Sensible Case Classification With OpenAI – DZone – Uplaza

This text will show how Kumologica and OpenAI can help in growing an AI agent API that effectively classifies circumstances inside an enterprise utilizing person information, with out the necessity for buyer help agent intervention. A really perfect case administration answer ought to be capable to routinely categorize and prioritize circumstances from varied channels, establish high-priority circumstances, apply labels, and assign them to the suitable teams with out requiring brokers to manually carry out these duties.

There are a number of case administration merchandise at the moment accessible in the marketplace, corresponding to ServiceNow, JIRA, and Salesforce Case Administration. Whereas a few of these merchandise embrace built-in options for ticket classification, others supply no such performance. Even for these with built-in options, there are limitations of their potential to combine with third-party programs.

Use Case

On this situation, an ABC enterprise handles each IT and non-IT points by way of an enterprise portal. Customers present key particulars, corresponding to the difficulty title, description, and the related division (infrastructure, networking, CRM, and so forth.), the place the difficulty must be submitted. As soon as the person completes these particulars, the case is submitted and enters a queue for a help agent to evaluation. The agent then retrieves the ticket from the queue, opinions the knowledge, and manually creates a ticket inside the case administration system. Under Fig 1 supplies the illustration of the prevailing case creation course of in ABC enterprise.

Design

New Structure

The structure crew has proposed a brand new design to handle delays in ticket processing and improve the effectivity of the ticketing system. They recognized that a good portion of the delay is attributable to the guide course of the place help brokers learn, perceive, and classify tickets into the right division inside the case administration platform.

In keeping with the brand new design, there’ll not be any guide intervention between the person’s case submission on the enterprise portal and the case administration platform. The enterprise portal might be straight built-in with the case administration platform by way of an clever case classification AI agent service. This agent will routinely interpret the user-provided particulars, categorize the ticket to the suitable division, and assign the right labels, tags, and initiatives inside the case administration system.

Technical Design

Within the new design, an API-based AI agent service might be developed to combine the enterprise portal with the case administration platform. This service will settle for requests from the enterprise portal, extract the outline particulars, and cross them to a synthetic intelligence supplier for classification. The AI will then return the required information to create the case inside the case administration platform. Kumologica might be used as the combination framework to construct the AI agent in a low code trend, using the OpenAI node to attach with OpenAI for clever classification.

Prerequisite

1. Obtain and set up Kumologica designer.

npm i @kumologica/sdk 

3. Set up OpenAI node within the Kumologica undertaking bundle.

 npm i @kumologica/kumologica-contrib-openai  

2. OpenAI account entry and token for accessing OpenAI platform.

Steps

Now we’ll begin the implementation of smartcase classifier service in Kumologica. For individuals who are new to Kumologica, you’ll be able to refer the next tutorial hyperlink to get began. 

1.  Open the Kumologica Designer, drag and drop the EventListner node from pallet to the canvas. Present the next config for the node.

Show Title : [POST] /case/create
Supplier : AWS
EventSource : Amazon API gateway
Verb : POST
URL : /case/create

Word: The article is taking the belief that ABC enterprise is having AWS cloud infrastructure.

2. Drag and drop Logger and wire it to the EventListener node added in the 1st step. Present the next config for Logger.

Show Title : Log Entry
Degree : INFO
Message : 'Request recevied : ' & msg.payload
Log format : String

3. Add two set property node to the canvas and supply the next config. That is to extract the request information and to set the principles for classifying the case.

Set-Property 1
Show Title : Set Case Knowledge

Operation : Set
Goal : msg.description
Supply : msg.payload.description

Operation : Set
Goal : msg.title
Supply : msg.payload.title

Set-Property 2
Show Title : Set Case Knowledge

Operation : Set
Goal : msg.rule
Supply : "if the outline incorporates something associated to cloud, AWS, Azure, Sharepoint then present the next JSON. label is dependent upon if its AWS , Azure, Sharepoint and so forth.
Description sttribute in JSON would be the unique description from person. 
{"Department" : "Infra-support", "Project" : "INF", "Label" : "AWS", "Description" : "" }
if the outline incorporates something associated to community then present the next JSON. 
Description sttribute in JSON would be the unique description from person. 
{"Department" : "Network-support", "Project" : "NET", "Label" : "Networking", "Description" : "" }"

4. Now add the OpenAI node from the pallet and supply the next config. Then wire the node to the set property node in step 3.

Show Title : OpenAI
Operation : Single Q&A
Mannequin : gpt-4o-mini
API Key : >
System : msg.rule
Person : msg.description

5. Lastly we might be ending the move with the response in EventListener Finish node. 

Show Title : Success
Response : HTTP Response
Standing Code : 200
Payload : msg.payload

The ultimate move will appear to be the picture beneath.

Strive It

The above move will be invoked by utilizing the beneath endpoint domestically.

Endpoint : http://localhost:1880/case/create
Methodology : POST
Content material-Kind : utility/json
Physique : {
  "title" : "Issue in with account access",
  "description" : "Request for providing the access the AWS dynamoDB in non prod account"
}

You’ll be getting the beneath because the response. The response reveals that the AI has categorised the division, undertaking, label based mostly on the person description.

{"Department" : "Infra-support", "Project" : "INF", "Label" : "AWS", "Description" : "Request for providing the access the AWS dynamoDB in non prod account"}

Conclusion

Whereas integrating Kumologica and OpenAI for case classification affords a promising answer to streamline case administration, there are additionally essential issues. The automation can significantly cut back delays and enhance accuracy, however enterprises ought to fastidiously assess their current infrastructure and potential integration challenges. Moreover, monitoring AI accuracy and guaranteeing correct oversight might be essential for sustaining service high quality. As with all AI implementation, ongoing optimization might be obligatory to make sure that the system adapts to evolving enterprise wants and altering case dynamics.