Book
The Book
A field guide to building reliable, evaluable, production-grade agent systems.
Foundations
Six hands-on sections that take you from zero to building your first agent, connecting it to tools via MCP, and drawing the line around what it can safely do.
- 00A How LLMs Actually Work The engineer's mental model for LLMs. Not transformers math. The five things you need to know to build real systems.
- 00B From API Calls to Tool Use How to go from sending text to having the model take actions. Function calling demystified, schema validation, and the bridge from text generator to system component.
- 00C Your First Agent, No Framework Build a complete agent in 100 lines of Python. No framework. No magic. Every line explained, including the ones where it breaks.
- 00D The Same Agent, With a Framework The same agent rebuilt with Google ADK and LangChain. Side-by-side comparison with eval scores. What frameworks give you, what they hide, and how to choose.
- 00E Connecting Your Agent to MCP Build an MCP server from scratch and connect your agent to it. The standard protocol for giving AI agents access to tools, data, and services.
- 00F The Production Boundary An LLM gets dangerous not when it speaks but when it acts. What every tool call really asks for, and the boundary that turns an agent into a system component you can trust.
Part I · Build
From components to multi-agent systems.
- 01 What "Agentic" Actually Means What makes a system agentic? Precise definitions of LLM apps, workflows, tool-using systems, agents, and multi-agent systems for engineers.
- 02 Tools, Context, and the Agent Loop How tool-using agents work: function calling, context window management, the agent loop, and writing a working agent without a framework.
- 03 Workflow First, Agent Second Why you should reach for deterministic workflows before agents. Decision criteria, architecture comparison, and the engineering instinct that saves production systems.
- 04 Multi-Agent Systems Without Theater When multi-agent systems are justified and when they are complexity theater. Patterns, coordination overhead, and honest cost analysis.
Part II · Judge
Oversight, evaluation, and knowing when to stop.
- 05 Human-in-the-Loop as Architecture Human-in-the-loop as a first-class architectural decision. Approval gates, escalation policies, audit logging, and the Incident Runbook Agent.
- 06 Evaluating and Hardening Agents How to evaluate and harden production agent systems. Metrics, adversarial testing, regression suites, and the difference between opinions and evidence.
- 07 When Not to Use Agents The most important chapter: when not to use agents. Decision framework, anti-patterns, and honest retrospective on simpler alternatives.
Part III · Operate
Production reality.
- 08 Metacognition and Self-Reflection Production patterns for agent metacognition: loop detection, quality assessment, cost-aware planning, and sycophancy defense.
- 09 Deploying and Scaling Deploying and scaling agent systems: durable execution, observability, autoscaling, and real production failures.
- 10 Governance and Auditability Agent governance and auditability: decision traces, compliance boundaries, risk tiers, and policy engines.
- 11 Security Deep Dive Security deep dive for agent systems: the Lethal Trifecta, defense in depth, MCP security, and red teaming.
Part IV · Advanced
Memory and protocols at scale.
- 12 Memory Management Memory management for production agents: session memory, long-term learning, multi-agent coordination, and memory security.
- 13 Agent Protocols in Production MCP, A2A, and AIP in production: building enterprise MCP servers, cross-boundary agent collaboration, identity and delegation chains, and production pitfalls.