Skill
4 entries mention it. All skills →
Wrote about experiments with Cedar and how hard it is to manage security policy at scale.
Cedar, Policy-as-code, Security architecture
On the clinical product I worked on structured extraction, evaluation (including LLM-as-judge), prompt versioning, tracing each statement back to its source, and protecting sensitive data.
Structured extraction, LLM evaluation, LLM-as-Judge, Prompt versioning, Provenance, Security architecture
Worked on identity and authorization between services, and between agents and their tools, using least privilege and avoiding shared secrets.
OAuth2, OIDC, Workload identity, Agent authorization, Security architecture
Tried keeping request-blocking rules in one place, so whatever enforces them, the browser or the router, can be swapped.
Policy modeling, HTTP analysis, Browser tools, Router integration, Security architecture