Memory and governance are enterprise AI's defining problems in 2026. Organizations scaling AI hit the same wall: dozens of agents touch the same customers, deals, and accounts, but none of them share memory, enforce schemas, or follow the same organizational rules. I call the root cause the memory governance gap.
I'm the co-founder and Product Lead of Personize.ai, where we build governed memory infrastructure for enterprise AI agents — schema-enforced extraction, organizational context routing, and quality feedback loops that make multi-agent workflows reliable at scale.
I designed the core architecture: dual memory stores (vector search and structured serving), governance routing by authority rather than semantic similarity, and the extraction pipelines that turn raw interactions into structured entity knowledge. The architecture is deployed in production across 60+ B2B customers and documented in peer-reviewed research.
Before Personize, I shipped AI and data products across startups and enterprises for 15+ years, staying hands-on across architecture, data modeling, ML systems, and cloud infrastructure.
I write here about what I'm building and what governed memory enables that hasn't been fully explored yet. Builder's notebook, not a marketing channel.
I live and work in Vancouver.