Shahram Anver
Co-Founder & CEO at Cleric | Building the first autonomous AI SRE
Actions
Shahram Anver is the Co-Founder and CEO of Cleric, where he's building an autonomous AI SRE that investigates and resolves production incidents 24/7. Before Cleric, Shahram led engineering for MLOps, container deployment, and FinOps platforms at Gojek, Southeast Asia's largest super-app, managing infrastructure handling millions of daily transactions across hundreds of microservices. He previously built TripAdvisor's first ML automated bidding system, scaling it to manage tens of millions in annual ad spend, and co-founded DataCue, an ML-driven e-commerce personalization platform.
Patterns to Build a Self-Learning AI Agent
AI agents are shifting from prompt-and-respond to autonomous background workers. Instead of waiting for an engineer to ask a question, they continuously watch infrastructure, learn from how teams work, and surface problems before anyone gets paged. No prompting required. This pattern is spreading across the entire dev lifecycle, from code review to deployment to monitoring to incident response.
These agents also need to capture engineer intent: the implicit SLOs, the acceptable degradations, and the tribal knowledge that determines whether something is a bug or a feature. This talk covers how we build agents that operate autonomously in the background, how they learn what engineers care about without constantly asking, and the failure modes when captured intent goes stale.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top