Work
Things I've built and written: open-source systems with the internals laid out, products, and shorter notes on what I learned along the way.
InstaLILYCase studySummer 2026
Lily-Eval: turning a codebase's merged PRs into a resettable environment for a coding agent
An evaluation environment for Lily, InstaLILY's coding agent, built by rewinding production repos to just before real merged PRs and grading the agent's blind reimplementation. It ran a 276-trial head-to-head against Claude Code and became the reward signal for tuning Lily's harness.
Stuart LabsProductAug–Oct 2026, ongoing
Outreach CRM
A multi-tenant CRM for student networking outreach. AI drafts each message from facts on file, the student sends it, and the whole pipeline doubles as an OAuth-protected MCP server that their own agent can work.
Cornell Generative AICase studySpring 2025 – present
Running Cornell Generative AI like a startup
As president of Cornell's student AI engineering club, I rebuilt how we hire, delivered client work for two finance firms, led the move to our own products, and built the club's operations platform with coding agents.
Stuart LabsOpen source2025–2026
HomeAssist and Tool-Calling Mini
An always-on voice assistant that I rebuilt from a Raspberry Pi prototype into an interruptible, proactive agent on the OpenAI Realtime API. Tool-Calling Mini is my QLoRA fine-tune of Qwen3-4B that can take over its tool routing from a self-hosted server.
Cornell CS 4701Open sourceFall 2026
HIVE: an eval-gated loop for improving agent harnesses
A Cornell CS 4701 project that freezes the model and lets a Claude Code overseer propose harness edits, kept only when they beat the current best on a graded suite. The scaffold runs end to end; so far it has run dry runs, not experiments.
Stuart LabsOpen sourceOctober 2026
echo-OS
A macOS menu bar tool that speaks a short headline when a long Claude Code turn finishes, tagged with the project folder and a per-session call sign, so I can leave several agents running and hear which one is done.
Stuart LabsOpen sourceSpring 2026
AgenticNodes
A local graph editor and runtime for agent workflows. You wire model, tool and data nodes on a canvas, run the graph, and inspect every node and edge event in per-agent swimlanes.
InstaLILYEssayJuly 2026
Build the Environment, Then Optimize the Harness
InstaLILY's two-part report on coding agents argues for mining merged PRs into a resettable environment and measuring its noise before letting an optimizer tune the harness. I led the evaluation work in Part 1.