Trio Health

A search platform that became an agentic platform

Trio Health builds custom datasets for highly specific rare diseases. How we designed an agentic search system capable of extracting meaningful insight from billions of clinical patient notes.

AWS EKS + KEDATurbopufferBM25 + semantic hybridGPU embedding pipeline

A two-week CLI sprint for an LLM evals platform

An LLM evaluation and observability platform needed a developer-grade CLI: onboarding, prompt-status, trace and session browsing, and a tree-view TUI that worked for humans and agents alike. Designed and shipped end-to-end in about two weeks, with the web app as a companion rather than a competitor.

TypeScriptNode CLITree-view TUIREST + OpenAPIGitHub ActionsTOON output for agents

vibecheck — a YAML-first eval framework for any LLM

An agent-evaluation framework built around a simple YAML DSL. Compare models, save suites, mix string matching with semantic and LLM-judge checks, and run multi-model evals from the command line. Open source CLI, hosted service in invite-only preview at vibescheck.io.

TypeScriptnpm CLIYAML DSLMulti-provider LLM (OpenRouter)Semantic + LLM-judge checksClaude Code skill / MCP testing
Taffrail

An MCP server for a wealth-advisory rules engine

Taffrail runs the rules engine behind Advice-as-a-Service for wealth and financial advisory teams. Wrapped the rules engine and the OpenAPI surface in two MCP servers so AI agents and developer tools (Cursor, Claude Desktop, Windsurf) can query live financial advice — not hallucinated approximations of it.

Model Context ProtocolOpenAPITypeScriptCursor / Claude Desktop / Windsurf