I am an AI Architect at CareFirst BCBS and Adjunct Data Scientist at Mount Sinai. I have spent years deploying AI in healthcare and insurance environments where a wrong automated decision means a patient gets denied care or a claim gets processed incorrectly.

Agent Sentinel is what I wish had existed in every system I ever built. My co-founder Kaustav Mukherjee is a Mount Sinai researcher with an active NIH grant.

Feedback on Agent Sentinel's technical approach to pre-execution enforcement for AI agents. 
Introductions to AI safety researchers, funders, or engineers deploying AI agents in production 
cloud environments. Design partners willing to test Sentinel on real agent workloads.

Healthcare AI architecture and deployment on AWS. 
RAG systems and enterprise LLM integration. 
AI safety guardrails for production systems. 
Grant writing for AI and clinical research projects.