Case Study Case Study
Perspectives

Case Studies

Customer Stories

Testimonials

ALM Media, LLC

Josh Gazes, Senior Vice President – Operations

British Gas

Jess Johnson, Head of Operational Excellence

Mosaic Insurance

Mitch Blaser, Co-CEO

Mosaic Insurance

Krishnan Ethirajan, COO

Oxford Nanopore Technologies

Jason Hendrey, Senior Director, Global Customer Services

WS Audiology (WSA)

Christof Steube, Director of Finance Excellence

Kiwi.com

Leonard McCullie, Director, Vendor Management

Kiwi.com

Petra Reiter, Vice President, Customer Services

Flight Centre

Aaron Fadelli, Business Leader

Healius Pathology

Alex Cook, Head of Finance Operations

Varo Bank

Breanna Rivers, Partner Performance Manager

Yorkshire Building Society Group (YBS)

Jessica Lockwood, Process Automation Manager

WS Audiology (WSA)

Sharang Patil, Director of Group Finance Excellence

Priya Madan Mohan, VP for Group Accounting & Controlling

United Airlines

Chris Kenny, VP and Controller

GFG Alliance

Phillip Irish, General Manager, Shared Services Delivery, Quality & Governance

Energy Australia

Steve Corden, Outsource Operations Leader

Delaware North

Christopher Lozipone, Senior Vice President and Global Business Services Head

Moneycorp

Nick Haslehurst, Chief Financial & Operating Officer

Prodigy Finance

Nico Barnard, Head of Operations

M&T Bank

Chris Tolomeo, Senior VP & Head of Banking Services

Minerals Technologies Inc. (MTI)

Khem Balkaran, CIO

Church's Chicken

Louis J. Profumo, CFO & EVP

The Industry Landscape: The Urgent Need for AI-driven Knowledge Management

For global enterprises, seamless knowledge access is critical to operational efficiency and compliance. This is especially true for Finance and Accounting (F&A) functions, where large-scale process documentation – such as Standard Operating Procedures (SOPs) and Detailed Process Manuals (DPMs) – is essential for process adherence. However, inefficient document management and knowledge silos create significant barriers to productivity and accuracy.

To address these challenges, companies are increasingly turning to Artificial Intelligence (AI)-driven solutions that accelerate contextualized tknowledge retrieval and enable employees to focus on high-value tasks.

The Client Challenge: Overcoming Complexity in F&A Document Management

The client managed an extensive repository of 300+ DPMs spanning more than 40 sub-processes, with each manual averaging 50 pages. The limitations of traditional document management created:

1. Prolonged Query Resolution: Agents had to manually navigate through SharePoint’s complex search functionality, leading to extended Average Handling Time (AHT).

2. Increased Risk of Errors and Compliance Issues: Manual handling increased the risk of document mismanagement, including accidental deletions, leading to process inconsistencies and non-compliance.

The Solution: Intelligent Knowledge Management with Gen AI & Analytics

WNS deployed a Gen AI-powered Virtual SME, leveraging cloud, Natural Language Processing (NLP), analytics and Machine Learning (ML) to automate document extraction and retrieval and streamline access to critical process manuals.

The solution incorporated:

  • Cloud-based Scalability: The solution was deployed on a scalable cloud platform, ensuring high availability, fast query resolution and secure document management.
  • Automated Document Ingestion and Pre-Processing: The system ingested and pre-processed documents from multiple sources, eliminating manual efforts and errors caused by outdated or misplaced files.
  • AI-led Intelligent Chunking and Embedding: Large documents were segmented into logical sections and transformed into vector representations for faster, context-aware retrieval, eliminating prolonged query resolution and inconsistent service quality caused by manual searches.
  • ML and Model Training for Intelligent Knowledge Processing:
    • The system leveraged ML frameworks to train and fine-tune models responsible for document chunking, embedding and indexing.
    • This ensured efficient handling of diverse document types, allowing agents to retrieve precise, context-aware responses even as process documents evolved.
    • The continuous training of models enhanced AI’s ability to interpret queries, ensuring highly relevant search results and improved response accuracy.
  • Vector Database for High-Speed Search: A scalable, high-performance vector database stored vectorized chunks of the documents, ensuring fast and accurate similarity-based searches.
  • Natural Language Processing (NLP) Engine: The NLP engine processed user queries in natural language, converting them into a format compatible with the vector database to fetch relevant information from the embedded document chunks.
  • Azure OpenAI Large Language Model (LLM) Integration: AI-generated responses provided instant, accurate and context-aware answers, reducing manual interpretation errors.
  • Advanced Analytics for Continuous Optimization: To ensure ongoing efficiency, accuracy and compliance, the solution integrated advanced analytics to track system performance, optimize AI responses and monitor document changes.
    • Response Accuracy & Confidence Scoring: The system continuously tracked response accuracy and assigned confidence scores, helping identify areas that needed refinement to improve precision.
    • Performance Analytics: Real-time tracking of response time, query handling time and knowledge retrieval efficacy ensured quick query resolution and process efficiency.
    • Document Change & Compliance Tracking: Regular monitoring of document updates ensured agents always accessed the most up-to-date and compliant information. This minimized errors from outdated knowledge and improved adherence to business policies.
  • API Development and Seamless Integration with Client Systems:
    • Application Programming Interface (API) frameworks were utilized to integrate the Virtual SME with the client’s existing platforms, including SharePoint and other enterprise systems.
    • These APIs enabled agents to query documents directly from their existing workflows, removing the need for platform switching and enhancing adoption rates.
  • Intuitive User Interface (UI): A user-friendly UI helped agents input queries, view responses and access links to relevant documents for verification and review.

The Outcome: Productive, Compliant and Scalable F&A Knowledge Management

The solution delivered immediate measurable improvements in knowledge management and retrieval, impacting operational and compliance efficiency. Key outcomes within the first two months of implementation included:

 percent reduction
in AHT, resulting in
improved productivity
 

Increased
DPM compliance

8.25/10 user satisfaction
rating from agents in a qualitative
survey on ease-of-use, functionality,
performance and user experience


Furthermore, early results indicate promising developments in critical areas such as:

Consistent Service Quality:
Standardized responses are improving accuracy and reliability, strengthening customer trust.

Stronger Knowledge Retention:
The platform is mitigating the impact of attrition by preserving institutional knowledge and simplifying onboarding for new agents.

Optimized Cost Efficiency:
Reduced handling times, lower training overheads and fewer errors are expected to contribute to cost savings and improved profitability.

Enhanced Scalability:
The API-driven architecture has enabled seamless integration with additional systems, positioning the client for future growth.

Join the conversation