What do you think?
Rate this book
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 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
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 patterns
The Harness Paradigm — why a model alone is not a product
Tool Architecture and the Tool Contract — the boundary between reasoning and consequence
The Query / Agent Loop — what happens between the model's tool call and the next turn
Permission Systems and Safety Guardrails — gating the destructive set
Tool Orchestration and Execution — partitioning safe vs. serial work
Context Management at Scale — the five strategies before compaction
Multi-Agent Coordination — when one agent isn't enough
Memory Systems and State Persistence — three tiers, one cache
Observability and Debugging — distributed tracing for non-deterministic systems
Production Deployment Patterns — SDK-first vs. gateway-first
Hook / Event-Driven Automation — the layer above the loop
The Skill System Pattern — capabilities as content, not code
MCP Integration — connecting agents to the world
Model Routing and Provider Abstraction — falling back without falling over
Structured Output and Schema-Constrained Generation — when free text isn't enough
Who this book is for
Engineers 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.
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 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
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 patterns
The Harness Paradigm — why a model alone is not a product
Tool Architecture and the Tool Contract — the boundary between reasoning and consequence
The Query / Agent Loop — what happens between the model's tool call and the next turn
Permission Systems and Safety Guardrails — gating the destructive set
Tool Orchestration and Execution — partitioning safe vs. serial work
Context Management at Scale — the five strategies before compaction
Multi-Agent Coordination — when one agent isn't enough
Memory Systems and State Persistence — three tiers, one cache
Observability and Debugging — distributed tracing for non-deterministic systems
Production Deployment Patterns — SDK-first vs. gateway-first
Hook / Event-Driven Automation — the layer above the loop
The Skill System Pattern — capabilities as content, not code
MCP Integration — connecting agents to the world
Model Routing and Provider Abstraction — falling back without falling over
Structured Output and Schema-Constrained Generation — when free text isn't enough
Who this book is for
Engineers 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.
447 pages, Kindle Edition
Published May 9, 2026
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
No one has reviewed this book yet.