I'm the Lead Engineer of the Agents team at Hypha — the platform's intelligence foundation. I define how Hypha builds agents: harness, infrastructure, evals, and applied AI research.
Many engineers think of Agent Tools as functions, but they aren't. They are closer to user actions. Backed by a leave-one-out ablation study: 300+ runs across the Codex SDK and the Claude Agent SDK.
More posts on agent infrastructure, evals, and reliability are coming — most will run on the Hypha engineering blog. I post shorter notes on LinkedIn and X.
The builder's guide to GPT‑5.6Luna keeps 98% of GPT‑5.5's extraction accuracy at one-eighteenth the cost. That gives our agents high-quality document understanding at a price that makes it practical across many more workflows.
Lead Engineer of the Agents team — Hypha's intelligence foundation. Created the agent platform: a harness-agnostic framework with pluggable intelligence, compute, and storage providers; its eval harness (pass@k, cache-hit-rate, trace-shape fidelity); and the external MCP server.
Built autonomous browser agents for insurance operations.
Led a 10-person team automating healthcare workflows; President's Award, 2024.