Tags
agents
4 articles.
-
The Terraphim Engine: Six Layers, Fifty-Two Crates
How the engine behind this reference architecture is actually decomposed: six layers, single-responsibility crates, and why that boundary discipline is what makes an agent system auditable.
-
The Twelve Core Patterns
The twelve patterns this reference architecture is built from, grouped by the three jobs of an agent harness: context architecture, execution guardrails, and memory infrastructure.
-
The MCP-Native Agent Architecture
Why Model Context Protocol is the missing link between probabilistic LLMs and production-grade agent orchestration — a reference architecture drawn from Terraphim
-
Harness Engineering for Self-Improving Agents
Proposed reference pattern for supervised feedback loops that make AI agent behavior measurable and improvable