Manning Publications Co.

Data structures and algorithms give you a programming toolbox. But sometimes the familiar tools only get you part of the way there. In Fabulous Adventures in Data Structures and Algorithms, Eric Lippert explores lesser-known algorithms that can help you approach problems from new angles—and expand the set of techniques you have to draw from when the standard solutions aren’t quite enough. Earlier this year, Eric joined Scott Hanselman on The Hanselminutes Podcast to talk about the book, the algorithms he chose to explore, and why they're worth adding to your repertoire. The conversation: https://hubs.la/Q04t3TVQ0 Learn more about the book: https://hubs.la/Q04t46Dc0

The more autonomy you give an AI agent, the more important it becomes to understand exactly what’s happening under the hood. Build an AI Agent (From Scratch) by Jungjun Hur 허정준 and Younghee Song takes you through the design, development, and deployment of an autonomous agent system step by step. Without hiding the mechanics behind black-box frameworks. Along the way, you'll build a research agent in Python designed to tackle complex, multi-step tasks from the GAIA (General AI Assistants) benchmark. By constructing the system end to end, you'll see how the pieces fit together and develop the practical understanding needed to build more capable and safer agents. Now in print — get it half off through August 28th: https://hubs.la/Q04t42JY0

Life comes with plenty of uncertainty. Statistics can't eliminate it, but they can help you make better sense of what the data is actually telling you. In Grokking Statistics, Thomas Nield makes statistical analysis approachable without stripping away the practical thinking behind it. Through hands-on mini-projects, you'll build a foundation in statistics and immediately apply each concept to real problems, so you're learning how to interpret data, not just memorize formulas. Want to see how the book approaches statistics? Read a free chapter: https://hubs.ly/Q04s-CQm0 Learn more about the book: https://hubs.ly/Q04s-g6m0

AI can generate code faster than most teams can review it. That changes where the real engineering bottleneck lives. Matt E 📖 Author (Manning), author of Grokking Software Engineering, argues that AI-generated code needs to be treated less like finished output and more like the work of a pair programmer: guide it step by step, review what it produces, and approve it before anything ships. Because while AI can accelerate development, that speed comes with a tradeoff if engineering judgment can't keep pace. Reliability, security, and maintainability still require human oversight. Matt digs into why organizations need to rethink their development processes as AI-generated code becomes more common in this AI Data Press article: https://hubs.la/Q04sZ4f_0 Learn more about software architecture in his book: https://hubs.la/Q04sZ4V50

Technology never stops changing. So how do you build something that lasts? That's the question at the center of Øredev's theme this year: Legacy. The conference will explore what's worth preserving, what's ready to be rebuilt, and how the decisions developers make today carry forward into the systems and culture of tomorrow. Because legacy isn't just what you leave behind — it's something you're actively shaping every time you design, build, or rethink a system. Several Manning authors will be part of that conversation, including Nicolai Parlog, author of The Java Module System. Catch him November 4th for a look at Java 27 and what's next for the platform. Learn more about Øredev: https://hubs.la/Q04sR-P90 And get 45% off Nicolai's book with code oredev26: https://hubs.la/Q04sR-Ln0

AI agents are everywhere. But a lot of the engineering behind them is still happening by trial and error. Agent Design Patterns by Peter Belcak turns the experience of a community of agent builders into reusable patterns for building agents that are more reliable, efficient, and controllable. Instead of tying your approach to a particular model or framework, you'll develop an engineering vocabulary for diagnosing what's going wrong and choosing a pattern that addresses it. That includes lowering per-run costs without redesigning your agent and building self-improving agents that can auto-tune their own prompts. Now available in Manning's Early Access Program — half off through August 26th: https://hubs.la/Q04sRbcz0

Bigger isn't always better. Especially when you need an AI model to know one domain really well. Domain-Specific Small Language Models by Guglielmo Iozzia shows you how to build generative AI models optimized for specific fields, without the compute demands of a large LLM. You'll learn how to adapt pretrained open source models using domain-specific data, then put those techniques to work building SLMs that generate everything from Python code to protein structures and antibody sequences. All on commodity hardware. It's a practical approach to getting focused, high-quality results when cost, hardware, or domain expertise matters more than sheer model size. Now 25% off on Amazon: https://hubs.la/Q04sMv8c0

Do platforms have an agenda? Are they favoring one type of content over another? And, who's in charge of such a decision? The answer lies in understanding recommender systems, the Hidden Influences behind our digital lives. As it turns out, it's more complicated than it seems, as it includes platform policy, human psychology and technical reasons. On August 12th at 12pm ET, Dr. Luca Belli will help us demystify the tools that have become an invisible part of our life. Register for the LinkedIn Live below ↓

What makes a reasoning model different from a conventional LLM? And why does that difference matter for AI agents? On August 19th, Sebastian Raschka, PhD, author of Build a Reasoning Model (From Scratch) and Build a Large Language Model (From Scratch), will join Marlene Mhangami for an ACM, Association for Computing Machinery TechTalk to exploring how reasoning models work and what they make possible. They'll dig into inference scaling and training techniques, then connect those ideas to agentic AI: how reasoning models enable agents to plan, use tools, evaluate intermediate results, and recover from mistakes. Register to attend live: https://hubs.la/Q04sHxqJ0 Can't make it live? Register anyway and you'll be notified when the recording is available. And if you want to go deeper, Build a Reasoning Model (From Scratch) is 45% off with code acmraschka2: https://hubs.la/Q04sHkSC0

Getting comfortable working with AI models is one thing. Knowing what to build with them — and how the pieces fit together — is the next step. Today's Deal of the Day offers a hands-on path from working with models to building agents, designing agent architectures, and putting it all together in an agentic RAG application: • Hugging Face in Action by Wei-Meng Lee to get practical with the Hugging Face ecosystem and the tools behind modern NLP and generative AI. • AI Agents in Action, Second Edition by Micheal Lanham to learn to build agents that can reason, use tools, and take action. • Designing AI Agents by Jia Huang to dig into the architecture and design principles behind reliable, effective agents. • Building an Agentic RAG Application by Matteus Tanha to bring those skills together by building a complete agentic RAG application. It's a progression from understanding the tools to designing systems that can actually do something useful with them. Get all four half off and more with today’s Deal of the Day: https://hubs.la/Q04sHh230