Yen Kha
Scaling Trustworthy AI Across Specialized Vertical Domains
San Francisco, California, United States
Actions
I am the Founder of GammaLex AI Inc. and Co-Founder of Justice for All (J4All.org), both launched at Stanford Law School. At GammaLex, I develop vertical AI solutions for high-stakes domains, where AI can meaningfully influence human outcomes, community systems, and long-term sustainability across health, legal technology, and AI infrastructure. Through Justice for All, we collaborate with Google Research to advance access to justice and deliver tangible humanitarian impact.
Links
Area of Expertise
Topics
Policy Agents for Secure Multi-Cloud Automation with Open Protocols
Cloud teams manage increasingly sophisticated environments across AWS, GCP, and Azure. Autonomous policy agents integrate the Pulumi Automation API with the Model Context Protocol (MCP) to deliver secure, policy-aware IaC workflows, reasoning, and compliance automation (HIPAA/SOC2). Agents continuously observe infrastructure, detect policy violations, and perform bounded remediations with human-in-the-loop oversight.
Live demos showcase security patterns, including policy-as-code enforcement, observability hooks, failure recovery, and auditable automation across providers. Attendees will take away extensible blueprints for self-healing, policy-aware infrastructure built on open protocols, ready to adapt to their own multi-cloud environments.
Secure MCP Agents in Practice: Lessons from Dali
AI agents are rapidly moving out of demos and into production. At higher levels of maturity, they are no longer simple assistants but systems trusted to run workflows, keep context over time, adapt when conditions change, and recover from failure. Once agents reach that point, the main challenge is no longer building them, but can we trust them to operate safely?
This talk shares lessons from building Dali, a DevOps agent that manages cloud agnostic infrastructure and deployment pipelines with limited human oversight. Using the Model Context Protocol (MCP), Dali connects language models to tools in an explicit, constrained, and auditable way. I will cover how we define what an agent can do, limit access, decide when humans must be involved, and handle failures and rollbacks.
The session shares lessons from operating autonomous systems in regulated environments, and shows how MCP patterns for access control, orchestration, and failure recovery are critical to ensure agents can operate reliably.
Yen Kha
Scaling Trustworthy AI Across Specialized Vertical Domains
San Francisco, California, United States
Links
Actions
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