Graph Engineering for Agentic AI Systems

Graph Engineering for Agentic AI Systems

Ken Huang

66,02 €
IVA incluido
Disponible
Editorial:
Packt Publishing
Año de edición:
2026
ISBN:
9781809208279
66,02 €
IVA incluido
Disponible

Selecciona una librería:

  • Librería Samer Atenea
  • Kálamo Books
  • Librería Elías (Asturias)
  • Librería Kolima (Madrid)
  • Librería Proteo (Málaga)

Design reliable agentic AI systems with explicit graph topology, controlled multi-agent orchestration, knowledge graph memory, and verifiable execution pathsKey Features:- Choose agent orchestration patterns that justify their complexity and cost- Apply graph design through worked examples, chapter exercises, and companion code- Test workflow paths, recovery behavior, and approval gates before agents take actionBook Description:Agentic AI systems need more than capable models: they need clear rules for how work runs. Graph Engineering for Agentic AI Systems helps you design that structure, starting with when a single-agent loop is enough and when multi-agent orchestration earns its complexity. Distinguish execution graphs, knowledge graphs, and learned graphs, then explore typed state, routing, parallel fan-out and joins, and human approval gates. Compare runtimes including LangGraph, Google ADK, Microsoft Agent Framework, and the OpenAI Agents SDK.Worked examples, chapter exercises, and companion code connect architecture to implementation. Explore knowledge graph memory and GraphRAG, checkpointing, bounded retries, idempotency, and production observability. Examine permissions and authorization boundaries, then evaluate execution traces, node contracts, and stop conditions. By the end, you’ll be equipped to design, test, and operate agent workflows with explicit topology, controlled side effects, and traceable decisions.What You Will Learn:- Choose when to keep an agent loop or introduce a graph- Design typed state, routing, parallel fan-out, and joins- Compare agent runtimes for orchestration and persistence- Build knowledge graph memory with typed, traceable facts- Operate workflows with checkpoints, retries, and idempotency- Verify execution paths, permissions, and human approval gatesWho this book is for:This book is for AI engineers, LLM application developers, software architects, and platform engineers building agent workflows beyond the prototype stage. Security engineers will also benefit from its treatment of agent identity, authorization, and approval boundaries. Familiarity with Python, LLM applications, and software architecture will help you engage with the code examples and exercises.Table of Contents- Graph Engineering Is Topology You Own- Execution Graphs and Memory Graphs- The Graph Under the Harness- Anatomy of an Agent Graph- When Not to Build a Graph- Patterns That Earn Their Nodes- Frameworks You Can Ship an Agent Graph On- Knowledge Graphs as Memory- Operating Graphs in Production- The Computer Science of Agent Graphs- Security, Identity, and Governance of Agent Graphs- Graph Intelligence Is Not the Runtime- Testing, Evaluation, and Verification of Agent Graphs- Keep the Graph After the Name Fades

Artículos relacionados

  • Poetry Is Our Ministry to Touch the Heart
    Anelda Lukesia Ballard / Jean Anelda Scott
    Poetry is Our Ministry to Touch the Heart, was birthed when Anelda L. Ballard became ill. God spoke to her in a dream and said 'pick up a pen and write' by being obedient this book was written through the Holy Spirit. Anelda and her mother Jean A. Scott believes that God’s wants to heal a hurting heart. This book will inspire you and encourage you to never give up hope. Jesu...
    Disponible

    11,12 €

  • I soldati lunghi
    Pierluigi Romeo di Colloredo Mels
    Il 24 maggio 1915 il Regno d’Italia entrò nella Grande Guerra, che si sarebbe dimostrata il momento più alto e tragico della sua storia, a poco più di cinquant’anni dalla sua unificazione.In quella lotta tremenda durata quattro anni, la Brigata Granatieri di Sardegna , con i suoi due valorosi Reggimenti, i più antichi del Regio Esercito scrisse, nel grande quadro della guerra d...
    Disponible

    32,59 €

  • Five Beneath Philly
    Susan Bandy / Tom Richmond
    Allen Williams plans to make something of his life and escape South Philly and the work at Cross Brothers’ Meat Packing Plant. He prepares himself with excellent grades and an upcoming full-ride scholarship to climb out of South Philly forever. Then fate changes his whole world. An only son in a family of six, Allen suddenly finds himself responsible for his mother, grandmother...
    Disponible

    18,28 €

  • Forms
    Sharon Welch
    I am an award-winning artist and my works hang in private residences, community hospitals, businesses, and restaurants across the US and also abroad.  I live in Pierre, South Dakota. Since 2008 I have owned Sharon Welch Gallery and Studio where I paint and teach classes.  My theory is have fun, remove the fear of failure, experiment and let the child inside of you play.Very oft...
  • Ricordi di una ausiliaria
    Andrea Lombardi / Raffaella Duelli
    Le memorie di Raffaella Duelli, Volontaria nel Battaglione Barbarigo della Decima Flottiglia Mas iniziano con la partenza del Barbarigo da Roma, narrando la lunga marcia del reparto verso il nord, sotto il mitragliamento degli aerei Alleati. Quindi, è descritta vividamente l'ultima battaglia del Barbarigo sul Fronte Sud, dal Senio a Comacchio: gli appunti di Raffaella, giov...
    Disponible

    28,08 €

  • Why Didn’t You Ask?
    Panya Dixon
    From an early occurrence in her childhood to a perilous thirteen-year relationship, Panya Dixon too often suffered from various forms of physical, emotional, and sexual abuse. Conflicted between love and the pain her loved ones brought on her, she consistently had to fight for her life and her will to move on. Why Didn’t You Ask? is an expression of Panya’s truth—her trials, pa...
    Disponible

    20,35 €

Otros libros del autor

  • Harness Engineering
    Ken Huang
    Build a secure control plane for agentic AI with design patterns for bounded autonomy, least privilege identity, trusted context, governed memory, and runtime recoveryKey Features:- Design a security control plane for long running agents and delegated multi-agent work- Contain prompt injection and memory poisoning through enforceable trust boundaries- Use HarnessLab scenarios t...
    Disponible

    72,39 €

  • OpenClaw AI in Production
    Ken Huang
    Build production grade AI agent platforms on OpenClaw with security, state management, and resilience patterns that are held under real loadDRM-free PDF version + access to Packt’s next-gen Reader*Key Features:- Apply a reusable pattern language, from Hub and Spoke to Heartbeat Loop across any agent stack- Embed zero trust identity, PBAC, and fault injection into your architect...
    Disponible

    62,20 €

  • Agentic AI
    Ken Huang
    This book analyzes the rise and transformative impact of generative AI agents or Agentic AI across industries, offering a comprehensive exploration of their development, applications, and implications. It highlights how these systems are revolutionizing business processes, enhancing decision-making, and reshaping entire sectors from finance to healthcare. It traces the evolutio...
  • LLM Design Patterns
    Ken Huang
    Explore reusable design patterns, including data-centric approaches, model development, model fine-tuning, and RAG for LLM application development and advanced prompting techniquesKey Features:- Learn comprehensive LLM development, including data prep, training pipelines, and optimization- Explore advanced prompting techniques, such as chain-of-thought, tree-of-thought, RAG, an...
    Disponible

    77,88 €