Agentic AI for Serious Engineers¶
Build trustworthy AI systems, not demos.
This book teaches you when to build an agent, when not to, and how to make the ones you build survive production. It threads a single project from first principles through production hardening, using working Python code that you can read, run, and adapt.
Chapter 1 is available here as a free sample. The full book is available on Amazon.
Foundations¶
Not familiar with LLMs or the basics of function calling? Start here before diving into the chapters. These four sections take you from zero to a working agent -- no framework required.
| # | Section | What you learn |
|---|---|---|
| 0a | How LLMs Actually Work | The engineer's mental model: APIs, tokens, context, hallucination |
| 0b | From API Calls to Tool Use | Function calling, schema validation, giving the model hands |
| 0c | Your First Agent, No Framework | Build a complete agent in 100 lines. See it work. See it break. |
| 0d | The Same Agent, With a Framework | ADK and LangChain side-by-side. Eval comparison. Choose with data. |
| 0e | Connecting Your Agent to MCP | Build an MCP server, connect your agent to real tools and services. |
Start with the Foundations if you are new to agentic AI. Skip ahead to Chapter 1 if you are already comfortable with LLM APIs and tool calling.
Chapters¶
Part I: Building
| # | Title | Focus |
|---|---|---|
| 1 | What "Agentic" Actually Means | Precise definitions, comparison table, decision map |
| 2 | Tools, Context, and the Agent Loop | Tool registry, context pipeline, first working agent |
| 3 | Workflow First, Agent Second | Same task two ways -- the key architectural decision |
| 4 | Multi-Agent Systems Without Theater | Coordination patterns, MCP, A2A, AIP protocols |
Part II: Judging
| # | Title | Focus |
|---|---|---|
| 5 | Human-in-the-Loop as Architecture | Approval gates, escalation, and audit trails |
| 6 | Evaluating and Hardening Agents | Eval, tracing, reliability, cost, security |
| 7 | When Not to Use Agents | The signature chapter -- engineering judgment |
Part III: Operating
| # | Title | Focus |
|---|---|---|
| 8 | Metacognition and Self-Reflection | Loop detection, quality assessment, strategy switching |
| 9 | Deploying and Scaling Agent Systems | Durable execution, observability, autoscaling |
| 10 | Agent Governance and Auditability | Decision traces, compliance boundaries, risk tiers |
| 11 | Security Deep Dive | The Lethal Trifecta, defense in depth, red teaming |
Part IV: Advanced Patterns
| # | Title | Focus |
|---|---|---|
| 12 | Memory Management | Session, long-term, shared memory, memory security |
| 13 | Agent Protocols in Production | Enterprise MCP, A2A at scale, AIP delegation chains |
The Running Example: Document Intelligence Agent¶
Every chapter uses the same project -- a Document Intelligence Agent that ingests documents, answers questions with citations, and knows when it does not know enough to answer. The project code lives in src/ and the project documentation lives in the Document Intelligence Agent project page.