MicrosoftExpanded

KPMG Australia boosts productivity with generative AI agent for employees and clients

KPMG Australia developed and deployed KymChat, a generative AI chat agent, to help its 10,000 employees access, summarize, and generate insights from both internal and external unstructured data sources. Leveraging Azure OpenAI (GPT-3.5, GPT-4), Azure Cosmos DB for MongoDB vCore (with vector search), Azure App Service, and Azure Container Registry, KymChat was rapidly scaled across the business. The deployment resulted in a substantial leap in search quality (from 50% to 91%) and reduced average response times to under a second. About 70% of employees adopted the tool, which has processed over 120,000 queries. KymChat is now being expanded for client offerings and to other KPMG member firms worldwide. The solution also includes user onboarding, prompt engineering training, and hackathons to encourage new use cases. The project was enabled by close collaboration with Microsoft engineering teams and involved significant integration between cloud, containerization, and advanced AI search capabilities. KymChat was designed for robust data security and privacy, ensuring sensitive information stays within the firm. The impact has included up to 50% productivity improvement in areas such as document drafting, communication, sales proposal development, and research, creating more time for client interaction and fostering a culture of continuous learning.

Organization
KPMG Australia
Location
Australia
Published
June 2023

Reported outcomes

+91%

quantified impactQuality & accuracy

+50%quantified impact70%quantified impact+50%productivity

Strategic outcomes

Customer experience & trustImproved search quality for usersSpeed & agilityReduced response times across use casesNew product / capabilityExpanded AI chat agent into client offeringsScale & capacityScaled AI solution across global firms

Primary read

Use case focus

Showing 3 of 3

  • 1Enterprise Search Assistant using Generative AI
  • 2Automated Document Summarization and Insight Generation
  • 3Employee Productivity Agent leveraging vector search
  • Employees struggled to efficiently surface insights from large amounts of unstructured internal and external data.
  • Traditional search and information retrieval was slow and yielding low-quality results, with a search quality baseline around 50%.
  • Frequent manual and repetitive tasks reduced productivity in document drafting, communication, proposal development, and research workflows.
  • Scaling AI solutions led to increasing response times and inconsistent result quality.
  • A need for secure, organization-controlled deployment of AI tools to meet privacy requirements.
  • Developed and launched KymChat, a generative AI agent, using Azure OpenAI (GPT-3.5 and GPT-4).
  • Integrated Azure Cosmos DB for MongoDB vCore with vector search for semantic understanding and rapid retrieval of unstructured data.
  • Deployed backend code via Azure Container Registry and Azure App Service for scalable, containerized delivery.
  • Incorporated prompt engineering training and user onboarding for employees.
  • Close collaboration with Microsoft engineering to optimize architecture and solution reliability.
  • Search quality increased from 50% to 91%.
  • Average response times reduced to under one second across use cases.
  • 70% employee adoption rate with 120,000+ queries processed in the first phase.
  • Productivity increased by up to 50% in key workflows.
  • Expanded to client offerings and global KPMG firms, demonstrating high scalability.
Architecture

KymChat uses Azure OpenAI (GPT-3.5, GPT-4) to process and generate responses based on enterprise data. Azure Cosmos DB for MongoDB vCore provides vector search capabilities for fast and context-aware retrieval of unstructured data, integrated with GPT-4 via Azure OpenAI Service. Backend code for data preparation and prompt handling is containerized with Azure Container Registry, and the chat agent is hosted and auto-scaled using Azure App Service. The architecture allows secure internal use, rapid scaling, and addition of new use cases and data sources.

Sources & evidence3
ExpandedExpanded

The same organization appears in newer AI deployment evidence.

  • Same organization re-documented as recently as 2024.

Measures whether this deployment's public evidence persists — not whether the system is still in production.

Groundedness: Unavailable

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

Loading comments...

Similar cases