Articles

Harness engineering, context architecture and production agent systems. Plus an archive of earlier work on Redis-based NLP pipelines.

• 8 Sep 2026 5 min

  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.

  Read
• 7 Sep 2026 10 min

  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

  Read
• 6 Sep 2026 6 min

  Harness Engineering for Self-Improving Agents

  Proposed reference pattern for supervised feedback loops that make AI agent behavior measurable and improvable

  Read