Background in cognitive science and neuroscience. I work for g2.com as an AI operations specialist, I build AI agents for the team working primarily in vertexAI. I've built Merger & Acquisition, category cleaning, and vendor audit agents for my team. All under an orchestrator.

Going deeper on: mechanistic interpretability, multi-agent orchestration beyond coordinator-router patterns, and where cognitive science can inform AI safety/alignment. Looking to connect with builders, agent architects, and researchers working anywhere on that triangle — especially folks pushing past the obvious patterns.

I'm very interested in extracting cause and effect chains from qualitative text at scale and applying those identified tags in rag applications. Aiming for interpretability work next.