LogAn: An LLM-Based Log Analytics Tool with Causal Inferencing
This paper demonstrates ''LogAn'', a first-of-a-kind LLM-powered intelligent log analytics tool that is designed for analyzing the behaviour of applications under faulty conditions. The tool features an intuitive GUI that displays key information, such as error cues or signals from log data, along with various analytics and summaries to assist IT engineers in identifying and understanding critical issues. LogAn has been successfully deployed in production and is now actively utilized by IBM Software Support. Since May 2024, it has processed 1, 376 cases, saving 8094 minutes of support engineers' time. Demo Video Link: https://tinyurl.com/demo-logan
Authors
- Seema Nagar (ORCID: https://orcid.org/0000-0003-1930-7101)
- Prateeti Mohapatra (ORCID: https://orcid.org/0009-0005-1418-0414)
- Debanjana Kar (ORCID: https://orcid.org/0009-0004-2878-5433)
- Karan Bhukar
- Pranjal Gupta (ORCID: https://orcid.org/0000-0002-0344-0859)
- Harshit Kumar (ORCID: https://orcid.org/0009-0000-9126-5634)
Institutions
- IBM Research - India (IN)
Publication Details
- Published
- 2025-05-03
- DOI
- https://doi.org/10.1145/3680256.3721246
- Citations
- 1
- Primary Topic
- Software System Performance and Reliability
- Type
- article
- Field-Weighted Citation Impact
- 1.49