The Weekly Roundup! Don’t miss out on our latest MEAPs and print books!

Save up to 45% on your entire purchase.

Expires midnight PT on May 31st. Only at manning.com.

Note: Final discount will be applied in cart. For products already on sale, the best available discount will be applied.

agents in banks, manufacturers, and AI startups. You’ll appreciate how this book guides you toward system and harness design that impose certainty and reliability on the non-deterministic behavior of LLM-driven agents. Once you catch author Jia Huang’s vision, you’ll stop asking “which tools” and start asking "which patterns”! [Read more]

5 chapters of this new MEAP are available now, with more to follow soon!

production-ready AI systems through task design, evaluation, and optimization. Readers build real applications—including classification systems, summarizers, RAG pipelines, and agentic workflows—using DSPy’s modular architecture without hand-writing prompts. Along the way, the authors provide clear guidance, examples, and proven techniques for creating scalable, dependable LLM applications. [Read more]

6 chapters of this new MEAP are available now with more to follow soon!

alongside the Rust features that make them safer and more expressive. It builds from foundational ideas toward real hardware-focused development in a way suitable for firmware beginners or experienced embedded developers who want to add Rust to their toolbox. [Read more]

4 chapters of this new MEAP are available now with more to follow soon!

JavaScript in Depth >> Chapter 8, “Scheduling” >> Examine how to spot and identify the “monster” that’s causing your code to behave unpredictably, and learn what scheduling has to do with it.  

Build a Multi-Agent System (From Scratch) >> Chapter 6, “Skills” >> Tools alone are not enough for tasks that require multi-step procedures that we want our LLM to perform repeatedly. Learn how to build those procedures into “skills” and enable our LLM to use them, saving yourself valuable time and effort. 

Hidden Influences >> Chapter 6, “The business of RecSys: how platforms make money” >> Drill down into several business models that online platforms employ to make money, examining not only how these models work in practice but also the central role recommender systems play in enabling and optimizing them.  

Building Agentic Applications with CrewAI and MCP >> Chapter 5, “Building multimodal crews”

>> Create an e-commerce crew that does the work for you! Extend the embedding models you’re already familiar with beyond text to the visual domain as you build a 3-agent crew that does the work of creating product listings for e-commerce—freeing you up to do…whatever you want to do!

Authorization in Action >> Chapter 17, “AI in policy practice”, Chapter 18, “Authorization for AI agents”, Chapter 19, “Authorization as strategy”, & Appendix C, “Cedar authorization with OpenClaw agents” >> Explore how AI can play a valuable role in creating and assessing an organization’s authorization policy—and why it should not be the final decision point. Then, delve into the importance of techniques like policy constraints on

AI agents themselves as well as how they affect agent behavior. Next, discover the crucial part continuous, policy-driven authorization will play in the future of digital systems, then check out the hands-on examples that illuminate how Cedar policies can shape agent behavior during execution, planning, and delegation.