Writing

Writing

Field notes and research on AI agents, distributed systems, and the things that break.

Field notes

Notes from work in progress, written when there is something useful to say.

Dispatch Nº 005 — London · August 2026

Testing Celln's Boundary

Four boundary probes and one successful computation: what a small Celln demonstration shows, and what it leaves untested.

Read essay ↗
Dispatch Nº 004 — London · August 2026

The Agent Environment Should Be a Lease

Why I built Celln to lend agents a defined capability set, and what that execution model still needs to prove.

Read essay ↗
Dispatch Nº 003 — London · July 2026

Post-Kubernetes Infrastructure for GenAI Workloads

Field notes on Modal's million-sandbox announcement, what it says about Kubernetes' assumptions, and the coming decoupling of coordination from execution.

Read essay ↗
Dispatch Nº 002 — London · May 2026

The Sticky-Note Problem: Making Agent Handoffs Reliable

Why agent handoffs lose context, and how shared evidence and explicit ownership can make coordination more reliable.

Read essay ↗
Dispatch Nº 001 — London · April 2026

Agents Need Somewhere to Share Their Work

What makes agents useful as a team, and how a shared, policy-controlled workspace might help.

Read essay ↗

Research papers

Longer technical work. Papers may be revised as the implementation develops.

paper · v2.2 · September 2026

The Synthetic Membrane: A Coordination Layer for Multi-Agent AI Systems

Revised position paper defining a coordination contract for shared evidence, selective access, and action ownership, with explicit limits and an evaluation plan.