Cloud Operations (CloudOps) is a rapidly growing field focused on the automated management and optimisation of cloud infrastructure which is essential for organisations navigating increasingly complex cloud environments. ABC Org is one of the major companies in the CloudOps domain that leverages autonomous bots to manage cloud compliance, security and continuous operations. In order to make their platform more accessible and effective to the customers, ABC worked with us to leverage the use of GenAI.

Developing a GenAI-based solution for autonomous CloudOps for the existing ABC system presented us with various challenges such as: i) diverse data sources; ii) orchestration of multiple processes and iii) handling complex workflows to automate routine tasks. To this end, we developed a multi-agent framework that leverages GenAI and balances autonomy with the necessary human control. This framework integrates various internal and external systems and is optimised for factors like task orchestration, security, and error mitigation while producing accurate, reliable and relevant insights by utilising Retrieval Augmented Generation (RAG). Evaluations of our multi-agent system with the help of practitioners as well as using automated checks demonstrate enhanced accuracy, responsiveness, and effectiveness over non-agentic approaches across complex workflows.