facebook
Home > Case study > How Qinfinite AI in ITSM Helped a UK-based Neo Bank Automate and Streamline Its IT Service Desk Operations Service

How Qinfinite AI in ITSM Helped a UK-based Neo Bank Automate and Streamline Its IT Service Desk Operations Service

Qinfinite-Chaos-Engineering

About the Client:

The client is a UK-based neo bank known for its digital-first approach to banking and commitment to delivering seamless financial services to its customers. Despite its innovative front-end experience, the bank faced challenges in its back-office IT service desk operations. 

Business Need

The neo-bank’s IT Service Desk manages numerous service requests and incidents daily through its JIRA ITSM platform. The existing process is manual and time-consuming, leading to delays in incident resolution and inefficient use of engineering resources. To improve service efficiency, the bank needed advanced AI Agents to automate ticket classification, routing, and resolution, reducing manual intervention and improving response times. 

The Qinfinite Solution

The solution leveraged Qinfinite’s AI Agents to streamline the IT service desk operations through an orchestrated process that involves ticket classification, role assignment, and resolution management. 

Detailed Description of the Workflow:

1: Ticket Ingestion and Initial Processing (ITSM System)

      • Pick New Ticket: The workflow begins when the system picks a new ticket from the ITSM platform (e.g., Jira). 
      • Extract Ticket Details: The ticket’s details are extracted, including all relevant metadata that will be used in subsequent steps. 
      • Check for Duplicates: The system checks whether the new ticket is a duplicate of any existing ticket in the system. 

2. Duplicate Handling (Deterministic & Classical AI Agents)

Duplicate Check Decision: 

      • If the ticket is identified as a duplicate, domain-specific rules are applied to determine if it truly is redundant. 
      • Duplicate Classifier Model: A machine learning model further validates if the ticket is a duplicate. 
      • Action: If confirmed, the ticket is canceled; otherwise, it proceeds further for classification. 

3. Ticket Classification (Classical AI Agents)

      • Ticket Profile Analysis: The ticket is analyzed to build a profile based on past data, context, and content. 
      • Priority Classifier: The AI agent classifies the ticket’s priority, helping to determine how quickly it should be addressed. 
      • Service Request/Incident Classifier: The ticket is categorized as either a service request or an incident, which dictates the subsequent workflow. 

4. Incident Management (Gen AI & SME Identification)

Is Incident Decision: 

      • If the ticket is an incident, a Slack room is created for real-time collaboration among stakeholders. 
      • SME Identification: The system identifies the appropriate Subject Matter Expert (SME) using rules-based and AI-driven approaches. 
      • SME Classifier: The SME Classifier determines the most suitable SME to handle the issue based on historical data and expertise profiles. 
      • Notify SME: The identified SME is notified to take action on the incident. 

5. Root Cause Analysis (RCA Agent)

      • Root Cause Analysis Decision: The AI agent determines if a root cause analysis is required for the incident. 
      • RCA Agent Execution: If required, the RCA (Root Cause Analysis) Agent performs the analysis using predefined RCA jobs, helping to identify the underlying cause of the issue. 

6. Remediation and Resolution (Gen AI Agents)

Is Root Cause Determined Decision: 

      • If the root cause is determined, the remediation process is initiated. 
      • Remediation Recommender: The AI suggests remediation actions based on the root cause identified. 
      • Remediation Job Execution: A rules-based remediation job is executed automatically to resolve the issue. 
      • Is Remediation Re-evaluation Decision: 
      • If the issue is not resolved, the remediation steps are re-evaluated, and alternative actions are recommended until the incident is fully addressed. 

7. Resolution and Closure (Solution Teams)

The final stage involves the SME or support engineer confirming the resolution, implementing necessary actions, and closing the ticket once all processes have been successfully executed. 

The Business We Delivered Benefits:

  • Reduced Ticket Handling Time: By automating ticket classification, role identification, and the resolution process, the service desk reduced the time spent on each ticket, resulting in faster resolution times and improved service levels. 
  • Efficient Resource Utilization: The automated role identification ensured that tickets are assigned to the most appropriate engineer, reducing the workload on L1 staff and enabling L2 engineers to focus on more complex issues. 
  • Enhanced Collaboration: The creation of dedicated Slack Rooms for incidents enhanced communication between teams, facilitating quicker problem-solving and reducing the need for multiple back-and-forth emails or calls. 
  • Improved Incident Management: Continuous learning from resolved tickets helped the AI agents improve classification and role identification accuracy over time, ensuring the service desk evolves and becomes more efficient with each interaction. 
  • Knowledge Retention: Automatic summarization of conversations and resolutions ensured that all relevant information is captured, providing a valuable knowledge base that can be used for training and improving future processes. 

Related Insights

Case study
Qinfinite

How Qinfinite’s AI-powered ITSM Capabilities Reduced MTTR and Increased Cost Efficiency for a Leading UK Bank

Discover how Qinfinite’s AI-powered ITSM solution helped a top UK bank reduce MTTR, double ticket volume handling, and improve cost efficiency—without changing tools like Jira or Slack

Read more
Case study
Qinfinite

How Qinfinite’s Event Intelligence Solutions Helped Leading a Manufacturing Company Reduce Mean Time to Resolve (MTTR) by 60% 

Learn how Qinfinite’s Event Intelligence slashed downtime and MTTR, and boosted operational efficiency by 50% for a leading manufacturing enterprise.

Read more
Case study
Qinfinite

How Qinfinite’s Hire-to-Retire Process Automation Helped a Leading UK Bank Achieve 80% Reduction in MTTR

Discover how Qinfinite’s AI-powered ITSM solution helped a top UK bank reduce MTTR, double ticket volume handling, and improve cost efficiency—without changing tools like Jira or Slack

Read more
Contact Us

Get in touch with Quinnox Inc to understand how we can accelerate success for you.