Now
The current chapter and operating focus.
Building AI products and turning this site into a public identity graph, research archive, and proof-of-work index.
Updated
June 11, 2026
This page is the public snapshot for what deserves attention right now.
Founder-led AI product work
Founder / Builder / Remote
Building practical AI products and a public archive around search, agents, tools, writing, and learning.
- Turning personal context into an owned-domain identity graph.
- Designing tool and writing systems that can be extended through Sanity.
- Building around AI search, agent workflows, and founder-led product loops.
Active questions
The ideas still being worked through.
AI agents become a personal operating layer
How much autonomy people will actually trust in high-stakes work without clear controls and audit trails.
medium confidence
Search becomes an answer and action interface
Which interfaces will earn enough trust for complex decisions: search boxes, browsers, agents, or embedded workflows.
medium confidence
Personal sites become identity infrastructure
Which agent-facing conventions will become durable standards versus useful-but-optional affordances.
high confidence
Operating principles
How the site should keep improving.
Context first: explain the life chapter behind the work, not only the resume line.
Writing as memory: turn books, articles, projects, and lessons into durable notes.
Tools are part of the story: interactive work should sit beside essays and experience.
Agent-friendly by default: keep site context, content models, and editorial direction documented in the repo.