harnesses

2 articles.

• 8 Sep 2026

  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.

• 6 Sep 2026

  Harness Engineering for Self-Improving Agents

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