Leanpub Header

Skip to main content

Filters

Category: "Artificial Intelligence"

Books

  1. LLM evaluation for developers
    LLM evaluation for developers
    Evals, LLM-as-a-judge and regression testing for AI applications, with Python examples and TypeScript notes
    30labs

    Know whether your LLM feature actually works, and keeps working after the next prompt tweak or model swap. Read traces, build a golden set, calibrate an LLM judge and turn it all into regression gates in CI, with Python examples run before publication.

  2. Juju-chu! —Comienza tu flujo de trabajo Jujutsu × IA con `jj new`

    Los agentes de programación con IA pueden avanzar más rápido de lo que permite el flujo de trabajo de Git basado en staging y commits.Juju-chu! muestra cómo Jujutsu🐦‍⬛ te da commits automáticos, una forma confiable de deshacer operaciones y una manera más segura de reorganizar los cambios desordenados que genera la IA, todo con compatibilidad total con Git y GitHub. Para desarrolladores que ya usan Git y quieren un flujo de trabajo con IA más tranquilo.

  3. AI Evals in Practice
    AI Evals in Practice
    Testing, reliability, and quality for LLM systems in production
    CAIO INCAU

    89% of teams with production AI have observability. Only 52% have evals. This book builds the missing 48%. Fifteen chapters teaching you to construct a production-grade evaluation harness from scratch — golden datasets, deterministic scorers, LLM-as-judge, RAG metrics, agent evals, CI regression detection, and production monitoring.

  4. Agentic Software Development: Don't Get Left Behind
    Agentic Software Development: Don't Get Left Behind
    A Practical Guide to Building with Claude Code, MCP, the Claude API, and the Agent SDK
    CAIO INCAU

    A hands-on guide to building with Claude Code, MCP, the Claude API, and the Agent SDK. From mental models to production architectures — everything an experienced developer needs to work agentically, not just use AI tools.

  5. One Human, Nine Agents, Nineteen Hours
    One Human, Nine Agents, Nineteen Hours
    How a factory of AI agents built a presentation in a day, and how to build yours
    Dinis Cruz

    One person, nine AI agents and one day: how a factory of agents built a talk, and how you can set up your own and start the same day.

  6. Simplifying Machine Learning with PyCaret
    Simplifying Machine Learning with PyCaret
    A Low-code Approach for Beginners and Experts!
    Giannis Tolios

    A beginner-friendly introduction to machine learning with Python, that is based on the PyCaret and Streamlit libraries. Readers will delve into the fascinating world of artificial intelligence, by easily training and deploying their ML models!

  7. Architecting Production-Ready Gen AI and Agentic AI Systems
    Architecting Production-Ready Gen AI and Agentic AI Systems
    A Practitioner’s Guide to Architecture, Retrieval, Agents, Evaluation, Security, Governance, FinOps, and Production Operations
    Srinivas Bommena

    An AI system becomes an architecture problem when it can influence decisions, invoke tools, carry state or change the outside world. This practitioner playbook shows how to design Gen AI and Agentic AI systems that remain reliable, governable and defensible once they reach production.

  8. Cheap Code, Expensive Judgment
    Cheap Code, Expensive Judgment
    Being a Leader in Software Engineering in the Era of AI
    Phillip Leonardo

    AI made code cheap, but it didn't make owning code cheap. A hands-on VP of Engineering's practical, evidence-based guide to leading a small engineering team when every engineer has an agent.

  9. Llama 4 for Education and Research
    Llama 4 for Education and Research
    A Practical Guide for Students Researchers and Professionals
    Anshuman Mishra

    Unlock the power of Llama 4 — the next generation of open-weight multimodal AI.This practical guide shows students, researchers, and professionals how to harness advanced AI tools for learning, research, teaching, and productivity. From generating study notes and research ideas to building educational chatbots and optimizing workflows, discover how Llama 4 can transform the way you work and learn

  10. Confiante e Errado
    Confiante e Errado
    Seu colega brilhante tem amnésia e mente com convicção — eis como construir software com ele mesmo assim.
    José Paschenda

    Um colaborador produtivo que escreve mais código que o time todo, mas esquece tudo com frequência. Quando não sabe, não hesita: inventa, confiante e errado. Você precisa aprender a trabalhar com ele: uma memória viva que mantém vocês na mesma página e um fluxo de trabalho que mantém tudo no lugar e funcionando. Dominar isso impede o agente de derivar e permite, enfim, produzir software de verdade.

  11. Secure All The Things!
    Secure All The Things!
    (with Spring Security)
    Josh Long

    UPDATE: Please don't pay for this!! It's free. Please just take it for free. I'd much rather give it away. Even when it's done, it'll still be free. I'm 100% NOT trying to make money on this. Tell your friends, and be sure to read it. Your applications lives and runs in more places - MCP, desktop applications, browser-based application, data integration pipelines, gRPC, browsers, etc. - than ever. Can your security framework keep up? If you're using Spring Security, then it definitely can, and this book - by Spring Developer Advocate Josh Long - will show you how.

  12. The Mathematical Intuition Behind Deep Learning
    The Mathematical Intuition Behind Deep Learning
    From the Dot Product to Multivariate Calculus and the Jacobian, with Python
    Alex Punnen

    Stop treating neural networks as magic. Starting from a single dot product, this book derives every step to Backpropagation with Matrix Calculus, then turns the math into working Python. No frameworks, no skipped steps. Written for developers who want to know why the equations work, not just how to call them.

  13. Innovating with AI
    Innovating with AI
    How Skilled AI Users Create What Was Never Possible Before
    Srinivas Bommena

    AI can make existing work faster. This book shows how to discover valuable work nobody was doing—and use AI to make it possible.

  14. Teach It Once (BETA)
    Teach It Once (BETA)
    Make AI your mission control for life and work
    Michael Zelbel

    Set up Godspeed Mission Control, a free personal AI that keeps what it learns about you in plain files you own, works on your goals while you are away, and messages you when it needs you. Every chapter ends with something that works.

  15. The MCP Handbook
    The MCP Handbook
    A practical guide to building servers and clients
    Sandeep Kumar Patel

    Build Model Context Protocol servers and clients in TypeScript, one working to-do server at a time.