ManningBooks

ManningBooks

Devtalk Sponsor

Agent Design Patterns (Manning)

AI agents are showing up everywhere—and most of them are being built by trial and error. Agent Design Patterns distills the experience of a growing community of agent builders into 20+ composable, reusable patterns for building AI agents that are reliable, efficient, controllable, and easy to reason about. In this uniquely valuable book, author and NVIDIA Research scientist Peter Belcak gives you a durable engineering vocabulary and design intuition that outlasts any new model release.

Peter Belcak

Agent Design Patterns by Peter Belcak is about moving beyond one-off prompts and treating agents as systems that can be designed, tested, and improved. It introduces reusable patterns for common challenges in agent development, particularly around capability, reliability, and robustness.

The book takes a practical approach. Peter builds a mortgage advisor to demonstrate how the patterns work together, then explores individual patterns such as:

• Errand, for breaking complex workflows into manageable units
• Guardrail, for gating actions and improving reliability
• Resampler, for using repeated sampling to produce more dependable results

Five chapters are currently available through Manning’s Early Access Program. Readers can follow the book as Peter writes it, receive new chapters when they’re released, and send feedback that may help shape the finished book.

If you’re already experimenting with agents, I’d be interested to hear which design problems have caused you the most trouble. For me, the gap between an impressive demo and an agent you can actually depend on is where this topic gets particularly useful.


Don’t forget you can get 45% off with your Devtalk discount! Just use the coupon code “devtalk.com” at checkout :+1:

First Post!

mira_tokarev

mira_tokarev

The distinction between making an agent capable and making it dependable feels important. Guardrails help with the obvious unsafe actions, but recovery after a partial tool failure is where many systems still become brittle. I’d be interested in seeing the patterns tested under interrupted runs: can the agent resume from a checkpoint without repeating side effects, and can it explain why it chose a fallback? Resampling seems useful for ambiguous decisions, but I’d probably reserve it for the steps where uncertainty is measurable rather than making every workflow more expensive.

Where Next?

Popular Ai topics Top

ManningBooks
Before deploying an AI model into production, you need to know more than just its accuracy. Will it be fast enough for your users? Will i...
New
ManningBooks
The bestselling book on Python deep learning, now covering generative AI, Keras 3, PyTorch, and JAX! François Chollet and Matthew ...
New
ManningBooks
AI agent technology is changing fast! This totally revised Second Edition of AI Agents in Action by Micheal Lanham guides you through the...
New
ManningBooks
After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In The RLHF Book, AI expert Natha...
New
ManningBooks
Dr Luca Belli, co-founder and former research lead for Twitter’s Machine Learning Ethics, Transparency and Accountability team, has been ...
New
ManningBooks
Introduction to Generative AI, Second Edition, guides you from your first eye-opening interaction with tools like ChatGPT to how AI tools...
New
ManningBooks
Today’s AI models demand a lot of memory, compute, and server horsepower–which quickly translates into cost. Quantization and Fast Infere...
New
ManningBooks
Building LLM Applications with DSPy introduces DSPy best practices you can adopt to create reliable, production-ready systems through pro...
New
ManningBooks
Build Applications with Local AI Models on a Mac shows you exactly how to build and run a ChatGPT-style assistant entirely on your own Ma...
New
ManningBooks
LLM Customization and Fine-Tuning is a hands-on playbook for turning a general-purpose open-weights model into a focused, cost-efficient ...
New

Other popular topics Top

AstonJ
Or looking forward to? :nerd_face:
503 15149 280
New
Exadra37
I am thinking in building or buy a desktop computer for programing, both professionally and on my free time, and my choice of OS is Linux...
New
New
PragmaticBookshelf
An illustrated guide to understanding and effectively using regular expressions. Staffan Nöteberg To effectively use regular expressi...
New
AstonJ
This is a very quick guide, you just need to: Download LM Studio: https://lmstudio.ai/ Click on search Type DeepSeek, then select the o...
New
AstonJ
Curious what kind of results others are getting, I think actually prefer the 7B model to the 32B model, not only is it faster but the qua...
New
PragmaticBookshelf
This book forgoes the abstract and instead provides concrete examples to help you better leverage the unique properties of Elixir, Erlang...
New
PragmaticBookshelf
Quickly turn complex problems into simple, working solutions using functional programming, safe concurrency, and the expressive tools of ...
New
pragdave
Build robust LLM-powered apps, chatbots, and agents while mastering AI engineering principles that will help you outlast the tools and th...
New
xiji2646-netizen
Woke up to this today: Claude Code’s complete source code exposed via npm source map. Not a snippet. All 512,000 lines. 1,900 TypeScript ...
New