A g

Building intelligent agent systems, LLMs, and AI architectures

• The Protocol Firm

  Published: 19 Sep, 2026 |  at  05:00 PM

  AI makes more intelligence available to the firm, allowing execution capacity to grow without a proportional increase in human effort at the point of execution. The Protocol Firm asks how delegated authority remains governable, testable and open to correction.

• celld: Durable Objects, Unbundled

  Published: 13 Sep, 2026 |  at  11:00 AM

  celld, a new open-source project from Deno, reimplements Cloudflare's Durable Objects model on infrastructure you own — and it's a good lens for asking what should actually own an AI agent's state.

• Why Agents Make Good Actors

  Published: 28 Jun, 2026 |  at  11:00 AM

  AI agents are stateful, long-running, and mostly idle. That's not a quirk — it's a specification. The actor model was built for exactly this shape of work.

• Designing environments for RL

  Published: 29 May, 2026 |  at  11:00 AM

  Most RL writing is about algorithms. In practice, environment design — the state, action, and reward decisions that sit between your system and the algorithm — is where projects succeed or fail. This is the part that almost never gets covered.