p><strong><span style="font-size: 10pt;">Fig 16. Setting to determine if FAQ list is indexed </span></strong></p><p><br></p><p>Articles will be indexed each time a new article is created but the 'Index articles' button can be used to index historical article data. </p><p><br></p><p id="isPasted">Now AI article suggestions are active, when a ticket is logged article suggestions for the ticket will appear in the problem/resolution finder. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6ImNjMjY3ZjdmLWUxYzMtNDczZS04NzU5LWUzYzI3NzNjNWQ0NCJ9.Q7wxFkUN1RKBxzBSSBWimtihk1NCKeaS806Z5ql0nXE" class="fr-fic fr-fil fr-dib" width="183" height="167"></p><p><strong><span style="font-size: 10pt;">Fig 17. AI article suggestions in the problem/resolution finder</span></strong></p><p><br></p><p>Article suggestions will also appear under the 'AI insights' tab against the ticket with a matched score. </p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjIxNzQ4NWZkLWI0ZmMtNDQ0OS04MWZlLWVmNDkzZTYyYjQxMSJ9.ede7FwTs7jRiYI2nOghTxQ7pzKKSGkkWxGrHcGile60" class="fr-fic fr-fil fr-dib" width="733" style="width: 735px; height: 525.986px;" height="526"></p><p><strong><span style="font-size: 10pt;">Fig 18. Matched articles</span></strong></p><p><br></p><p>The "Next Review Date" will also show in this table, allowing agents to ensure the article they are referencing is relevant and in-date. If an article has expired, the agent can create a new article or update the existing version.</p><p><br></p><p><br></p><p><br></p><p><br></p><p><br></p>
