Now

Updated May 2026 · Boulder, CO

Research

MissionControl — building a production-grade multi-agent orchestration framework. The core design question: what does it take to run agent fleets with real operational rigor? Current focus is task durability, mesh-based inter-agent messaging, and evaluation frameworks that catch failure modes before they reach production. Delivering agent skills, sub-agents, and MCP integrations as first-class artifacts.
Agent evaluation — developing methods for measuring agentic system reliability in enterprise contexts, where failure modes are often subtle and the cost of errors is real. Most existing evals assume clean inputs and well-specified tasks. Production doesn't look like that.

Principal Forward Deployed Engineer at Alteryx. Embedded with strategic enterprise customers building production AI applications — shipping working systems, not decks. Current engagements involve agent-native workflows in organizations navigating complex legacy infrastructure and real data governance constraints. Codifying what works into repeatable deployment patterns for the broader practice.

What the right abstraction layer for enterprise agent orchestration looks like — and why the gap between "it works in a notebook" and "it runs in production" is still so wide for most organizations deploying LLMs at scale.
How frontier model capability improvements are changing the economics and architecture of agentic systems. The answer is shifting faster than most enterprise deployment patterns can keep up with.
The organizational conditions that determine whether enterprise AI deployments compound or decay. High agency and the ability to navigate ambiguity in complex organizations matter as much as the technical implementation.

Turning the research and field pattern-matching into writing that's useful for practitioners building and deploying AI systems. Aria drafts; I edit; we ship.