Work
Engineering case studies from two decades in the industry.
OTTER: Transforming on-call with multi-agent AI incident triage
Architecting a system that ingests production incidents, queries telemetry through 33 MCP tools, and learns from engineer feedback to automate root cause analysis.
Observability at hyperscale: telemetry anomaly detection across datacenters
Building KQL pipelines to detect SSO latency anomalies across datacenter hops, and solving the meta-problem of telemetry systems becoming their own bottleneck.
Building a coding agent before the category existed
An auto-PR-from-tickets system at Microsoft, and what it taught us about the architecture decisions the industry would rediscover years later.
OnePayment: Unifying payment processing across acquired brands at Expedia
How we consolidated five different payment systems across Expedia's portfolio brands into a single platform over three years.
Copilot for Whiteboard: AI-powered collaboration at Microsoft scale
Bringing LLM-powered suggestions and automations to real-time collaboration across Web, iOS, Android, Surface Hub, and Teams Rooms.