Intuit's Customer-Centric Observability Journey Using AIOps

Explore Intuit's journey in implementing customer-centric observability using AIOps in this 24-minute conference talk. Discover how Intuit, running approximately 2500 services on Kubernetes, tackled the challenge of identifying customer impact and causal services to improve Mean Time to Detect and Respond (MTTD/R). Learn about their innovative approach to analyzing massive amounts of real-time data using Numaproj, an open-source project, along with other CNCF technologies. Gain insights into the implementation of Numaflow, a stream processing platform, and Numalogic, a collection of ML models, to compute normalized anomaly scores for every data point. Understand how this solution helped Intuit establish a cookie-cutter approach to reduce MTTD from over 30 minutes to less than 3 minutes, achieving a 98% confidence rate in incident detection based on AIOps-generated scores.