Blog
Deep dives on AI engineering, Rust, and the systems that run agents safely in production. The full archive lives on Substack.
Context, Harness, Loop
draft
The model is fixed. Everything that makes one agent reliable and another useless lives in three layers around it: what it sees, what it can do, and how its steps become a task. Jul 2026 Inside Aster's Sandbox Orchestrator
How Aster runs untrusted code-review agents safely: a Rust backend, a self-hosted Docker orchestrator, and ephemeral containers that clean up after every run. Jul 2026