Sara Mo

AI agent evaluation, Harness Engineering, Python, LLM applications, agent systems, evaluation design, test design, LangGraph, LangChain, SQL, PostgreSQL.

Nugalaxy: building practical evaluation frameworks for AI agents, focused on behavioral requirements, edge cases, evidence, and proving whether an agent actually works as required.

AI agent evaluation, Harness Engineering, and technical collaboration. Say hey if you're building an AI agent and need to prove it works as required.