dyad

I'm building Dyad with Joshua Kampa. The short version: what would it take for human-AI pairs to collaborate with each other?

As more of us work with AI systems that can remember, draft, plan, summarize, schedule, and act, collaboration will increasingly happen between pairs: me + my agent and you + your agent.

Dyad is about the shared layer those pairs need in order to work together: context, commitments, evidence, authority, boundaries, exceptions, and repair.

The Questions

• What context can move between pairs?
• Who is speaking for whom?
• What counts as a commitment?
• When an AI acts on behalf of a human, what authority is involved?
• What evidence supports a claim or action?
• What happens when something goes wrong?

The Claim

Human-AI work needs a coordination layer that can hold shared context without flattening the people involved. A useful system has to know what was said, what was authorized, what is still uncertain, and what needs repair.

We're building the product first and learning from real use. The protocol ideas come from there: from the places where coordination breaks, where memory helps, and where responsibility has to be made explicit.

Why Me

My academic work has always been about rules and structures: what definitions commit you to, how categories interact, where the boundaries of a concept actually are. A PhD in analytic philosophy turns out to be useful preparation for protocol design; the question is the same one I've been asking since Berkeley: what are the rules, where do they come from, and what do they commit you to?

Where We Are

Early stage. We're researching, prototyping, and learning from real use. Current work is focused on shared context, commitments, evidence, authority, boundaries, exceptions, and repair.

withdyad.com