---
title: "Book Review: Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems"
pubDate: 2026-03-29T00:00:00.000Z
updatedDate: 2026-03-29T00:00:00.000Z
tags:
  - AI
image: /images/blog/agentic-design-book-review/featured.png
---

# Overall verdict

*Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems*
https://github.com/DanieleSalatti/AgenticDesignPatterns/blob/main/Agentic_Design_Patterns.pdf

Springer edition: https://link.springer.com/book/10.1007/978-3-032-01402-3. It costs 50 euros.

Some of its high-level concepts still hold up, but the text descriptions are more useful than the code examples. I prefer Pydantic AI to the frameworks used in the book (LangChain, Google ADK, and Agent Crew), and found some examples distracting. The sections promoting Google products, particularly Agent2Agent and Gemini ADK, can be skipped; the author's bias is fairly clear given that they work at Google.

## Chapter 1: Prompt Chaining 
Useful concept, although LangChain Expression Language feels like overkill here.

## Chapter 2: Routing

Very useful concept: divide and conquer.

## Chapter 3: Parallelization

Useful for reducing latency, though the value depends on how important latency is in the specific use case.

## Chapter 4: Reflection

Useful for advanced agentic systems, though reasoning models have absorbed the classic self-critique loop in many settings.

## Chapter 5: Tool Use

At the time of writing, agent skills were still in their infancy, which makes this chapter feel somewhat outdated.

## Chapter 6: Planning

Useful for advanced agentic systems. If the steps are known in advance, routing is often enough; Cursor's "Plan Mode" is a good example of when planning earns its place.

## Chapter 7: Multi-Agent 

This chapter is thin relative to how much the field has moved since publication. Cursor's experiments with self-driving codebases are particularly noteworthy: https://cursor.com/blog/self-driving-codebases

See also https://ai.pydantic.dev/multi-agent-applications/.
Another useful search term is "agent swarms."

## Chapter 8: Memory Management

This is one area where agent frameworks differ meaningfully. In Pydantic AI, some of the same ideas would be implemented via https://ai.pydantic.dev/dependencies/, which is more general than memory management but can also handle it.

## Chapter 9: Learning and Adaptation

This seems overhyped and not especially useful in practice for production use.

## Chapter 10: Model Context Protocol (MCP)

The distinction between tool use and MCP is not explained clearly. Conceptually, MCP is a structured way to implement tool use: it defines a protocol for how an agent interacts with tools, while tool use can also be implemented ad hoc.

In practice, the conceptual difference between the two is not very important, especially if you use agentic coding.

Developments since publication:

- https://pydantic.dev/articles/pydantic-monty
- https://blog.cloudflare.com/code-mode/
- https://www.anthropic.com/engineering/code-execution-with-mcp

## Chapter 11: Goal Setting and Monitoring 
Think of the TODO list in Cursor's "Plan Mode" as a practical example of goal setting and monitoring.

Since publication, [Karpathy's autoresearch](https://github.com/karpathy/autoresearch) has taken this further with a self-driving codebase that conducts deep-learning research. The agent sets goals, monitors progress, and adapts its strategy.

## Chapters 12–14

Chapter 12 covers Exception Handling and Recovery; Chapter 13 covers Human-in-the-Loop; and Chapter 14 covers Knowledge Retrieval (RAG).

## Chapter 15: Inter-Agent Communication (A2A)

This reads as advertising for Google's Agent2Agent protocol, which has not seen much adoption. MCP can also support inter-agent communication and is more widely adopted. Skip this chapter.

## Chapters 16–21

Chapter 16 covers Resource-Aware Optimization; Chapter 17, Reasoning Techniques; Chapter 18, Guardrails/Safety Patterns; Chapter 19, Evaluation and Monitoring; Chapter 20, Prioritization; and Chapter 21, Exploration and Discovery.