carrot carrot carrot Change Centers x cognizanti collaborators create-folder Data Science Decisive Infrastructure download download edit Email exit Facebook files folders future-of-work global sourcing industry info infographic linkedin location Mass Empowerment Mobile First our-latest-thinking pdf question-mark icon_rss save-article search-article search-folders settings icon_share smart-search Smart Sourcing icon_star Twitter Value Webs Virtual Capital workplace Artboard 1

Please visit the COVID-19 response page for resources and advice on managing through the crisis today and beyond.


AI and automation improve insurance claims process

The challenge

A leading property and casualty insurance company wanted to improve its first notice of loss process to meet the dual mandate of following business protocol while being sympathetic to its customers. Although the company must be cognizant of the fact that a first notice of loss process can be stressful for customers initiating a claim, it must also ensure that the issue is resolved to the customer’s satisfaction while minimizing the risk of litigation, detecting potential fraud and controlling costs. The company asked Cognizant to examine and improve its first notice of loss process.

Our approach

We transcribed 25,000 saved calls using voice-to-text technology and analyzed these calls to identify the most commonly repeated activities. We built a chatbot functionality to capture these processes automatically. By mapping the revamped first notice of loss session to a template of 80 capture fields, we ensured that all aspects of a session are captured. The session also includes recommendations for service rep dialogue. Using artificial intelligence (AI) helps streamline the insurance claims process as well as cut down costs and improve customer satisfaction.

Automated transcription reduces call duration and costs

With our solution, the voice-to-text transcription rate went up to 92%, from 67%. All calls are transcribed in real time. After a call is completed the transcription is summarized and automatically presented to service rep supervisors for review and approval, helping them focus on quality and efficiency. The evaluation of the pilot project showed that call duration and associated costs have gone down. The company is set to launch a full deployment of the AI and analytics solution soon, and it’s planning for next-phase enhancements.


reduction in average call length


reduction in call costs due to post-call approval process


accuracy of automated transcription, up from 67%