Agent Assist: Automating Enterprise IT Support Help Desks


  • Senthil Mani IBM Research AI
  • Neelamadhav Gantayat IBM Research AI
  • Rahul Aralikatte IBM Research AI
  • Monika Gupta IBM Research AI
  • Sampath Dechu IBM Research AI
  • Anush Sankaran IBM Research AI
  • Shreya Khare IBM Research AI
  • Barry Mitchell IBM Global Business Services
  • Hemamalini Subramanian IBM Global Business Services
  • Hema Venkatarangan IBM Global Business Services



Question Answering, Cognitive Ensemble, IT support, Machine Learning


In this paper, we present Agent Assist, a virtual assistant which helps IT support staff to resolve tickets faster. It is essentially a conversation system which provides procedural and often complex answers to queries. This system can ingest knowledge from various sources like application documentation, ticket management systems and knowledge transfer video recordings. It uses an ensemble of techniques like question classification, knowledge graph based disambiguation, information retrieval, etc., to provide quick and relevant solutions to problems from various technical domains and is currently being used in more than 650 projects within IBM.




How to Cite

Mani, S., Gantayat, N., Aralikatte, R., Gupta, M., Dechu, S., Sankaran, A., Khare, S., Mitchell, B., Subramanian, H., & Venkatarangan, H. (2018). Agent Assist: Automating Enterprise IT Support Help Desks. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).