English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 6h 25m | 1023 MB
Create LLM-powered autonomous agents and intelligent assistants tailored to your business and personal needs.
From script-free customer service chatbots to fully independent agents operating seamlessly in the background, AI-powered assistants represent a breakthrough in machine intelligence. In AI Agents in Action, you’ll master a proven framework for developing practical agents that handle real-world business and personal tasks.
Author Micheal Lanham combines cutting-edge academic research with hands-on experience to help you:
- Understand and implement AI agent behavior patterns
- Design and deploy production-ready intelligent agents
- Leverage the OpenAI Assistants API and complementary tools
- Implement robust knowledge management and memory systems
- Create self-improving agents with feedback loops
- Orchestrate collaborative multi-agent systems
- Enhance agents with speech and vision capabilities
You won’t find toy examples or fragile assistants that require constant supervision. AI Agents in Action teaches you to build trustworthy AI capable of handling high-stakes negotiations. You’ll master prompt engineering to create agents with distinct personas and profiles, and develop multi-agent collaborations that thrive in unpredictable environments. Beyond just learning a new technology, you’ll discover a transformative approach to problem-solving.
Most production AI systems require many orchestrated interactions between the user, AI models, and a wide variety of data sources. AI agents capture and organize these interactions into autonomous components that can process information, make decisions, and learn from interactions behind the scenes. This book will show you how to create AI agents and connect them together into powerful multi-agent systems.
In AI Agents in Action, you’ll learn how to build production-ready assistants, multi-agent systems, and behavioral agents. You’ll master the essential parts of an agent, including retrieval-augmented knowledge and memory, while you create multi-agent applications that can use software tools, plan tasks autonomously, and learn from experience. As you explore the many interesting examples, you’ll work with state-of-the-art tools like OpenAI Assistants API, GPT Nexus, LangChain, Prompt Flow, AutoGen, and CrewAI.
What’s Inside
- Knowledge management and memory systems
- Feedback loops for continuous agent learning
- Collaborative multi-agent systems
- Speech and computer vision
Table of Contents
Chapter 1. Introduction to agents and their world
Chapter 1. Understanding the component systems of an agent
Chapter 1. Examining the rise of the agent era: Why agents?
Chapter 1. Peeling back the AI interface
Chapter 1. Navigating the agent landscape
Chapter 1. Summary
Chapter 2. Harnessing the power of large language models
Chapter 2. Exploring open source LLMs with LM Studio
Chapter 2. Prompting LLMs with prompt engineering
Chapter 2. Choosing the optimal LLM for your specific needs
Chapter 2. Exercises
Chapter 2. Summary
Chapter 3. Engaging GPT assistants
Chapter 3. Building a GPT that can do data science
Chapter 3. Customizing a GPT and adding custom actions
Chapter 3. Extending an assistant’s knowledge using file uploads
Chapter 3. Publishing your GPT
Chapter 3. Exercises
Chapter 3. Summary
Chapter 4. Exploring multi-agent systems
Chapter 4. Exploring AutoGen
Chapter 4. Group chat with agents and AutoGen
Chapter 4. Building an agent crew with CrewAI
Chapter 4. Revisiting coding agents with CrewAI
Chapter 4. Exercises
Chapter 4. Summary
Chapter 5. Empowering agents with actions
Chapter 5. Executing OpenAI functions
Chapter 5. Introducing Semantic Kernel
Chapter 5. Synergizing semantic and native functions
Chapter 5. Semantic Kernel as an interactive service agent
Chapter 5. Thinking semantically when writing semantic services
Chapter 5. Exercises
Chapter 5. Summary
Chapter 6. Building autonomous assistants
Chapter 6. Exploring the GPT Assistants Playground
Chapter 6. Introducing agentic behavior trees
Chapter 6. Building conversational autonomous multi-agents
Chapter 6. Building ABTs with back chaining
Chapter 6. Exercises
Chapter 6. Summary
Chapter 7. Assembling and using an agent platform
Chapter 7. Introducing Streamlit for chat application development
Chapter 7. Developing profiles and personas for agents
Chapter 7. Powering the agent and understanding the agent engine
Chapter 7. Giving an agent actions and tools
Chapter 7. Exercises
Chapter 7. Summary
Chapter 8. Understanding agent memory and knowledge
Chapter 8. The basics of retrieval augmented generation (RAG)
Chapter 8. Delving into semantic search and document indexing
Chapter 8. Constructing RAG with LangChain
Chapter 8. Applying RAG to building agent knowledge
Chapter 8. Implementing memory in agentic systems
Chapter 8. Understanding memory and knowledge compression
Chapter 8. Exercises
Chapter 8. Summary
Chapter 9. Mastering agent prompts with prompt flow
Chapter 9. Understanding agent profiles and personas
Chapter 9. Setting up your first prompt flow
Chapter 9. Evaluating profiles: Rubrics and grounding
Chapter 9. Understanding rubrics and grounding
Chapter 9. Grounding evaluation with an LLM profile
Chapter 9. Comparing profiles: Getting the perfect profile
Chapter 9. Summary
Chapter 10. Agent reasoning and evaluation
Chapter 10. Reasoning in prompt engineering
Chapter 10. Employing evaluation for consistent solutions
Chapter 10. Exercises
Chapter 10. Summary
Chapter 11. Agent planning and feedback
Chapter 11. Understanding the sequential planning process
Chapter 11. Building a sequential planner
Chapter 11. Reviewing a stepwise planner: OpenAI Strawberry
Chapter 11. Applying planning, reasoning, evaluation, and feedback to assistant and agentic systems
Chapter 11. Exercises
Chapter 11. Summary
Resolve the captcha to access the links!