Agentic AI Harness Pattern: The Top 15 Patterns Learned from Leaked Claude Code and Hermes Agent

Most AI tutorials teach you prompts. This book teaches you patterns.Production AI engineering — the discipline of turning a language model into something reliable, safe, auditable, and shippable — is mostly undocumented. The libraries churn every quarter. The patterns endure.Agentic AI Harness Pattern distills 15 of those patterns by reading two mature production codebases side by side: Claude Code, Anthropic's TypeScript CLI for agentic coding, and Hermes, a Python agent built to run across messaging platforms. The two systems make different language choices, different concurrency choices, and different deployment choices — but the harness pattern they implement is the same.Every chapter follows the same rhythm:Name the pattern. What problem is the harness solving?Show Claude Code's implementation in real TypeScript.Show Hermes's implementation in real Python.Compare them as a table. Where do they diverge, and why?Recommend when to use which. A decision rule, not a hot take.Apply the pattern to a defensive cyber-security agent. A worked example that shows the pattern under operational pressure. Inside the 15 patternsThe Harness Paradigm — why a model alone is not a productTool Architecture and the Tool Contract — the boundary between reasoning and consequenceThe Query / Agent Loop — what happens between the model's tool call and the next turnPermission Systems and Safety Guardrails — gating the destructive setTool Orchestration and Execution — partitioning safe vs. serial workContext Management at Scale — the five strategies before compactionMulti-Agent Coordination — when one agent isn't enoughMemory Systems and State Persistence — three tiers, one cacheObservability and Debugging — distributed tracing for non-deterministic systemsProduction Deployment Patterns — SDK-first vs. gateway-firstHook / Event-Driven Automation — the layer above the loopThe Skill System Pattern — capabilities as content, not codeMCP Integration — connecting agents to the worldModel Routing and Provider Abstraction — falling back without falling overStructured Output and Schema-Constrained Generation — when free text isn't enough Who this book is forEngineers building AI products who keep hitting the same architectural questions and want vetted answers.Architects and tech leads making the build-vs-buy-vs-wrap decision for an agent platform.Security and compliance reviewers who need to understand how a production agent enforces a destructive-action gate, an audit trail, and an iteration budget. Each chapter stands alone. Read what you need; read end-to-end and the patterns compound. Either way, you'll close the book with a working mental model of how to design an AI agent that survives contact with production. About the authorsKen Huang is CEO of DistributedApps.ai, advising organizations on production-grade agent deployment at the intersection of AI, distributed systems, and security.Grace Huang is a Product Manager and AI Engineer at PIMCO, where she ships AI features for the world's largest fixed-income asset manager. Her focus is the engineering rigor that makes AI products trustworthy in regulated environments.The model is intelligence. The harness is the system.Start here. Read more