Cleric AI SRE - Towards Self-healing Autonomous Software

Explore the development of AI-powered Site Reliability Engineering in this technical talk that delves into Cleric's autonomous agent system designed for monitoring, diagnosing, and resolving issues in complex distributed systems. Learn how autonomous SRE agents can handle novel situations, continuously adapt to their environment, and respond to system failures at superhuman speeds. Discover the technical architecture behind creating AI systems capable of understanding system architectures, reasoning about failures, and taking independent corrective actions. Gain insights from Willem Pienaar, co-founder and CTO of Cleric, creator of the open-source feature store Feast, and former engineering leader at Tecton and Gojek, as he shares his extensive experience in building and scaling production AI systems across major tech companies including Google, Apple, Cloudflare, Shopify, and Robinhood.