Revolutionizing Contact Center Performance – The Power of AI-Driven Agent Evaluations
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V5I3P105Keywords:
Generative AI, Amazon Connect, Contact Lens, Machine Learning, AWS Lambda, Sentiment Analysis, Amazon BedrockAbstract
This paper examines the possibilities of using Amazon Connect, Contact Lens, AI, ML, and generative AI to automate the assessment of agent performance in contact centers. The methods of agent evaluation are currently usually manual and subjective, where a small sample of recordings is reviewed by the supervisors, usually only 2-5% of all interactions, so they provide a very limited and potentially skewed view. These methods are also time-consuming and not feasible, especially when the contact centers are expanding. In an effort to address these challenges, this paper proposes a new and intelligent architecture for implementing the monitoring and resolution of issues related to the platform, which incorporates AWS components, including Amazon S3, AWS Lambda, Amazon SQS, and Amazon Bedrock, as well as Contact Lens and Amazon Connect. The proposed system allows for the automation of sample quality evaluations by responding to 100% of the customer-agent interactions using natural language understanding and sentiment analysis and finally giving automated feedback using generative AI. It was also evidenced that the evaluation enhanced its coverage, objectivity, operational efficiency, and specificity of feedback. This effectively brought down bias to the evaluations by 35% and greatly cut back on the time spent on the evaluations, taking half the required time. It also makes the assessments fair and exhaustive while at the same time improving the development of the agents and the overall evaluation of their performance in customer service. The paper concludes with a proposal for future research lines, such as the addition of multiple channel analyses and innovations in the present channel
References
[1] Shermis, M. D., & Burstein, J. (2013). Handbook of automated essay evaluation. NY: Routledge.
[2] Ahmed, S., Zaki, A., & Bentley, Y. (2024). Automated evaluation techniques and AI-enhanced methods. In Utilising AI for Assessment, Grading, and Feedback in Higher Education (pp. 1-27). IGI Global.
[3] Mughele, E. S., Ogala, J. O., & Okpako, E. A. (2024). Utilising Amazon Web Services Tools for Efficient Multilingual Omnichannel Contact Centres. Faculty of Natural and Applied Sciences Journal of Computing and Applications, 2(1), 51-57.
[4] Živković, M. (2019). Integration of artificial intelligence with cloud services. In Sinteza 2019-International Scientific Conference on Information Technology and Data Related Research (pp. 381-387). Singidunum University.
[5] Chien, M., & Jain, A. (2019). Magic quadrant for data quality tools. Gartner.
[6] Wilkins, M. (2019). Learning Amazon Web Services (AWS): A hands-on guide to the fundamentals of AWS Cloud. Addison-Wesley Professional.
[7] Kumar, C. V. A., Eemani, A. K., Kalluri, G. C., & Rudra, G. (2024). A survey on automated student evaluation and analysis using machine learning. World Journal of Advanced Research and Reviews, 21(3), 2547-2554.
[8] Jabbour, J., & JanapaReddi, V. (2024). Generative AI agents in autonomous machines: A safety perspective. In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design (pp. 1-13).
[9] Rikap, C., & Lundvall, B. Å. (2021). Amazon and Microsoft: Convergence and the emerging AI technology trajectory. The Digital Innovation Race: Conceptualising the Emerging New World Order, 91-119.
[10] Prashanth, K., & Rahul, K. (2023). Automate agent evaluations with Amazon Connect and generative AI. AWS re: Invent 2023.
[11] Buddha, J. P., Beesetty, R., Buddha, J. P., & Beesetty, R. (2019). Simple Queue Service. The Definitive Guide to AWS Application Integration: With Amazon SQS, SNS, SWF and Step Functions, 59-138.
[12] de Oliveira Donas-Botto, R. F. (2018). A Framework for Dataflow Orchestration in Lambda Architectures.
[13] Malawski, M., Gajek, A., Zima, A., Balis, B., & Figiela, K. (2020). Serverless execution of scientific workflows: Experiments with hyperflow, AWS lambda, and Google Cloud functions. Future Generation Computer Systems, 110, 502-514.
[14] Diagboya, E. (2021). Infrastructure Monitoring with Amazon CloudWatch: Effectively monitor your AWS infrastructure to optimize resource allocation, detect anomalies, and set automated actions. Packt Publishing Ltd.
[15] Prashanth Krishnamurthy, Revolutionizing Contact Center Performance – The Power of AI-Driven Agent Evaluations, techbullion, 2024. online. https://techbullion.com/revolutionizing-contact-center-performance-the-power-of-ai-driven-agent-evaluations/
[16] Pu, M., Wang, A., Chang, A., Quan, K., & Zhou, Y. W. (2024). Exploring Amazon Simple Queue Service (SQS) for Censorship Circumvention. Free and Open Communications on the Internet.
[17] Hernández, S., Fabra, J., Álvarez, P., & Ezpeleta, J. (2013). A reliable and scalable service bus based on Amazon SQS. In Service-Oriented and Cloud Computing: Second European Conference, ESOCC 2013, Málaga, Spain, September 11-13, 2013. Proceedings 2 (pp. 196-211). Springer Berlin Heidelberg.
[18] Ding, S., & Raman, V. (2024, June). Harness the Power of Generative AI in Healthcare with Amazon AI/ML Services. In 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI) (pp. 490-492). IEEE.
[19] Ramadan, Z., F Farah, M., & El Essrawi, L. (2021). From Amazon. Com to Amazon. Love: How Alexa redefines companionship and interdependence for people with special needs. Psychology & Marketing, 38(4), 596-609.
[20] Chinamanagonda, S. (2021). AI-driven Performance Testing AI tools enhance the accuracy and efficiency of performance testing. Advances in Computer Sciences, 4(1).
