Jamie's Blog

The curious developer's ODYSSEY, Exploring the Universe of TECH, CODE & AI.

Building Eval Literacy & Red-Teaming for Multi-Agent AI Code Review

How to upgrade an AI Agent from a 'working prototype' to an empirical, production-grade review system with OWASP 2026 Agentic Security defenses.

Posted by Jamie Zhang on Sunday, August 23, 2026

The Self-Declaration Principle: Why Handoffs Only Works When Agents Know Their Own Edges

Self-declaration is not an optional enhancement to Handoffs — it's what makes Handoffs a coherent pattern. A conversation with Claude uncovered the design principle that every multi-agent framework tutorial quietly skips.

Posted by Jamie Zhang on Wednesday, July 8, 2026

Multi-Agent Architectures: The Diagrams the Numbers Are Hiding

A companion to LangChain's 'Choosing the Right Multi-Agent Architecture' — full sequence diagrams and call-by-call token math for Skills, Handoffs, and Router, not just Subagents.

Posted by Jamie's Blog on Tuesday, June 23, 2026