You Live by "If Cannot Also, Must Can." This is our unofficial motto. It's the mindset that no challenge is too big and "no" is not the final answer. It’s about perseverance and an absolute refusal to fail.
Build evaluation harnesses that measure output quality, faithfulness, hallucination rate, latency, and cost across model versions and prompt changes — governing whether AI features ship or roll back.
Demonstrated experience across the Agent Development Lifecycle: specification, harness build, tool and MCP integration, evaluation, deployment, observability, and refinement.