An archive of decisions, failures, changes, and shipped work. The record stays useful by keeping the sequence—and the limits—visible.
Why an agent that can modify its own harness needs a separate boundary between authoring the next candidate and trusting it as the next baseline.
Give an agent a rulebook. It can act within the rules written there.
A reconstructed failure reflection on why AI-assisted work needs exact source identity, bounded verification, and evidence that matches each transition.
Why agent architecture becomes easier to replace, debug, and govern when reusable execution and host-application authority have separate owners.
A model-churn test for agent architecture: micro-orchestration may decay as models improve, while context structure, tools, boundaries, state, and scaffolding retain value.
Why a stable agent name is not enough to identify the exact configuration that evaluation, debugging, reproduction, and rollback actually apply to.
Faster agent implementation shifted Dream Atlas's bottleneck from producing changes to establishing what was reviewed, verified, and authorized.
A task can use hierarchy, delegation, and specialist roles without turning them into permanent agents. Persistence is a separate architecture decision.