# ai-agent-book | Bojie Li | Knowledge Base | Instagit

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

GitHub Stars: 9.6k

Repository: https://github.com/bojieli/ai-agent-book

---

## Articles

### [Implications of Incomplete Context for AI Agents: 6 Critical Architectural Failures](/bojieli/ai-agent-book/what-are-the-implications-of-incomplete-context-for-an-ai-agent)

Discover how incomplete context leads to AI agent hallucinations, KV-Cache invalidation, and unreliable decisions. Learn about 6 critical architectural failures.

- Tags: architecture
- Published: 2026-08-26

### [How the Correction Function Works Within the Harness Architecture: Arena Validation and Logging](/bojieli/ai-agent-book/how-does-correction-function-within-the-harness-architecture)

Understand the Correction function in the Harness architecture. It validates LLM actions, applies fallbacks, and logs adjustments for diagnostics. Learn how it ensures reliable agent behavior.

- Tags: deep-dive
- Published: 2026-08-26

### [Understanding the Role of Verification in the Harness Layer of AI Agents](/bojieli/ai-agent-book/what-role-does-verification-play-in-the-harness-layer)

Discover verification's crucial role in the AI agent harness layer. It ensures safe tool calls, validates results, and provides auditable evidence for reliable workflows.

- Tags: deep-dive
- Published: 2026-08-26

### [What Is the Constraint Function in Harness Engineering? Purpose and Code Implementation](/bojieli/ai-agent-book/what-is-the-purpose-of-the-constraint-function-in-harness-engineering)

Discover the Constraint function in Harness Engineering. Learn how it transforms business rules into enforceable logic for feasibility checks, safety gates, and agent validation. Understand its purpose and code implementation.

- Tags: deep-dive
- Published: 2026-08-26

### [What Is the Difference Between an Agent and Its Environment in the Instagit Framework](/bojieli/ai-agent-book/what-is-the-difference-between-an-agent-and-its-environment-in-this-framework)

Understand the distinct roles of Agents and Environments in the Instagit framework. Agents make decisions, Environments provide context and data for execution.

- Tags: deep-dive
- Published: 2026-08-26

### [How Skill Documents Differ from Other Tool Descriptions in AI Agents](/bojieli/ai-agent-book/how-do-skill-documents-differ-from-other-tool-descriptions-in-ai-agents)

Understand how skill documents differ from tool descriptions in AI agents. Learn about natural-language workflows and structured JSON-Schema metadata for agent capabilities.

- Tags: deep-dive
- Published: 2026-08-26

### [ACI Principles for Tool Design: The Agent-Computer Interface Framework](/bojieli/ai-agent-book/what-are-the-aci-principles-for-tool-design)

Discover ACI principles for tool design. Learn how to treat tool APIs as agent interfaces with capability expression, tool description, and parameter passing for better AI agent integration.

- Tags: deep-dive
- Published: 2026-08-26

### [How Context and Agent Decision-Making Interact: Insights from the ai-agent-book Repository](/bojieli/ai-agent-book/what-is-the-key-insight-regarding-context-and-agent-decision-making)

Discover how context dictates AI agent decision-making. Explore the bojieli ai-agent-book repository for insights into how information quantity and quality set agent capabilities.

- Tags: deep-dive
- Published: 2026-08-26

### [The Five Components That Constitute Context in an LLM API Call for an Agent](/bojieli/ai-agent-book/what-are-the-five-components-that-constitute-context-in-an-llm-api-call-for-an-agent)

Understand the five essential components of LLM API calls for agents: System Prompt, Tool Definitions, User Messages, Assistant Messages, and Tool Results. Learn how they enable multi-turn reasoning.

- Tags: deep-dive
- Published: 2026-08-26

### [The Five Stages of Evolution for AI Application Engineering: From Static Prompts to Autonomous Graphs](/bojieli/ai-agent-book/what-are-the-five-stages-of-evolution-for-ai-application-engineering)

Explore the five stages of AI application engineering evolution: Prompt, Context, Harness, Loop, and Graph Engineering. Understand the journey from static prompts to autonomous systems.

- Tags: architecture
- Published: 2026-08-26

### [Harness Engineering: The Competitive Advantage for AI Agent Systems](/bojieli/ai-agent-book/why-is-harness-engineering-considered-the-competitive-advantage-for-ai-agent-systems)

Discover how harness engineering provides a competitive advantage for AI agent systems. Learn how it transforms LLMs into production-ready agents with context management, tool interfaces, and safety.

- Tags: deep-dive
- Published: 2026-08-26

### [What Is the Role of the Stable Prefix in a ReAct Loop?](/bojieli/ai-agent-book/what-is-the-role-of-the-stable-prefix-in-the-react-loop-context)

Discover the stable prefix role in a ReAct loop. Learn how this constant prompt element enhances efficiency, cuts costs, and secures your AI agent by enabling prefix caching.

- Tags: deep-dive
- Published: 2026-08-26

### [How Trajectory is Managed in the ReAct Loop: A Complete Technical Breakdown](/bojieli/ai-agent-book/how-is-the-trajectory-managed-in-the-react-loop)

Learn how ReAct loop trajectory is managed by appending step dictionaries to a Python list and saving the complete sequence. Understand the technical breakdown.

- Tags: deep-dive
- Published: 2026-08-26

### [What Is the ReAct Loop? A Deep Dive into AI Agent Task Execution](/bojieli/ai-agent-book/what-is-the-react-loop-and-how-does-it-work-for-ai-agent-task-execution)

Explore the ReAct loop and master AI agent task execution. Understand how Reason-Act-Observe empowers LLMs to solve complex problems by integrating reasoning, tool use, and observation.

- Tags: deep-dive
- Published: 2026-08-26

### [The Five Core Functions of the Harness Layer in an AI Agent](/bojieli/ai-agent-book/what-are-the-five-core-functions-of-the-harness-layer-in-an-ai-agent)

Discover the five core functions of the Harness layer in AI agents: Context Management, Tool Interfaces, Constraints, Verification, and Correction. Ensure safety, validate outputs, and achieve reliable tool execution.

- Tags: deep-dive
- Published: 2026-08-26

### [Agent-Tool Interaction Fidelity: The Core Principle for Reliable AI Systems](/bojieli/ai-agent-book/agent-tool-interaction-fidelity-principle)

Master agent-tool interaction fidelity. Discover the core principle for reliable AI systems: aligning model perception with tool execution to eliminate discrepancies and ensure accuracy.

- Tags: deep-dive
- Published: 2026-08-25

### [AI Agent Capability Expression Forms: Dedicated Tools, General Executors, and Skills Explained](/bojieli/ai-agent-book/capability-expression-forms-ai-agent-tools)

Explore AI agent capability expression forms including dedicated tools, general executors, and Skills. Understand trade-offs in cost, flexibility, and maintenance.

- Tags: deep-dive
- Published: 2026-08-25

### [ACI (Agent-Computer Interface) Principles: A Complete Guide for LLM Tool Design](/bojieli/ai-agent-book/aci-agent-computer-interface-principles)

Explore ACI Agent Computer Interface principles for LLM tool design. Learn how to create effective AI agent interfaces focusing on capability representation, tool description, and faithful parameter passing.

- Tags: deep-dive
- Published: 2026-08-25

### [What Is RAG (Retrieval-Augmented Generation) in AI Agent Knowledge Integration?](/bojieli/ai-agent-book/rag-knowledge-integration-ai-agents)

Discover RAG Retrieval-Augmented Generation an AI pattern enabling agents to access external knowledge for dynamic responses. Enhance your AI agent capabilities.

- Tags: deep-dive
- Published: 2026-08-25

### [How External Knowledge Bases Are Integrated into AI Agent Systems: A Complete RAG Pipeline Guide](/bojieli/ai-agent-book/knowledge-base-integration-ai-agent-systems)

Discover how AI agents integrate external knowledge bases using retrieval-augmented generation (RAG). Learn the complete RAG pipeline for enhanced AI responses.

- Tags: how-to-guide
- Published: 2026-08-25

### [How Context Compression Manages Long Contexts in AI Agents: A Technical Deep Dive](/bojieli/ai-agent-book/context-compression-long-contexts-ai-agents)

Discover how context compression effectively manages long contexts in AI agents. Learn to condense conversation history, retain crucial info, and stay within LLM limits.

- Tags: deep-dive
- Published: 2026-08-25

### [What Are Agent Skills? A Modular Approach to AI Agent Context Engineering](/bojieli/ai-agent-book/agent-skills-context-engineering-ai-agents)

Discover Agent Skills, a modular system for AI agents. Load domain-specific knowledge on demand, optimizing performance and avoiding static prompt overload. Learn more today!

- Tags: deep-dive
- Published: 2026-08-25

### [Context Engineering for AI Agents: Shaping the Informational Environment That Drives Decisions](/bojieli/ai-agent-book/context-engineering-ai-agents)

Discover context engineering for AI agents and learn how to shape their informational environment to enhance decision making. Unlock full AI potential.

- Tags: deep-dive
- Published: 2026-08-25

### [How Context and Tools Improve AI Agent Performance: Architecture Deep Dive](/bojieli/ai-agent-book/context-tools-ai-agent-performance-improvement)

Discover how AI agents boost performance with context memory and specialized tools. Explore the bojieli/ai-agent-book architecture for enhanced AI reasoning and efficiency.

- Tags: deep-dive
- Published: 2026-08-25

### [What is the Model-Harness Architecture in an AI Agent?](/bojieli/ai-agent-book/model-harness-architecture-ai-agent)

Understand the Model-Harness architecture in AI agents. Learn how this design pattern separates model inference from tool execution, safety, and side-effects for cleaner agent development.

- Tags: deep-dive
- Published: 2026-08-25

### [How the AI Agent Book Defines the Agent-Environment Interaction Loop](/bojieli/ai-agent-book/agent-environment-interaction-loop)

The AI Agent Book explains the agent-environment interaction loop: observations from the environment inform agent actions, which in turn modify the environment for the next cycle.

- Tags: deep-dive
- Published: 2026-08-25

### [How the AI Agent Book MkDocs Site Is Built and Deployed: Complete Pipeline Guide](/bojieli/ai-agent-book/ai-agent-book-mkdocs-build-deploy)

Discover the three stage pipeline for building and deploying the AI Agent Book MkDocs site. Learn how documentation is assembled, rendered with MkDocs Material, and deployed to GitHub Pages.

- Tags: how-to-guide
- Published: 2026-08-24

### [What Is the agentbook Python Package? Provider Registry and Backend Resolution Explained](/bojieli/ai-agent-book/agentbook-python-package-purpose)

Explore the agentbook Python package, the AI Agent Book's infrastructure library. Discover its provider registry and backend resolution for seamless LLM service connections.

- Tags: getting-started
- Published: 2026-08-24

### [Stages of AI Model Capability Development in Post-Training: The Three-Stage Pipeline](/bojieli/ai-agent-book/ai-agent-model-post-training-stages)

Discover the three stages of AI model capability development in post-training SFT, RL, and Continuous Evolution. Transform models into adaptive agents.

- Tags: deep-dive
- Published: 2026-08-24

### [How to Use Unsloth for Accelerated Fine-Tuning of AI Agents](/bojieli/ai-agent-book/ai-agent-unsloth-accelerated-finetuning)

Accelerate AI agent fine-tuning with Unsloth. Slash training time in half and cut VRAM by 30% using optimized CUDA kernels and LoRA. Seamlessly integrates with Hugging Face Trainer.

- Tags: how-to-guide
- Published: 2026-08-24

### [AI Agent Evaluation Metrics: A Complete Guide to Measuring Performance, Cost, and Multilingual Capability](/bojieli/ai-agent-book/ai-agent-evaluation-metrics)

Discover essential AI agent evaluation metrics for performance, cost, and multilingual capability. Learn how to measure your AI agents effectively with this comprehensive guide.

- Tags: deep-dive
- Published: 2026-08-24

### [Key AI Agent Evaluation Environments in the ai-agent-book Repository](/bojieli/ai-agent-book/ai-agent-evaluation-environments)

Discover key AI agent evaluation environments in the ai-agent-book repo. Test autonomous agents in health data analysis, world simulation, sandboxing, and browser automation with reproducible scoring.

- Tags: article
- Published: 2026-08-24

### [Multimodal Perception for AI Agents: Architecture, Strategies, and Implementation](/bojieli/ai-agent-book/ai-agent-multimodal-perception)

Explore multimodal perception for AI agents. Learn how AI understands images audio video and more beyond text. Discover architectures strategies and implementation.

- Tags: deep-dive
- Published: 2026-08-24

### [How AI Agents Can Expand Their Observation and Action Spaces: Multi-Modal Architecture Guide](/bojieli/ai-agent-book/ai-agent-expand-observation-action-spaces)

Discover how AI agents expand observation and action spaces using multi-modal sensors and asynchronous tools. Learn the Agent = LLM + Context + Tools formula.

- Tags: architecture
- Published: 2026-08-24

### [Code-as-Universal-Metatool: Why This Architecture Changes How AI Agents Execute Capabilities](/bojieli/ai-agent-book/ai-agent-code-universal-metatool-benefits)

Discover the code-as-universal-metatool paradigm and its benefits for AI agents. Learn how this architecture simplifies capability execution and eliminates tool bindings.

- Tags: architecture
- Published: 2026-08-24

### [How Code Is Treated as a Tool for Creating New Tools in AI Agents](/bojieli/ai-agent-book/ai-agent-code-as-tool-creation)

Discover how AI agents use code as a tool to build new tools. Learn about sandboxing, JSON serialization, and library interfaces for dynamic code reuse.

- Tags: deep-dive
- Published: 2026-08-24

### [Proposer-Reviewer Pattern for AI Agent Actions: A Two-Stage Validation Workflow](/bojieli/ai-agent-book/ai-agent-proposer-reviewer-pattern)

Discover the Proposer-Reviewer pattern, a two-stage AI agent workflow that separates plan generation from multimodal validation for iterative output refinement and structured feedback loops.

- Tags: deep-dive
- Published: 2026-08-24

### [How the Sidecar Mechanism Enhances AI Agent Security: A Deep Dive into Isolated Gatekeeping](/bojieli/ai-agent-book/ai-agent-sidecar-mechanism-security)

Discover how the Sidecar mechanism boosts AI agent security. Learn how isolated gatekeeping prevents prompt injection and blocks unsafe actions for enhanced protection.

- Tags: deep-dive
- Published: 2026-08-24

### [Security Risks in AI Agent Tool Usage: A Deep Dive into the ai-agent-book Safety Gate](/bojieli/ai-agent-book/ai-agent-tool-security-risks)

Explore AI agent tool security risks like path traversal and command injection. Learn how the ai-agent-book Safety Gate prevents malicious tool execution.

- Tags: deep-dive
- Published: 2026-08-24

### [What is the Skills-over-MCP Pattern for AI Agents?](/bojieli/ai-agent-book/ai-agent-skills-over-mcp-pattern)

Discover the Skills-over-MCP pattern an AI agent architecture blending universal tool interoperability with compact, on-demand access to thousands of capabilities. Learn more!

- Tags: deep-dive
- Published: 2026-08-24

### [What Is the Model Context Protocol (MCP) for Tool Communication?](/bojieli/ai-agent-book/ai-agent-mcp-protocol)

Discover the Model Context Protocol MCP an open communication layer letting LLMs invoke tools via a universal JSON-RPC interface. Simplify tool integration.

- Tags: deep-dive
- Published: 2026-08-24

### [How Agent Skills Reduce Tool Selection Burden in LLM Systems](/bojieli/ai-agent-book/ai-agent-skills-tool-selection)

Discover how agent skills simplify LLM tool selection from complex search to efficient knowledge retrieval. Keep prompts compact and capabilities ready on demand.

- Tags: deep-dive
- Published: 2026-08-24

### [What Is Prompt Engineering for AI Agents? A Technical Deep Dive](/bojieli/ai-agent-book/ai-agent-prompt-engineering)

Master prompt engineering for AI agents. Learn to design system prompts that define identity, constraints, and tool use, optimizing for cache reuse and security.

- Tags: deep-dive
- Published: 2026-08-24

### [AI Agent Context Engineering: Core Principles and Implementation Patterns](/bojieli/ai-agent-book/ai-agent-context-engineering-topics)

Master AI agent context engineering. Learn core principles and implementation patterns to systematically design and deliver information for LLM agents. Build better AI tools.

- Tags: deep-dive
- Published: 2026-08-24

### [How the AI Agent Book Structures Its Curriculum Around the Core Formula Agent = LLM + Context + Tools](/bojieli/ai-agent-book/ai-agent-book-structure-formula)

Discover how the AI Agent book structures its curriculum around Agent = LLM + Context + Tools. Learn about building, evaluating, and scaling AI agents.

- Tags: architecture
- Published: 2026-08-24

### [Negative Results in Coding Agent Experiments: Why Generated Code Fails](/bojieli/ai-agent-book/coding-agent-negative-results-chapter-5)

Discover negative results in AI coding agent experiments. Learn why generated code fails due to sandbox crashes, constraint errors, and off-by-one bugs impacting accuracy and latency.

- Tags: deep-dive
- Published: 2026-08-23

### [How the Full Coding Agent Loop Works in chapter5/coding-agent/](/bojieli/ai-agent-book/coding-agent-loop-implementation-chapter-5)

Explore the full Coding Agent loop implementation in chapter5/coding-agent/. Discover its fetch-process-execute-feedback cycle for LLM queries and tool execution.

- Tags: deep-dive
- Published: 2026-08-23

### [Deploy the MCP Tool Server with Docker Compose: A Complete Guide to Chapter 4 Orchestration](/bojieli/ai-agent-book/docker-compose-mcp-tool-server-deployment)

Easily deploy the MCP tool server using Docker Compose. Follow this guide to launch execution, perception, and collaboration tools with a single command.

- Tags: how-to-guide
- Published: 2026-08-23

### [How the Active Tool Discovery Experiment (4-5) Enables Agents to Proactively Select Tools](/bojieli/ai-agent-book/active-tool-discovery-experiment-4-5)

Discover how the active tool discovery experiment (4-5) lets agents proactively select tools. Learn how LLMs identify and request needed tools for smarter AI agent performance.

- Tags: deep-dive
- Published: 2026-08-23

### [How MCP (Model Context Protocol) is Implemented in ai-agent-book: Schema Validation and Sandboxing Explained](/bojieli/ai-agent-book/mcp-protocol-implementation-features)

Explore the ai-agent-book's MCP implementation featuring FastMCP, Pydantic schema validation, and sandbox execution for secure AI agent RPC.

- Tags: deep-dive
- Published: 2026-08-23

### [The Three Categories of Tools Discussed in Chapter 4 of the AI Agent Book](/bojieli/ai-agent-book/agent-tool-categories-chapter-4)

Explore the three tool categories in the AI Agent Book Chapter 4: perception, execution, and collaboration tools. Understand how agents gather info, act, and coordinate.

- Tags: deep-dive
- Published: 2026-08-23

### [Backends for Semantic Memory Retrieval and Structured Storage in the `mem` Extra](/bojieli/ai-agent-book/semantic-memory-backends-mem-extra)

Explore backends for semantic memory retrieval and structured storage in the mem extra. Discover mem0ai[nlp] for vector search and memobase for persistent data.

- Tags: api-reference
- Published: 2026-08-23

### [What RAG and Vector Database Tools are Integrated in the agentbook `rag` Extra?](/bojieli/ai-agent-book/rag-vector-database-tools-pyproject-toml)

Explore RAG tools in the agentbook `rag` extra. Discover integrations for vector stores like ChromaDB FAISS, embedding models, sparse retrieval BM25, ANN indexes, and production utilities. Boost your AI agent capabilities.

- Tags: deep-dive
- Published: 2026-08-23

### [Long-Term Memory Architecture Components in Chapter 3: A Three-Dimensional Design](/bojieli/ai-agent-book/long-term-memory-architecture-chapter-3)

Explore the three-dimensional long-term memory architecture from Chapter 3. Discover how AI agents achieve scalability and persistence through distinct storage, format, and cognitive types.

- Tags: deep-dive
- Published: 2026-08-23

### [How to Deploy Local LLM Services Using vLLM or Ollama: A Complete Guide](/bojieli/ai-agent-book/local-llm-serving-vllm-ollama)

Deploy local LLM services easily using vLLM or Ollama backends. This guide shows you how to set up your environment for efficient AI model deployment on CPUs or GPUs.

- Tags: how-to-guide
- Published: 2026-08-23

### [Context Compression Strategies Compared in Experiment 2-IO: A Technical Analysis](/bojieli/ai-agent-book/context-compression-strategies-experiment-2-10)

Experiment 2-IO compares six context compression strategies: none, individual, combined, context-aware, context-aware with citations, and windowed. Analyze their impact on performance metrics.

- Tags: technical-analysis
- Published: 2026-08-23

### [How Prompt Engineering Is Quantitatively Evaluated Using Tau-Bench: Experiment 2-4 Analysis](/bojieli/ai-agent-book/prompt-engineering-quantitative-evaluation-tau-bench)

Discover how prompt engineering is quantitatively evaluated using Tau-Bench in experiments 2-4. Analyze the impact of tone, organization, and tool descriptions on task completion.

- Tags: deep-dive
- Published: 2026-08-23

### [How the Learning from Experience Experiment Evaluates an Agent's Ability to Learn from Its Running Trajectory](/bojieli/ai-agent-book/learning-from-experience-experiment-1-5)

Discover how the learning from experience experiment evaluates an agent's ability to learn from its running trajectory. See how agents improve performance by leveraging past execution data.

- Tags: deep-dive
- Published: 2026-08-23

### [How the Deep Research Loop (I-3) Works: Intent Clarification, Multi-Turn Search, and Server-Side Code Execution](/bojieli/ai-agent-book/deep-research-loop-implementation)

Uncover how the Deep Research loop (I-3) clarifies intent, uses multi-turn search, and executes server-side code for effective AI agent research. Learn more now.

- Tags: deep-dive
- Published: 2026-08-23

### [What LLM Providers Are Used in the Context Ablation Experiment? A Complete Provider Guide](/bojieli/ai-agent-book/context-ablation-llm-providers)

Discover the nine LLM providers powering the context ablation experiment in bojieli ai agent book. Explore dashscope, qwen, bailian, kimi, moonshot, doubao, siliconflow, deepseek, and openrouter.

- Tags: getting-started
- Published: 2026-08-23

### [How the Context Ablation Experiment Validates Essential Context Components for Agent Performance](/bojieli/ai-agent-book/context-ablation-experiment-importance)

Discover how context ablation experiments prove tool definitions, results, reasoning, and conversation history are essential for AI agent performance. Learn what truly matters for reliable task completion.

- Tags: deep-dive
- Published: 2026-08-23

### [How to Install Chapter-Specific Dependencies using uv sync --locked --extra chN](/bojieli/ai-agent-book/install-chapter-dependencies-uv-sync)

Install chapter specific dependencies for the AI Agent Book using uv sync --locked --extra chN. Ensure precise version control for each chapter by following this simple command.

- Tags: how-to-guide
- Published: 2026-08-23

### [Pyproject.toml Extras in AI-Agent-Book: Modular Dependency Guide](/bojieli/ai-agent-book/pyproject-toml-extras-explained)

Explore pyproject.toml extras in bojieli/ai-agent-book. Understand optional dependencies like viz web and rag to install only what you need for AI projects.

- Tags: tutorial
- Published: 2026-08-23

### [How ai-agent-book Manages Dependencies with uv and pyproject.toml Optional-Dependencies](/bojieli/ai-agent-book/dependency-management-uv-pyproject-toml)

Discover how ai-agent-book uses pyproject.toml optional-dependencies and uv for efficient dependency management. Achieve lightweight installs and reproducible environments.

- Tags: how-to-guide
- Published: 2026-08-23

### [Agent = LLM + Context + Tools: The Core Formula for Building Autonomous AI Agents](/bojieli/ai-agent-book/agent-formula-components-llm-context-tools)

Discover the core formula for building autonomous AI agents. Learn how LLM, Context, and Tools combine to create powerful AI systems capable of reasoning, remembering, and acting.

- Tags: deep-dive
- Published: 2026-08-23

### [How the AI Agent Book Structures Its Curriculum Around the Core Formula Agent = LLM + Context + Tools](/bojieli/ai-agent-book/ai-agent-book-core-formula-structure)

Discover how the AI Agent Book structures its curriculum around the core formula Agent = LLM + Context + Tools transforming theory into production ready AI agents.

- Tags: architecture
- Published: 2026-08-23

### [How to Generate EPUB from Markdown: Complete Build Pipeline for AI Agent Book](/bojieli/ai-agent-book/what-are-steps-to-generate-epub-from-markdown)

Generate EPUB from Markdown easily. Follow steps to install tools, run a build script, and automate your EPUB creation pipeline for your AI agent book project.

- Tags: how-to-guide
- Published: 2026-08-22

### [How to Configure MkDocs for Multi-Language Support: A Complete Implementation Guide](/bojieli/ai-agent-book/how-to-configure-mkdocs-multi-language-support)

Learn to configure MkDocs for multi-language support. This guide details setting up language mappings, internationalization assets, and navigation for your multilingual documentation.

- Tags: how-to-guide
- Published: 2026-08-22

### [How to Use FAISS or ChromaDB for Vector Storage in the AI Agent Book](/bojieli/ai-agent-book/how-to-use-faiss-or-chromadb-for-vector-storage)

Learn to use FAISS or ChromaDB for vector storage in the AI Agent Book. Explore pluggable architecture for easy switching between local and client-server options.

- Tags: how-to-guide
- Published: 2026-08-22

### [Python Packages Used for Sentence Embeddings in the AI-Agent-Book Repository](/bojieli/ai-agent-book/which-python-packages-for-sentence-embeddings)

Discover the Python packages sentence-transformers and faiss powering sentence embeddings in the bojieli/ai-agent-book repository. Learn how they enable efficient indexing and searching.

- Tags: tutorial
- Published: 2026-08-22

### [How to Set Up a Local Ollama Server for AI Agents: Complete Setup Guide](/bojieli/ai-agent-book/how-to-set-up-local-ollama-server-for-ai-agents)

Set up a local Ollama server for AI agents easily. Follow this complete guide to install Ollama, pull models, and connect your agent code to the local endpoint for powerful AI integration.

- Tags: how-to-guide
- Published: 2026-08-22

### [How to Build PDF and EPUB Versions of the AI Agent Book](/bojieli/ai-agent-book/how-to-build-pdf-epub-ai-agent-book)

Learn to build PDF and EPUB versions of the AI Agent Book from Markdown. Use XeLaTeX for PDF and Pandoc for EPUB. Access build scripts in the bojieli/ai-agent-book repository.

- Tags: how-to-guide
- Published: 2026-08-22

### [Integration Dependencies for AI Agents: Complete Guide Based on the AI Agent Book](/bojieli/ai-agent-book/what-are-integration-dependencies-for-ai-agents)

Discover essential integration dependencies for AI agents, including openai, requests, python-dotenv, and tenacity, as detailed in the AI Agent Book repository.

- Tags: how-to-guide
- Published: 2026-08-22

### [What Are the Dependencies for Fine-Tuning AI Agents in the ai-agent-book Repository?](/bojieli/ai-agent-book/what-are-dependencies-for-fine-tuning-ai-agents)

Discover the essential dependencies for fine-tuning AI agents in the ai-agent-book repository. Learn about PyTorch, Hugging Face Transformers, Accelerate, and more for efficient model training.

- Tags: tutorial
- Published: 2026-08-22

### [RAG Dependencies in AI Agent Book: Complete Package Guide for RAPTOR and GraphRAG](/bojieli/ai-agent-book/what-are-dependencies-for-rag)

Explore RAG dependencies in the AI Agent Book. Understand RAPTOR and GraphRAG package sets, common vector storage, LLM, and document processing libraries.

- Tags: complete-package-guide
- Published: 2026-08-22

### [How to Install Dependencies for a Specific Chapter in AI Agents in Depth](/bojieli/ai-agent-book/how-to-install-dependencies-for-specific-chapter)

Install AI Agents in Depth book chapter dependencies easily. Run uv sync --locked --extra chX from the repo root, specifying your chapter number for a quick setup.

- Tags: how-to-guide
- Published: 2026-08-22

### [How Python Dependencies Are Managed in the AI-Agent-Book Repository](/bojieli/ai-agent-book/how-are-python-dependencies-managed)

Discover how Python dependencies are managed in the ai agent book repo. Learn about chapter specific requirements, lock files, and runtime code isolation.

- Tags: how-to-guide
- Published: 2026-08-22

### [How to Use the Provider Lookup Function in ai-agent-book: A Complete Guide](/bojieli/ai-agent-book/how-to-use-provider-lookup-function)

Master the provider lookup function in ai-agent-book. This guide shows how to convert user-supplied names into detailed Provider dataclasses with endpoints, models, and credentials.

- Tags: how-to-guide
- Published: 2026-08-22

### [Complete List of LLM Provider Aliases in ai-agent-book](/bojieli/ai-agent-book/what-are-aliases-for-llm-providers)

Discover the 14 LLM provider aliases in ai-agent-book. Map human-friendly names like moonshot to backend providers like kimi for easier integration.

- Tags: api-reference
- Published: 2026-08-22

### [How to Configure API Keys for Different LLM Providers: A Complete Guide](/bojieli/ai-agent-book/how-to-configure-api-keys-for-llm-providers)

Learn to configure API keys for various LLM providers like OpenAI, Moonshot, and Ark. Easily set environment variables and select your active provider for seamless integration.

- Tags: how-to-guide
- Published: 2026-08-22

### [Which LLM Providers Are Supported by the AI Agent Book? Complete Registry Guide](/bojieli/ai-agent-book/what-llm-providers-are-supported-by-ai-agent-book)

Discover which LLM providers the AI Agent Book supports. This guide lists major options like OpenAI, Google Gemini, and DeepSeek for your AI projects.

- Tags: registry-guide
- Published: 2026-08-22

### [How to Select Different LLM Providers in Chapter CLIs](/bojieli/ai-agent-book/how-to-select-different-llm-providers-in-chapter-clis)

Learn how to select different LLM providers in chapter CLIs by exploring the centralized provider registry in bojieli/ai-agent-book. Use the --provider flag for easy selection.

- Tags: how-to-guide
- Published: 2026-08-22

### [How the Multi-Provider LLM Registry Works in AI Agent Book](/bojieli/ai-agent-book/how-does-multi-provider-llm-registry-work)

Learn how the multi-provider LLM registry in AI Agent Book centralizes language model configuration using Provider dataclasses and immutable mappings. Understand canonical name resolution and alias support.

- Tags: deep-dive
- Published: 2026-08-22

### [How to Access the Book's Prose Content in the AI Agent Book Repository](/bojieli/ai-agent-book/how-to-access-books-prose-content)

Easily access AI Agent Book prose content from the bojieli/ai-agent-book repository. Learn how to retrieve Markdown files via GitHub URLs, local clones, or Python scripts.

- Tags: getting-started
- Published: 2026-08-22

### [Where Is the Shared Plumbing Code for AI Agent Experiments in ai-agent-book?](/bojieli/ai-agent-book/where-is-shared-plumbing-code-for-ai-agent-experiments)

Locate the shared plumbing code for AI agent experiments in the ai-agent-book repository. Discover its central role in provider resolution, environment loading, and trace printing within the agentbook package.

- Tags: how-to-guide
- Published: 2026-08-22

### [How Experiments Are Organized in the AI Agent Book: A Technical Guide](/bojieli/ai-agent-book/how-are-experiments-organized-in-ai-agent-book)

Discover the organized experimental structure in the AI Agent Book. Learn how exploration, evidence generation, and post-processing scripts work together for efficient AI research.

- Tags: how-to-guide
- Published: 2026-08-22

### [Core Components of an AI Agent: Understanding the LLM + Context + Tools Architecture](/bojieli/ai-agent-book/what-are-the-core-components-of-an-ai-agent)

Discover the core components of an AI agent: LLM, Context, and Tools. Learn how this Agent = LLM + Context + Tools architecture powers intelligent systems.

- Tags: deep-dive
- Published: 2026-08-22

### [How to Set Up AI Agents with LLM, Context, and Tools: A Complete Implementation Guide](/bojieli/ai-agent-book/how-to-set-up-ai-agents-with-llm-context-and-tools)

Learn how to set up AI agents with LLM, context, and tools. This guide explains the three core components for building powerful AI agents.

- Tags: how-to-guide
- Published: 2026-08-22

### [What Is LoRA and Its Application in Agent Model Post‑Training? A Complete Guide in ai-agent-book](/bojieli/ai-agent-book/what-is-lora-and-its-application-in-agent-model-post-training)

Discover LoRA, a parameter-efficient fine-tuning method for AI agents. Learn how LoRA cuts memory use and training time for specialized agent tasks, enabling a single base model for multiple applications.

- Tags: deep-dive
- Published: 2026-08-18

### [Implementing Knowledge Graphs for AI Agent Knowledge Bases: A GraphRAG Deep Dive](/bojieli/ai-agent-book/implementing-knowledge-graphs-for-ai-agent-knowledge-bases)

Learn how to implement knowledge graphs for AI agent knowledge bases using GraphRAG. Transform documents into queryable structures with LLM entity extraction and graph traversal.

- Tags: deep-dive
- Published: 2026-08-18

### [Security Considerations for AI Agent Tool Parameter Fidelity: A Complete Guide](/bojieli/ai-agent-book/security-considerations-for-ai-agent-tool-parameter-fidelity)

Secure your AI agents by mastering tool parameter fidelity. Prevent execution failures, data corruption, and privilege escalation with this essential guide to safe AI parameter handling.

- Tags: deep-dive
- Published: 2026-08-18

### [Implementing Agent Continuous Evolution from Runtime Trajectories: A Production-Ready Self-Modifying System](/bojieli/ai-agent-book/implementing-agent-continuous-evolution-from-runtime-trajectories)

Discover agent continuous evolution from runtime trajectories. This production-ready system enables self-modifying AI agents to improve performance and adapt in real time.

- Tags: deep-dive
- Published: 2026-08-18

### [Optimizing Token Usage for AI Agent Context Management: A Complete Guide Based on ai-agent-book](/bojieli/ai-agent-book/optimizing-token-usage-for-ai-agent-context-management)

Master AI agent token optimization with context compression and budget-aware truncation. This guide shows how to reduce consumption by up to 76% without losing quality. Learn from bojieli ai agent book.

- Tags: how-to-guide
- Published: 2026-08-18

### [Orchestration vs. Peer Collaboration Patterns in AI Agents: A Code-Level Comparison](/bojieli/ai-agent-book/orchestration-vs-peer-collaboration-patterns-in-ai-agents)

Explore orchestration vs peer collaboration patterns in AI agents. Understand code-level differences and choose the right architecture for your multi-agent systems.

- Tags: comparison
- Published: 2026-08-18

### [Building Agent Evaluation Benchmarks with Detailed Rubrics: A Complete Framework from ai-agent-book](/bojieli/ai-agent-book/building-agent-evaluation-benchmarks-with-detailed-rubrics)

Learn to build robust LLM agent evaluation benchmarks with detailed rubrics. Discover a three-layer framework for reliable and auditable agent testing.

- Tags: tutorial
- Published: 2026-08-18

### [Implementing Event-Driven Asynchronous Communication in Agent Systems: A Complete Guide to In-Process Message Buses](/bojieli/ai-agent-book/implementing-event-driven-asynchronous-communication-in-agent-systems)

Learn to implement event-driven asynchronous communication in agent systems with an in-process Python message bus. Build decoupled coordination without external infrastructure.

- Tags: how-to-guide
- Published: 2026-08-18

### [Dynamic Tool Discovery: How to Reduce Agent Context Overhead in LLM Systems](/bojieli/ai-agent-book/dynamic-tool-discovery-to-reduce-agent-context-overhead)

Learn dynamic tool discovery to reduce LLM agent context overhead. Request tools on-demand and avoid token bloat. Optimize your AI agent performance now.

- Tags: deep-dive
- Published: 2026-08-18

### [Context Compression in LLM Agents: When and How to Apply It](/bojieli/ai-agent-book/what-is-context-compression-in-llm-agents-and-when-to-apply-it)

Understand context compression in LLM agents. Learn when and how to apply this technique to manage token limits and optimize conversations for better performance.

- Tags: deep-dive
- Published: 2026-08-18

### [Implementing Persistent User Memory Across Agent Sessions in AWorld](/bojieli/ai-agent-book/implementing-user-memory-across-multiple-agent-sessions)

Implement persistent user memory across agent sessions. Leverage MemoryFactory with in-memory or PostgreSQL storage for lasting context in your AI agents.

- Tags: how-to-guide
- Published: 2026-08-18

### [MCP Tool Description Poisoning: Critical Security Risks in AI Agent Systems](/bojieli/ai-agent-book/security-risks-associated-with-mcp-tool-description-poisoning)

Discover MCP tool description poisoning risks. Learn how attackers exploit hidden commands in LLM agents for unauthorized actions like data theft and system destruction.

- Tags: security-risks
- Published: 2026-08-18

### [Building Production-Ready AI Coding Agents: Architecture and Usage of the ai-agent-book Repository](/bojieli/ai-agent-book/building-production-ready-ai-coding-agents)

Build production-ready AI coding agents with the ai-agent-book repository. Decouple experiment code from LLM backends and enable automatic fallback to OpenRouter.

- Tags: architecture
- Published: 2026-08-18

### [Implementing Shared vs Non-Shared Context in Multi-Agent Systems: A Complete Guide](/bojieli/ai-agent-book/implementing-shared-vs-non-shared-context-in-multi-agent-systems)

Learn to implement shared vs non-shared context in multi-agent systems. Understand how a single Context object or isolated instances impact agent communication and state management for AI development.

- Tags: how-to-guide
- Published: 2026-08-18

### [Evaluating AI Agent Performance Using Pass@k Metrics: A Complete Guide](/bojieli/ai-agent-book/evaluating-ai-agent-performance-using-pass-k-metrics)

Master Pass@k metrics to evaluate AI agent performance. Learn how this guide demystifies probabilistic success for k independent attempts.

- Tags: how-to-guide
- Published: 2026-08-18

### [Supervised Fine-Tuning vs Reinforcement Learning for Agent Training: A Complete Technical Comparison](/bojieli/ai-agent-book/comparing-supervised-fine-tuning-sft-vs-reinforcement-learning-rl-for-agent-training)

Explore Supervised Fine-Tuning vs Reinforcement Learning for agent training. Understand how SFT uses expert data while RL learns via interaction and rewards. Make informed choices for your AI.

- Tags: deep-dive
- Published: 2026-08-18

### [Handling Tool Selection with Hundreds of Tools in an Agent Context: A Scalable Architecture](/bojieli/ai-agent-book/handling-tool-selection-with-hundreds-of-tools-in-agent-context)

Discover how the ai-agent-book framework handles tool selection with hundreds of tools using a scalable three-layer architecture: Provider Registry, Safety Policy Gate, and Resolver Executor.

- Tags: architecture
- Published: 2026-08-18

### [Understanding and Building MCP Protocol Servers for AI Agents: A Complete Guide](/bojieli/ai-agent-book/understanding-and-building-mcp-protocol-servers-for-ai-agents)

Learn to build MCP protocol servers for AI agents using FastMCP. Discover how to enable AI agents to invoke remote tools as services with this comprehensive guide.

- Tags: how-to-guide
- Published: 2026-08-18

### [Designing Tool Descriptions for AI Agents Using ACI Principles: A Complete Guide](/bojieli/ai-agent-book/designing-tool-descriptions-for-ai-agents-using-aci-principles)

Learn to design effective AI agent tool descriptions using ACI principles. Write JSON schemas from the agent's view to reduce hallucination and ensure reliable tool use.

- Tags: how-to-guide
- Published: 2026-08-18

### [What Is KV Cache and How It Boosts AI Agent Efficiency](/bojieli/ai-agent-book/what-is-kv-cache-and-its-role-in-ai-agent-efficiency)

Discover how KV Cache optimizes AI agents by storing past attention keys and values. Learn how this technique boosts efficiency and reduces computation in transformer models.

- Tags: deep-dive
- Published: 2026-08-18

### [How LLM Context Window Size Impacts Agent Performance: A Deep-Dive Analysis](/bojieli/ai-agent-book/how-does-llm-context-window-size-impact-agent-performance)

Discover how LLM context window size affects AI agent performance. Learn strategies to manage limitations and maintain accuracy for better results.

- Tags: deep-dive
- Published: 2026-08-18

### [Agent Prompt Engineering and Instruction Optimization: Best Practices from the AI Agent Book](/bojieli/ai-agent-book/what-are-best-practices-for-agent-prompt-engineering-and-instruction-optimization)

Master agent prompt engineering with three layers: static, process, and dynamic. Optimize instructions to boost KV-cache efficiency and avoid performance degradation. Learn best practices from the AI Agent Book.

- Tags: best-practices
- Published: 2026-08-17

### [How to Design Agent Evaluation Environments with Statistical Significance: A Practical Guide](/bojieli/ai-agent-book/how-to-design-agent-evaluation-environments-with-statistical-significance)

Learn to design agent evaluation environments with statistical significance using paired tasks and McNemar's test. Ensure your AI agent improvements are real, not random.

- Tags: how-to-guide
- Published: 2026-08-17

### [Agent Action Grounding and Verification: 6 Proven Strategies from the ai-agent-book](/bojieli/ai-agent-book/what-strategies-for-handling-agent-action-grounding-and-verification)

Discover 6 proven strategies for agent action grounding and verification. Ensure traceable claims with token-level semantic overlap and deterministic evidence serialization from the ai-agent-book.

- Tags: best-practices
- Published: 2026-08-17

### [How to Implement Controllable TTS for Agent Voice Output Using Fish Audio S1](/bojieli/ai-agent-book/how-to-implement-controllable-tts-for-agent-voice-output)

Implement controllable TTS for agent voice output with Fish Audio S1. Dynamically adjust emotion, speed, and style using voice clips and markup tags.

- Tags: how-to-guide
- Published: 2026-08-17

### [Architectural Differences Between Reactive and Event-Driven Agent Frameworks](/bojieli/ai-agent-book/what-are-architectural-differences-between-reactive-and-event-driven-agent-frameworks)

Explore the architectural differences between reactive and event-driven agent frameworks. Understand how reactive agents block during tools while event-driven agents use async queues for non-stop workflows.

- Tags: architecture
- Published: 2026-08-17

### [How Knowledge Graphs Enhance Agent Reasoning and Context: A Deep Dive into HybridStructuredRetriever](/bojieli/ai-agent-book/how-do-knowledge-graphs-enhance-agent-reasoning-and-context)

Unlock advanced agent reasoning and context with knowledge graphs. Learn how HybridStructuredRetriever enables multi-hop inference and reduces ambiguity for better AI performance.

- Tags: deep-dive
- Published: 2026-08-17

### [Patterns for Agent Self-Evolution and Continuous Learning: A Deep Dive into the ai-agent-book Repository](/bojieli/ai-agent-book/what-patterns-for-agent-self-evolution-and-continuous-learning)

Explore agent self-evolution and continuous learning patterns. Discover versioned memory and a proposer-reviewer loop for iterative code improvement in the ai-agent-book repository.

- Tags: deep-dive
- Published: 2026-08-17

### [How to Build Evaluation-Driven Model Selection for Agent Systems](/bojieli/ai-agent-book/how-to-build-evaluation-driven-model-selection-for-agent-systems)

Build evaluation-driven model selection for agent systems. Use reproducible benchmarks and LLM-as-a-Judge to score agent performance. Optimize models with statistical evidence while managing latency and cost.

- Tags: how-to-guide
- Published: 2026-08-17

### [KV Cache Optimization in Agent Context: 3 Patterns to Cut Inference Costs by 30%](/bojieli/ai-agent-book/what-is-the-role-of-kv-cache-optimization-in-agent-context)

Optimize KV Cache in agent context to cut inference costs by 30%. Learn 3 patterns for structuring conversation history and reusing cached key-value matrices for efficient AI.

- Tags: performance
- Published: 2026-08-17

### [How to Implement Streaming Speech Processing with VAD, ASR, and TTS](/bojieli/ai-agent-book/how-to-implement-streaming-speech-processing-with-vad-asr-and-tts)

Implement streaming speech processing with VAD, ASR, and TTS. Explore a production-ready reference implementation for real-time barge-in capabilities in the bojieli ai-agent-book repository.

- Tags: how-to-guide
- Published: 2026-08-17

### [How to Design Agent Skill Orchestration and Active Tool Discovery](/bojieli/ai-agent-book/how-to-design-agent-skill-orchestration-and-active-tool-discovery)

Learn agent skill orchestration with state-machine workflows and role-based tool permissions. Discover active tool discovery for runtime expansion via semantic search when needed.

- Tags: how-to-guide
- Published: 2026-08-17

### [The Three Paradigms of Voice Agent Implementation: Cascaded, End-to-End, and Full-Duplex](/bojieli/ai-agent-book/what-are-the-three-paradigms-of-voice-agent-implementation)

Explore the three voice agent implementation paradigms: cascaded, end-to-end, and full-duplex. Understand their trade-offs in modularity, latency, and complexity.

- Tags: deep-dive
- Published: 2026-08-17

### [How the Browser-Use Framework Enables Computer Use with Open-Source Models](/bojieli/ai-agent-book/how-does-the-browser-use-framework-enable-computer-use-with-open-source-models)

Learn how the browser-use framework empowers open-source LLMs like Llama 3 to control web browsers. Discover the think act observe loop for AI agent computer use.

- Tags: deep-dive
- Published: 2026-08-17

### [Sim-to-Real Transfer in Robotic Manipulation Agents: 7 Proven Strategies from the AI Agent Book](/bojieli/ai-agent-book/what-strategies-for-sim-to-real-transfer-in-robotic-manipulation-agents)

Unlock sim-to-real transfer for robotic manipulation. Discover 7 AI agent book strategies including domain randomization, LLM rewards, and hardware fine-tuning. Improve your robot's real-world performance today.

- Tags: deep-dive
- Published: 2026-08-17

### [How to Implement Persistent User Memory Across Agent Sessions](/bojieli/ai-agent-book/how-to-implement-persistent-user-memory-across-agent-sessions)

Learn how to implement persistent user memory across agent sessions using PostgresMemoryStore and MemoryFactory. Ensure user data survives process restarts with this guide.

- Tags: how-to-guide
- Published: 2026-08-17

### [How to Evaluate AI Agent Performance Using OSWorld, SWE-bench, and GAIA Benchmarks](/bojieli/ai-agent-book/what-benchmarks-and-metrics-evaluate-agent-performance-osworld-swe-bench-gaia)

Learn how to evaluate AI agent performance using OSWorld, SWE-bench, and GAIA benchmarks. Discover key metrics and methods for assessing AI capabilities.

- Tags: deep-dive
- Published: 2026-08-17

### [Production-Grade Coding Agent Architecture: Inside the AI Agent Book Implementation](/bojieli/ai-agent-book/what-is-the-architecture-of-production-grade-coding-agents)

Discover the production-grade coding agent architecture: streaming LLM, modular tool registry, and self-aware hint engine for secure autonomous code generation. Explore the implementation.

- Tags: architecture
- Published: 2026-08-17

### [Tradeoffs Between Context Compression Techniques for LLMs: A Deep Dive into AI-Agent-Book](/bojieli/ai-agent-book/what-are-tradeoffs-between-context-compression-techniques-for-llms)

Explore LLM context compression tradeoffs. Discover why simple truncation is fast but lossy, summarization is semantic but costly, and token-level methods offer a balanced approach. Learn more.

- Tags: deep-dive
- Published: 2026-08-17

### [How RAG Integrates with Agent Memory Systems: A Dual-Layer Architecture](/bojieli/ai-agent-book/how-does-rag-integrate-with-agent-memory-systems)

Learn how RAG integrates with agent memory systems using a dual-layer architecture. Combine short-term history and long-term knowledge for context-aware AI.

- Tags: deep-dive
- Published: 2026-08-17

### [Best Practices for Event-Driven Async Agents with FastAPI](/bojieli/ai-agent-book/what-are-best-practices-for-event-driven-async-agents-with-fastapi)

Learn best practices for event-driven async agents with FastAPI. Implement resource management, state protection, background tasks, and health endpoints for production-grade AI agents.

- Tags: best-practices
- Published: 2026-08-17

### [How MCP Enables Tool Interoperability in AI Agents: A Technical Deep Dive](/bojieli/ai-agent-book/how-does-mcp-enable-tool-interoperability-in-ai-agents)

Discover how MCP enables tool interoperability in AI agents. Learn about standardized descriptions, abstract transport, and dynamic discovery for seamless integration.

- Tags: deep-dive
- Published: 2026-08-17

### [How Agent Evaluation Relates to Simulation Environments in AI Development](/bojieli/ai-agent-book/agent-evaluation-vs-simulation-environments)

Discover how AI agent evaluation uses simulation environments as ground-truth recorders. Learn about trajectory consumption, deterministic checks, and policy verification for effective AI development.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Implement Computer Use and GUI Automation Agents: A Complete Guide](/bojieli/ai-agent-book/implement-computer-use-gui-automation-agents)

Learn how to implement computer use and GUI automation agents. This guide details capturing screenshots, LLM interaction, and command execution for efficient automation.

- Tags: how-to-guide
- Published: 2026-08-06

### [Agent Continuous Evolution from Run Trajectories: 7 Techniques for Self-Improving AI Systems](/bojieli/ai-agent-book/agent-continuous-evolution-run-trajectories-techniques)

Discover 7 techniques for AI agent continuous evolution. Learn how agents analyze run trajectories to self-improve without human intervention. Boost your AI system's performance.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Implement Multi-Agent Collaboration with Context Sharing and Isolation in Python](/bojieli/ai-agent-book/multi-agent-collaboration-context-sharing-isolation)

Implement multi-agent collaboration in Python using Swarm, Context, and ContextRule from ai-agent-book. Master configurable state sharing and isolation for advanced AI systems.

- Tags: how-to-guide
- Published: 2026-08-06

### [Model as Agent Paradigm: When to Use Autonomous LLM Tool Calling](/bojieli/ai-agent-book/model-as-agent-paradigm-when-to-use)

Understand the Model as Agent paradigm and when to use it. Discover how LLMs autonomously decide tool usage, revolutionizing agent control without external orchestration.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Implement Event-Driven Asynchronous Agent Architecture: A Production-Ready Guide](/bojieli/ai-agent-book/implement-event-driven-asynchronous-agent-architecture)

Implement event driven asynchronous agent architecture using asyncio and uniform event messages. Learn production ready techniques from bojieli ai agent book repository for scalable AI agents.

- Tags: how-to-guide
- Published: 2026-08-06

### [The Three Phases of Agent Model Post‑Training: Pre‑training, SFT, and RL Explained](/bojieli/ai-agent-book/three-phases-agent-model-post-training)

Master agent model post-training. Understand the three key phases: pre-training for language priors, SFT for instruction alignment, and RL for reward optimization and tool use.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Use LoRA for Parameter-Efficient Fine-Tuning of Agent Models: Complete Implementation Guide](/bojieli/ai-agent-book/use-lora-parameter-efficient-fine-tuning-agent-models)

Master LoRA for parameter-efficient fine-tuning of agent models. This guide shows how to adapt large models on single GPUs, reducing trainable parameters significantly. Get the complete implementation guide.

- Tags: how-to-guide
- Published: 2026-08-06

### [SFT vs RL for Agent Model Training: Key Differences and When to Use Each](/bojieli/ai-agent-book/sft-vs-rl-agent-model-training)

Discover the key differences between SFT and RL for agent model training. Learn when to use SFT for memorization and RL for generalizable strategies.

- Tags: deep-dive
- Published: 2026-08-06

### [How LLM-as-a-Judge Works for Automated Agent Evaluation in ai-agent-book](/bojieli/ai-agent-book/llm-as-a-judge-automated-agent-evaluation)

Discover how LLM-as-a-Judge automates agent evaluation using language models for scoring open-ended behaviors. Learn this effective technique for AI agent assessment.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Evaluate Agent Performance: Metrics, Benchmarks, and Significance in the AI-Agent-Book Repository](/bojieli/ai-agent-book/evaluate-agent-performance-metrics-benchmarks-significance)

Discover how to evaluate agent performance with key metrics, benchmarks, and significance. Learn the three-tier system for safe AI agent deployment from the AI-Agent-Book repository.

- Tags: deep-dive
- Published: 2026-08-06

### [KV Cache Optimization Techniques for Context Engineering: 8 Proven Methods from the ai-agent-book Repository](/bojieli/ai-agent-book/kv-cache-optimization-techniques-context-engineering)

Discover 8 KV Cache optimization techniques for context engineering. Boost performance, reduce API costs, and speed up generation with these proven methods from ai-agent-book.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Build User Memory and Knowledge Bases with RAG: A Complete Implementation Guide](/bojieli/ai-agent-book/build-user-memory-knowledge-bases-rag)

Learn to build user memory and knowledge bases with RAG. Persist conversation history, index it, and use OpenAI function-calling for LLM access. A complete implementation guide.

- Tags: how-to-guide
- Published: 2026-08-06

### [Sessionless Design Pattern: Architecture for Always-Available AI Agents](/bojieli/ai-agent-book/sessionless-design-pattern-always-available-agents)

Explore the sessionless design pattern for always-available AI agents. Learn how this architecture ensures instant responsiveness without logins or UI.

- Tags: architecture
- Published: 2026-08-06

### [Security Considerations for Coding Agents: Sandbox and Command Parsing Explained](/bojieli/ai-agent-book/security-considerations-coding-agents-sandbox-command-parsing)

Learn essential security considerations for coding agents. Discover how sandboxing and command parsing prevent privilege escalation and data exfiltration in your AI agent development.

- Tags: best-practices
- Published: 2026-08-06

### [How the File System Functions as the Central Nervous System for AI Agents](/bojieli/ai-agent-book/filesystem-central-nervous-system-for-agents)

Discover how the file system acts as the central nervous system for AI agents, coordinating perception, memory, and action dispatch through LLM tools for seamless operation.

- Tags: deep-dive
- Published: 2026-08-06

### [How to Build a Coding Agent with Seven Core Tools](/bojieli/ai-agent-book/build-coding-agent-seven-core-tools)

Build a coding agent that reads writes and executes code with seven core Python tools. Learn how to orchestrate LLM code execution autonomously.

- Tags: how-to-guide
- Published: 2026-08-05

### [Implementing Tool Granularity Tradeoffs: Integration vs. Separation in AI Agent Frameworks](/bojieli/ai-agent-book/implement-tool-granularity-tradeoffs-integration-separation)

Learn to implement tool granularity tradeoffs in AI agent frameworks by balancing LLM load with implementation complexity and performance transparency. Decide integration vs. separation for optimal results.

- Tags: deep-dive
- Published: 2026-08-05

### [What Is MCP (Model Context Protocol)? A Complete Guide to Standardizing AI Tool Ecosystems](/bojieli/ai-agent-book/what-is-mcp-model-context-protocol-standardize-tool-ecosystems)

Discover the Model Context Protocol MCP, an open standard from Anthropic. Learn how MCP unifies AI tool integration with a client-server architecture and JSON-Schema for seamless discovery and invocation.

- Tags: deep-dive
- Published: 2026-08-05

### [How to Design Effective Tool Descriptions for LLM Tool Calling: 7 Patterns from ai-agent-book](/bojieli/ai-agent-book/design-effective-tool-descriptions-llm-tool-calling)

Learn to design effective LLM tool descriptions using 7 patterns from ai-agent-book. Optimize clarity, minimize token usage, and maximize actionability for better tool calling.

- Tags: how-to-guide
- Published: 2026-08-05

### [Observation Space vs Action Space in LLM Agents: Key Differences Explained](/bojieli/ai-agent-book/observation-space-vs-action-space-llm-agents)

Understand the key differences between observation space and action space in LLM agents. Learn what information agents perceive and what actions they can perform.

- Tags: deep-dive
- Published: 2026-08-05

### [Preventing Prompt Injection Attacks in Production AI Agents: A Two-Layer Defense Strategy](/bojieli/ai-agent-book/preventing-prompt-injection-attacks-in-production-ai-agents)

Secure your AI agents from prompt injection attacks. Implement a two-layer defense strategy for production systems to protect against malicious inputs.

- Tags: best-practices
- Published: 2026-08-01

### [Speech Interaction Paradigms for AI Agents: Live, Streaming, and End-to-End Architectures](/bojieli/ai-agent-book/speech-interaction-paradigms-for-ai-agents)

Explore speech interaction paradigms for AI agents including live, streaming, and end-to-end architectures. Discover real-time voice AI implementations from bojieli/ai-agent-book.

- Tags: architecture
- Published: 2026-08-01

### [Voice-first Agent Architectures: Three Implementation Patterns from the AI Agent Book](/bojieli/ai-agent-book/voice-first-agent-architectures)

Explore voice-first agent architectures with three key patterns: cascaded, end-to-end, and full-duplex. Learn to balance modularity, latency, and observability.

- Tags: deep-dive
- Published: 2026-08-01

### [How AI Agents Achieve Continuous Learning from Execution Traces: A Complete Technical Guide](/bojieli/ai-agent-book/ai-agent-continuous-learning-from-execution-traces)

Master AI agent continuous learning from execution traces. Discover the technical guide detailing the three-layer verification pipeline for structured learning signals and persistent memory.

- Tags: deep-dive
- Published: 2026-08-01

### [Implementing Cross-Session User Memory Systems for AI Agents: A Complete Technical Guide](/bojieli/ai-agent-book/implementing-cross-session-user-memory-systems-for-ai-agents)

Master cross-session user memory for AI agents with this technical guide. Learn to implement persistent memory using pluggable backends and background fact extraction for production-ready systems.

- Tags: how-to-guide
- Published: 2026-08-01

### [Visualizing LLM Attention Mechanisms for Debugging: A Complete Toolkit](/bojieli/ai-agent-book/visualizing-llm-attention-mechanisms-for-debugging)

Debug LLM behavior with a complete toolkit for visualizing attention mechanisms. Convert raw Transformer weights into actionable heatmaps, flow diagrams, and statistical summaries.

- Tags: tutorial
- Published: 2026-08-01

### [AI Agent Tool Design Patterns: Collaboration Tools](/bojieli/ai-agent-book/ai-agent-tool-design-patterns-collaboration-tools)

Discover AI agent tool design patterns for collaboration. Learn how MCP servers transform utility functions into first-class tools for LLM agents via a JSON-RPC-like interface.

- Tags: design-patterns
- Published: 2026-08-01

### [AI Agent Tool Design Patterns: How Execution Tools Enable Self-Evolving Agents](/bojieli/ai-agent-book/ai-agent-tool-design-patterns-execution-tools)

Discover AI agent execution tool design patterns. Learn how a five step pipeline enables self evolving agents to extend capabilities without human intervention.

- Tags: deep-dive
- Published: 2026-08-01

### [AI Agent Tool Design Patterns: Perception Tools Explained](/bojieli/ai-agent-book/ai-agent-tool-design-patterns-perception-tools)

Explore AI agent tool design patterns focusing on perception tools. Learn how FastMCP architecture enables dynamic tool discovery for seamless interaction with web search, file systems, and APIs.

- Tags: deep-dive
- Published: 2026-08-01

### [Implementing RAPTOR for Structured Knowledge Retrieval: A Complete Guide to Tree-Based Document Indexing](/bojieli/ai-agent-book/implementing-raptor-for-structured-knowledge-retrieval)

Learn to implement RAPTOR for structured knowledge retrieval. This guide explains tree-based document indexing with recursive summarization and semantic embeddings for efficient information access.

- Tags: how-to-guide
- Published: 2026-08-01

### [Implementing GraphRAG for Structured Knowledge Retrieval: A Complete Guide](/bojieli/ai-agent-book/implementing-graphrag-for-structured-knowledge-retrieval)

Implement GraphRAG for structured knowledge retrieval. This guide shows how to build agentic systems with LLM-powered entity extraction and multi-hop traversal for explainable evidence.

- Tags: how-to-guide
- Published: 2026-08-01

### [LLM Tool Calling Internalization in AI Agent Book: A Provider Registry Architecture](/bojieli/ai-agent-book/llm-tool-calling-internalization)

Master LLM tool calling internalization with a provider registry architecture. Dynamically add tools to your AI agent without changing code. Explore the AI Agent Book.

- Tags: architecture
- Published: 2026-08-01

### [LLM Post-Training: SFT vs RL Tradeoffs and Implementation Strategies](/bojieli/ai-agent-book/llm-post-training-sft-vs-rl-tradeoffs)

Explore LLM post-training: understand Supervised Fine-Tuning SFT vs Reinforcement Learning RL tradeoffs and implementation strategies. Optimize your AI agent's performance.

- Tags: deep-dive
- Published: 2026-08-01

### [Building AI Agents for Automated Code Generation: A Complete Guide Using the ai-agent-book Repository](/bojieli/ai-agent-book/building-ai-agents-for-automated-code-generation)

Learn to build AI agents for automated code generation using the ai-agent-book repository. Explore 95+ Python experiments and a reusable SDK for seamless multi-backend code creation.

- Tags: how-to-guide
- Published: 2026-08-01

### [Multi-Agent Context Sharing Patterns: Architecture Guide from AI-Agent-Book](/bojieli/ai-agent-book/multi-agent-context-sharing-patterns)

Explore multi-agent context sharing patterns architecture. Understand shared/non-shared context and collaboration topology for effective agent communication and history inheritance.

- Tags: architecture
- Published: 2026-08-01

### [Multi-Agent Collaboration Frameworks: A Deep Dive into the ai-agent-book Repository](/bojieli/ai-agent-book/multi-agent-collaboration-frameworks)

Explore multi-agent collaboration frameworks in the ai-agent-book repository. Discover sequential delegation, parallel ensemble, hierarchical tree, and feedback loop patterns for building advanced AI systems.

- Tags: deep-dive
- Published: 2026-08-01

### [Designing Multimodal AI Agents with Speech Capabilities: A Production-Ready Guide](/bojieli/ai-agent-book/designing-multimodal-ai-agents-with-speech-capabilities)

Design production-ready multimodal AI agents with speech capabilities. Explore a complete, auditable stack for building speaking and listening AI agents with configurable TTS and end-to-end speech models.

- Tags: how-to-guide
- Published: 2026-08-01

### [Designing Multimodal AI Agents with Vision Capabilities: A Complete Implementation Guide](/bojieli/ai-agent-book/designing-multimodal-ai-agents-with-vision-capabilities)

Learn to design multimodal AI agents with vision capabilities. Explore native vision, extract-to-text, and tool-on-demand modes using the MultimodalAgent class.

- Tags: how-to-guide
- Published: 2026-08-01

### [Context Engineering Best Practices: Prompt Compression for AI Agents](/bojieli/ai-agent-book/context-engineering-best-practices-prompt-compression)

Master prompt compression for AI agents. Learn context engineering best practices to prevent overflow and ensure accurate reasoning by condensing conversation data.

- Tags: best-practices
- Published: 2026-08-01

### [Context Engineering Best Practices: KV Cache Optimization for AI Agents](/bojieli/ai-agent-book/context-engineering-best-practices-kv-cache-optimization)

Master KV cache optimization for AI agents. Reduce time-to-first-token from seconds to milliseconds by reusing attention key-value pairs. Boost AI performance now.

- Tags: best-practices
- Published: 2026-08-01

### [Building Production-Ready RAG Systems with Knowledge Graphs: A Complete Implementation Guide](/bojieli/ai-agent-book/building-production-ready-rag-systems-with-knowledge-graphs)

Build production-ready RAG systems with knowledge graphs using LLMs and ReAct. Master dense vector search, BM25, and graph traversal for complex queries. Learn implementation now.

- Tags: how-to-guide
- Published: 2026-08-01

### [How to Implement MCP Protocol for AI Agent Tool Integration: A Complete Guide](/bojieli/ai-agent-book/how-to-implement-mcp-protocol-for-ai-agent-tool-integration)

Learn to implement the MCP protocol for AI agent tool integration. This guide covers using the mcp SDK Server class and registration decorators for seamless external tool calls and structured results.

- Tags: how-to-guide
- Published: 2026-08-01

### [Sim2Real Transfer for Robotics AI Agents: Implementation Guide with AI Agent Book](/bojieli/ai-agent-book/simulation-to-real-sim2real-transfer-for-robotics-agents)

Master Sim2Real transfer for robotics AI agents with the AI Agent Book. Explore a modular framework for seamless simulation-to-real-world deployment and reduce development time.

- Tags: how-to-guide
- Published: 2026-07-31

### [How to Extend LLM Capabilities with an Agent Skill System: A Three-Layer Progressive Disclosure Pattern](/bojieli/ai-agent-book/agent-skill-system-extending-llm-capabilities-with-custom-skills)

Extend LLM capabilities with an agent skill system using a progressive disclosure pattern. This approach minimizes context while maximizing extensibility by loading skills and workflows on demand.

- Tags: deep-dive
- Published: 2026-07-31

### [Evaluating Agents on Mobile App Automation with Android World: A Complete Framework](/bojieli/ai-agent-book/android-world-agent-evaluation-on-mobile-application-automation)

Evaluate AI agents on mobile app automation with Android World. Explore a modular framework for benchmarking autonomous agents on real-world tasks with controlled experiments and reproducible metrics.

- Tags: tutorial
- Published: 2026-07-31

### [Evaluating AI Agents in CLI Environments with Terminal-Bench: A Complete Technical Guide](/bojieli/ai-agent-book/terminal-bench-evaluating-agents-in-cli-environments)

Master evaluating AI agents in CLI environments with Terminal-Bench. This technical guide details a Docker-based framework for performance measurement and verification.

- Tags: how-to-guide
- Published: 2026-07-31

### [How to Integrate Knowledge Graphs for Structured Agent Memory](/bojieli/ai-agent-book/knowledge-graph-integration-for-structured-agent-memory)

Learn to integrate knowledge graphs for structured agent memory. Extend the KnowledgeBase class to store RDF triples and enable semantic search and graph queries for enhanced AI agent capabilities.

- Tags: how-to-guide
- Published: 2026-07-31

### [Browser Automation Tools for Web Agent Execution: Playwright, browser-use, and Python webbrowser](/bojieli/ai-agent-book/browser-automation-tools-for-web-based-agent-execution)

Explore Playwright, browser-use, and Python webbrowser for efficient web agent execution. Discover the best tools for your AI agent projects.

- Tags: deep-dive
- Published: 2026-07-31

### [User Memory Architecture for Cross-Session Context Persistence in Agents: A Deep Dive into the ai-agent-book Implementation](/bojieli/ai-agent-book/user-memory-architecture-cross-session-context-persistence-in-agents)

Explore the user memory architecture for cross-session context persistence in agents. Learn how ai-agent-book uses layered memory, JSON storage, and LLM analysis for seamless continuity.

- Tags: deep-dive
- Published: 2026-07-31

### [Continual Pretraining vs Domain Adaptation for Agent Fine-Tuning: When to Use Each Strategy](/bojieli/ai-agent-book/continual-pretraining-vs-domain-adaptation-for-agent-fine-tuning)

Understand continual pretraining vs domain adaptation for agent fine-tuning. Learn when to apply each strategy to boost your AI agent's performance and knowledge.

- Tags: deep-dive
- Published: 2026-07-31

### [Multi-Modal Agent Cost Analysis and Optimization: A Practical Guide to Reducing AI Agent Expenses](/bojieli/ai-agent-book/multi-modal-agent-cost-analysis-and-optimization-strategies)

Master multi-modal agent cost analysis and optimization. Learn strategies like prompt distillation and batch inference to cut AI agent expenses by up to 75%.

- Tags: how-to-guide
- Published: 2026-07-31

### [How to Design and Implement an ELO-Based Agent Performance Leaderboard](/bojieli/ai-agent-book/elo-based-agent-performance-leaderboard-design-and-implementation)

Learn to design and implement an ELO based agent performance leaderboard with this ready to run implementation. Calculate agent ratings from match results and track performance over time.

- Tags: how-to-guide
- Published: 2026-07-31

### [Real-time Voice Interaction Paradigms for AI Agents: Architecture and Implementation](/bojieli/ai-agent-book/speech-three-paradigms-real-time-voice-interaction-for-ai-agents)

Explore real-time voice interaction paradigms for AI agents. Learn about VAD, cascaded provider pipelines, and WebSocket streaming for sub-second conversational AI in the bojieli ai-agent-book repo.

- Tags: architecture
- Published: 2026-07-31

### [Building GUI Automation Agents with Vision-Language Models: A Complete Implementation Guide](/bojieli/ai-agent-book/computer-use-building-gui-automation-agents-with-vision-language-models)

Build GUI automation agents with vision-language models. Learn the complete implementation guide for autonomous GUI control using the Perceive-Think-Act loop.

- Tags: how-to-guide
- Published: 2026-07-31

### [Prompt Injection Attacks and Defense Strategies in AI Agent Systems](/bojieli/ai-agent-book/prompt-injection-attacks-and-defense-strategies-in-agent-systems)

Understand prompt injection attacks in AI agent systems. Learn effective defense strategies like context isolation and execution restrictions to protect your AI agents from malicious inputs and unauthorized actions.

- Tags: deep-dive
- Published: 2026-07-31

### [RAG Implementation Patterns for Agent Knowledge Base Integration: 5 Modular Architectures](/bojieli/ai-agent-book/rag-implementation-patterns-for-agent-knowledge-base-integration)

Explore 5 RAG implementation patterns for agent knowledge base integration. Discover modular architectures from offline BM25 to graph-based retrieval with bojieli/ai-agent-book.

- Tags: architecture
- Published: 2026-07-31

### [How Agents Discover and Select Optimal Tool Combinations Dynamically](/bojieli/ai-agent-book/active-tool-discovery-how-agents-dynamically-select-optimal-tool-combinations)

Learn how AI agents dynamically discover and select optimal tool combinations by identifying gaps, retrieving specialists via semantic search, and prioritizing domain-specific tools.

- Tags: deep-dive
- Published: 2026-07-31

### [Designing Multi-Agent Collaboration Frameworks with Context Sharing: A Production-Ready Implementation](/bojieli/ai-agent-book/designing-multi-agent-collaboration-frameworks-with-context-sharing-and-isolation)

Implement production-ready multi-agent collaboration frameworks. Learn secure context sharing with explicit JSON payloads and role-based isolation from bojieli/ai-agent-book.

- Tags: deep-dive
- Published: 2026-07-31

### [How to Evaluate AI Agent Performance Using τ-Bench, GAIA, or OSWorld](/bojieli/ai-agent-book/evaluating-agent-performance-tau-bench-vs-gaia-vs-osworld-benchmarks)

Learn to evaluate AI agent performance with τ-Bench, GAIA, or OSWorld. Configure frameworks and run evaluations to measure pass@k and exact-match metrics for AI agent capabilities.

- Tags: how-to-guide
- Published: 2026-07-31

### [SFT vs RL for Tool Calling in LLMs: A Complete Technical Guide](/bojieli/ai-agent-book/comparing-sft-vs-rl-for-tool-calling-internalization-in-llms)

Compare SFT vs RL for LLM tool calling. Discover how SFT teaches syntax and RL optimizes strategy, with the combined SFT->RL pipeline achieving higher accuracy and lower costs. Master effective tool use.

- Tags: deep-dive
- Published: 2026-07-31

### [How to Implement Asynchronous Agent Architecture with FastAPI: A Production-Ready Pattern](/bojieli/ai-agent-book/implementing-event-driven-asynchronous-agent-architecture-with-fastapi)

Implement asynchronous agent architecture with FastAPI. Leverage async/await and lifespan events for non-blocking AI agent initialization, ensuring a responsive server during heavy I/O operations like tool loading and LLM setup.

- Tags: how-to-guide
- Published: 2026-07-31

### [KV Cache Optimization Strategies for Agent Context Management: 6 Proven Methods Explained](/bojieli/ai-agent-book/kv-cache-optimization-strategies-for-context-management-in-production-agents)

Master KV cache optimization for agent context management. Discover 6 proven strategies to boost LLM performance and reduce computation with a stable prompt prefix.

- Tags: deep-dive
- Published: 2026-07-31

### [How MCP Protocol Helps AI Agents Abstract Tools: A Technical Implementation Guide](/bojieli/ai-agent-book/how-mcp-protocol-enables-tool-abstraction-for-ai-agents)

Discover how MCP Protocol enables AI agents to abstract tools seamlessly. Learn the technical implementation for standardized, language-agnostic interaction with external capabilities. Boost agent functionality today.

- Tags: how-to-guide
- Published: 2026-07-31

### [How to Implement Tool Parameter Fidelity to Prevent Silent Input Transformation Bugs in Agents](/bojieli/ai-agent-book/implement-tool-parameter-fidelity-avoid-silent-input-bugs-agents)

Prevent silent input transformation bugs in AI agents. Implement tool parameter fidelity using JSON Schema contracts and validation to ensure accurate parameter passing during tool execution.

- Tags: best-practices
- Published: 2026-07-30

### [AI Agent Cost Analysis and Performance Benchmarking: A Complete Framework](/bojieli/ai-agent-book/ai-agent-cost-analysis-performance-benchmarking-best-practices)

Master AI Agent cost analysis and performance benchmarking with a complete framework. Track finances and metrics efficiently for optimal results. Learn best practices now.

- Tags: best-practices
- Published: 2026-07-30

### [How to Implement AI Agent Memory Using Markdown Files Instead of Vector Databases](/bojieli/ai-agent-book/ai-agent-memory-markdown-files-vs-vector-databases)

Learn to implement AI agent memory using Markdown files and TF-IDF for lightweight text retrieval. Replace complex vector databases with simple .md files in your AI agent projects.

- Tags: how-to-guide
- Published: 2026-07-30

### [Dedicated Tools vs. Skills and General Executors: Trade-offs for AI Agent Capabilities](/bojieli/ai-agent-book/dedicated-tools-vs-skills-general-executors-ai-agent-capabilities)

Discover the trade-offs between dedicated tools and skills for AI agent capabilities. Learn when to use each for optimal performance and determinism in complex operations.

- Tags: architecture
- Published: 2026-07-30

### [How to Design Effective Tool Descriptions for AI Agents with Parameter Examples](/bojieli/ai-agent-book/design-effective-tool-descriptions-ai-agents-parameter-examples)

Learn to design effective AI agent tool descriptions using imperative verbs, JSON Schema parameters with examples, and operational contracts for reliable function calling and autonomous error recovery.

- Tags: best-practices
- Published: 2026-07-30

### [Understanding the "Agent = LLM + Context + Tools" Formula and Context's Role in AI Agent Capability](/bojieli/ai-agent-book/agent-llm-context-tools-formula-context-capability-ceiling)

Explore the Agent = LLM + Context + Tools formula. Understand how context powers AI agent capabilities, binding LLM reasoning to external tools for enhanced performance.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Implement Multimodal AI Agents with Speech, GUI, and Robotics Capabilities](/bojieli/ai-agent-book/implement-multimodal-ai-agents-speech-gui-robotics)

Learn to implement multimodal AI agents with speech, GUI, and robotics. Orchestrate an Agent Core, perception tools, FastAPI GUI, and MCP for robotics control. Explore the bojieli/ai-agent-book repo.

- Tags: how-to-guide
- Published: 2026-07-30

### [Strategies for AI Agent Continuous Evolution from Runtime Trajectories: A Closed-Loop Architecture](/bojieli/ai-agent-book/ai-agent-continuous-evolution-runtime-trajectories)

Unlock AI agent continuous evolution with runtime trajectories. Learn how structured diagnostics and recurring patterns drive auditable knowledge for advanced AI.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Implement Scalable Tool Discovery for AI Agents Managing Hundreds of Tools](/bojieli/ai-agent-book/implement-tool-discovery-ai-agents-hundreds-tools)

Implement scalable tool discovery for AI agents. Learn to manage hundreds of tools efficiently using JSON libraries, keyword search, and sandboxed execution. Optimize agent performance today.

- Tags: how-to-guide
- Published: 2026-07-30

### [Multi-Agent Collaboration and Context Sharing/Isolation Architecture in Python](/bojieli/ai-agent-book/multi-agent-collaboration-context-sharing-isolation-architecture)

Explore the ai-agent-book Python architecture for multi-agent collaboration. Discover how Swarm, Context, and ContextRule enable secure, configurable memory sharing and isolation.

- Tags: architecture
- Published: 2026-07-30

### [How to Implement Event-Driven Asynchronous AI Agent Architecture](/bojieli/ai-agent-book/implement-event-driven-asynchronous-ai-agent-architecture)

Learn to implement event-driven asynchronous AI Agent architecture using standardized message events, asyncio coroutines, and event bus coordination for scalable and observable systems. Explore the bojieli/ai-agent-book repo.

- Tags: how-to-guide
- Published: 2026-07-30

### [SFT vs RL for AI Agent Post-Training: Core Differences and Implementation Guide](/bojieli/ai-agent-book/sft-vs-rl-ai-agent-post-training)

Discover SFT vs RL for AI agent post-training. Learn core differences: SFT memorizes, RL generalizes. Get implementation insights to optimize your AI.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Evaluate AI Agent Performance Using GAIA, OSWorld, and SWE-bench](/bojieli/ai-agent-book/evaluate-ai-agent-performance-benchmarks-gaia-osworld-swe-bench)

Evaluate AI agent performance using benchmarks like GAIA, OSWorld, and SWE-bench. Learn how to use companion tools in the ai-agent-book repository for comprehensive testing.

- Tags: how-to-guide
- Published: 2026-07-30

### [How to Implement User Memory Across Sessions in AI Agents Using RAG and Knowledge Graphs](/bojieli/ai-agent-book/implement-user-memory-ai-agents-rag-knowledge-graphs)

Learn to implement user memory across AI agent sessions using RAG and knowledge graphs. Enhance conversations with persistent cross-session memory storage and retrieval.

- Tags: how-to-guide
- Published: 2026-07-30

### [Context Engineering in AI Agents: KV Cache and Prompt Engineering Best Practices](/bojieli/ai-agent-book/ai-agent-context-engineering-best-practices-kv-cache-prompt-engineering)

Master context engineering for AI agents. Learn KV cache and prompt engineering best practices to boost performance and cut costs.

- Tags: best-practices
- Published: 2026-07-30

### [How to Implement Sandbox Isolation for Safe Code Execution in AI Agents: A Modular Framework Guide](/bojieli/ai-agent-book/implement-sandbox-isolation-safe-code-execution-ai-agents)

Secure your AI agents by implementing sandbox isolation for safe code execution. Discover a modular framework in the bojieli/ai-agent-book repository for robust and efficient isolation.

- Tags: how-to-guide
- Published: 2026-07-30

### [Security Threats in Coding Agents: The Three Lethal Elements Attack Explained](/bojieli/ai-agent-book/security-threats-coding-agents-three-lethal-elements-attack)

Discover security threats in coding agents including the three lethal elements attack. Learn how private data exposure, untrusted content, and network communication enable prompt injection and data exfiltration.

- Tags: deep-dive
- Published: 2026-07-30

### [Sessionless Design Pattern for Always-On Agents: State Persistence Architecture](/bojieli/ai-agent-book/sessionless-design-pattern-always-on-agents-state-persistence)

Discover the Sessionless design pattern for always-on AI agents. Learn how state persistence maintains responsiveness by decoupling user sessions from process lifetimes. Explore two-layer state management for external file pers...

- Tags: architecture
- Published: 2026-07-30

### [How OpenClaw Architecture Implements a General-Purpose Agent with a Coding Kernel](/bojieli/ai-agent-book/how-openclaw-implements-general-purpose-agent-coding-kernel)

Discover how OpenClaw architecture implements a general-purpose agent with a coding kernel. Learn about code execution tool orchestration and state management.

- Tags: architecture
- Published: 2026-07-30

### [Coding Agent Architecture: A Deep Dive into the Seven Core Tools](/bojieli/ai-agent-book/architecture-coding-agent-seven-core-tools)

Explore the Coding Agent architecture built with seven core tools: Read, Write, Grep, Glob, Bash, Code Interpreter, and Generic Executor for autonomous coding workflows.

- Tags: deep-dive
- Published: 2026-07-30

### [How the MCP Protocol Standardizes Tool Ecosystems in AI Agents](/bojieli/ai-agent-book/how-mcp-protocol-standardizes-ai-agent-tool-ecosystems)

Discover how the MCP protocol standardizes AI agent tool ecosystems with a unified RPC interface, JSON schema contracts, and language-agnostic HTTP transport for seamless integration.

- Tags: deep-dive
- Published: 2026-07-30

### [Future Trends in AI Agent Development: 8 Directions Shaping Autonomous Systems](/bojieli/ai-agent-book/what-are-future-trends-in-ai-agent-development)

Discover future trends in AI agent development including self-improving loops, persistent memory, and parallel execution. Explore 8 directions shaping autonomous systems.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Fine-Tune Pre-Trained Models for Agent Tasks: A Complete TRL Pipeline](/bojieli/ai-agent-book/how-to-fine-tune-pre-trained-models-for-agent-tasks)

Fine-tune pre-trained models for agent tasks using TRL and LoRA adapters. Convert generic LLMs into task-oriented agents with our complete pipeline and chat-formatted datasets. Easy and effective.

- Tags: how-to-guide
- Published: 2026-07-30

### [Frameworks for Building Goal-Oriented AI Agents: A Technical Deep Dive into ai-agent-book](/bojieli/ai-agent-book/frameworks-for-building-goal-oriented-ai-agents)

Explore frameworks for building goal-oriented AI agents with ai-agent-book. Learn the Agent = LLM + Context + Tools equation through 94 code experiments and theoretical insights.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Manage State and Memory in AI Agents: Versioned Storage and Profile-Based Updates](/bojieli/ai-agent-book/how-to-manage-state-and-memory-in-ai-agents)

Learn to manage AI agent state and memory using versioned storage and profile updates. Track context and rule application for better AI performance.

- Tags: deep-dive
- Published: 2026-07-30

### [Best Libraries for Building Autonomous Agents: A Production-Ready Stack from ai-agent-book](/bojieli/ai-agent-book/best-libraries-for-building-autonomous-agents)

Discover the best libraries for building autonomous agents. Leverage LLM clients, browser automation, tool libraries, and code interpreters for a production-ready stack based on ai-agent-book.

- Tags: best-practices
- Published: 2026-07-30

### [How to Ensure Explainability in AI Agents: A Trajectory-Centric Architecture](/bojieli/ai-agent-book/how-to-ensure-explainability-in-ai-agents)

Ensure AI agent explainability by recording interactions as immutable trajectories for deterministic verification, policy checking, and visual replay. Learn the trajectory-centric architecture.

- Tags: architecture
- Published: 2026-07-30

### [Developing Agents for Specific Domains Like Healthcare or Finance: A Modular Blueprint](/bojieli/ai-agent-book/developing-agents-for-healthcare-or-finance)

Develop AI agents for healthcare or finance. Learn a modular blueprint to curate tool libraries, restrict LLM functions, and boost tool selection precision for specialized AI.

- Tags: modular-blueprint
- Published: 2026-07-30

### [Latest Advancements in AI Agent Research: From ReAct to Self-Evolving Multi-Agent Systems](/bojieli/ai-agent-book/latest-advancements-in-ai-agent-research)

Discover the latest AI agent research advancements including ReAct reasoning and self-evolving multi-agent systems. Explore 94 experiments in the bojieli/ai-agent-book repository.

- Tags: deep-dive
- Published: 2026-07-30

### [Techniques for Scaling AI Agent Systems: A Production Blueprint from bojieli/ai-agent-book](/bojieli/ai-agent-book/techniques-for-scaling-ai-agent-systems)

Discover techniques for scaling AI agent systems: leverage test-time compute scaling, distributed training, Ray async inference, and tool parallelism for robust production workloads.

- Tags: how-to-guide
- Published: 2026-07-30

### [How to Monitor AI Agent Performance Over Time: A Complete Observability Pipeline](/bojieli/ai-agent-book/how-to-monitor-ai-agent-performance-over-time)

Monitor AI agent performance over time using an observability pipeline. Capture trajectories, extract metrics, and generate version-controlled reports to track latency, throughput, and errors.

- Tags: how-to-guide
- Published: 2026-07-30

### [Ethical Implications of AI Agent Development: A Deep Dive into Responsible Architecture](/bojieli/ai-agent-book/ethical-implications-of-ai-agent-development)

Explore the ethical implications of AI agent development including sandboxed execution and bias-aware evaluation. Learn how bojieli/ai-agent-book pioneers responsible architecture for safer AI.

- Tags: deep-dive
- Published: 2026-07-30

### [Understanding Security Considerations for AI Agents: Threat Models and Defense-in-Depth Strategies](/bojieli/ai-agent-book/understanding-security-considerations-for-ai-agents)

Explore security considerations for AI agents. Learn about threat models and defense-in-depth strategies to protect your AI systems from unique vulnerabilities.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Deploy AI Agents to Production: A Complete Guide to Model Serving, MCP Tools, and Orchestration](/bojieli/ai-agent-book/how-to-deploy-ai-agents-to-production)

Learn how to deploy AI agents to production. This guide covers model serving, MCP tools, and orchestration using Docker or Kubernetes for seamless AI agent deployment.

- Tags: how-to-guide
- Published: 2026-07-30

### [Tools for Building Modular AI Agents: Inside the AI-Agent-Book Repository](/bojieli/ai-agent-book/tools-for-building-modular-ai-agents)

Discover tools for building modular AI agents in the AI-Agent-Book repository. Explore layered architecture, LLM backends, context management, and pluggable tool execution with ReAct.

- Tags: deep-dive
- Published: 2026-07-30

### [Strategies for AI Agent Learning and Adaptation: A 10-Phase Framework from the AI Agent Book](/bojieli/ai-agent-book/strategies-for-ai-agent-learning-and-adaptation)

Explore AI agent learning and adaptation with the AI Agent Book's 10-phase framework. Discover how agents evolve from LLM wrappers to self-modifying systems through context engineering and continuous evaluation.

- Tags: deep-dive
- Published: 2026-07-30

### [How to Implement Agent Reasoning and Decision-Making: A Technical Guide to the ai-agent-book Architecture](/bojieli/ai-agent-book/how-to-implement-agent-reasoning-and-decision-making)

Implement agent reasoning and decision-making with the ai-agent-book architecture. Discover how a modular three-layer system transforms LLM responses into actions via an Agent policy loop.

- Tags: how-to-guide
- Published: 2026-07-30

### [AI Agent Communication Protocols: MCP, A2A, A2UI and the Modern Agent Stack](/bojieli/ai-agent-book/examples-of-ai-agent-communication-protocols)

Explore AI agent communication protocols like MCP, A2A, and A2UI. Understand how these protocols power modern LLM systems and enable seamless agent interaction and tool integration.

- Tags: deep-dive
- Published: 2026-07-30

### [Guide to Agent Architecture Patterns in AI: 8 Modular Designs from Production Code](/bojieli/ai-agent-book/guide-to-agent-architecture-patterns-in-ai)

Explore 8 modular agent architecture patterns in AI, from ReAct loops to multi-agent orchestration. Learn how LLMs, context, and tools drive complex reasoning using production code examples.

- Tags: architecture
- Published: 2026-07-30

### [Core Principles of Building AI Agents: The Complete Architectural Blueprint](/bojieli/ai-agent-book/what-are-core-principles-building-ai-agents)

Discover the core principles of building AI agents with this architectural blueprint. Learn about LLM context tools SOLID design asynchronous architecture and safety.

- Tags: architecture
- Published: 2026-07-30

### [How to Set Up a Local AI Agent Development Environment: The Complete Guide](/bojieli/ai-agent-book/how-to-set-up-local-ai-agent-development-environment)

Set up your local AI agent development environment easily. This guide covers Python installation, API key configuration, and running quickstart scripts from the bojieli/ai-agent-book repository for AI agent experiments.

- Tags: how-to-guide
- Published: 2026-07-30

### [How to Fork and Modify the AI Agent Book for Custom Research and Teaching](/bojieli/ai-agent-book/how-to-fork-and-modify-ai-agent-book)

Learn to fork and modify the AI agent book for custom research and teaching. Clone the repository, customize agents, add chapters, and rebuild the PDF.

- Tags: how-to-guide
- Published: 2026-07-29

### [Examples of Agents Built Using This Framework: 3 Production-Ready AI Agents](/bojieli/ai-agent-book/examples-of-agents-built-using-ai-agent-book-framework)

Explore bojieli/ai-agent-book for three production-ready AI agent examples: UserMemoryAgent, MultimodalAgent, and SelfEvolvingAgent. Learn about ReAct loops, multimodal processing, and self-evolution.

- Tags: examples
- Published: 2026-07-29

### [What Is the Purpose of the Knowledge Base Article in the AI Agent Book?](/bojieli/ai-agent-book/purpose-of-knowledge-base-article-ai-agent-book)

Discover the purpose of the knowledge base article in the AI Agent Book. Learn about the bojieli/ai-agent-book repository structure, experiments, and how to leverage its deep-dive content for developers.

- Tags: article
- Published: 2026-07-29

### [How to Update Dependencies in the AI Agent Book Project: A Chapter-Based Guide](/bojieli/ai-agent-book/how-to-update-dependencies-in-ai-agent-book-project)

Learn to update dependencies in the bojieli/ai-agent-book project. Follow this chapter-based guide for easy package upgrades and reproducible environments.

- Tags: how-to-guide
- Published: 2026-07-29

### [What Are the Licensing Terms for the AI Agent Book Repository?](/bojieli/ai-agent-book/licensing-terms-for-ai-agent-book-repository)

Understand the MIT license terms for the AI agent book repository covering free use modification distribution and sublicensing. Get all the details now.

- Tags: licensing-information
- Published: 2026-07-29

### [How to Deploy the AI Agent Book Application](/bojieli/ai-agent-book/how-to-deploy-ai-agent-book-application)

Learn to deploy the AI Agent Book application on GitHub Pages. Explore automated GitHub Actions workflows and manual builds for your static site.

- Tags: how-to-guide
- Published: 2026-07-29

### [AI Agent Book Project Roadmap: Core Chapters, Multilingual Releases, and Publication Pipeline](/bojieli/ai-agent-book/roadmap-for-ai-agent-book-project)

Discover the AI agent book project roadmap: foundational chapters, multilingual releases, automated publishing, and async tooling. Learn how we're building the definitive AI agent guide.

- Tags: getting-started
- Published: 2026-07-29

### [How to Test the AI Agent Book Code: A Complete pytest Guide](/bojieli/ai-agent-book/how-to-test-ai-agent-book-code)

Learn how to test the AI agent book code. Install dependencies and run pytest from the repository root to execute the chapter test suites and ensure your AI agent functions correctly.

- Tags: how-to-guide
- Published: 2026-07-29

### [AI Concepts Demonstrated by the AI Agent Book Project: From LLM Brain to Multi-Agent Systems](/bojieli/ai-agent-book/ai-concepts-demonstrated-by-ai-agent-book-project)

Explore AI concepts like LLMs, context engineering, RAG, and multi-agent systems through the AI Agent Book project's practical autonomous agent ecosystem. Learn more today.

- Tags: deep-dive
- Published: 2026-07-29

### [How to Generate Documentation for the AI Agent Book: Complete MkDocs Build Guide](/bojieli/ai-agent-book/how-to-generate-documentation-for-ai-agent-book)

Learn to generate documentation for the AI agent book using MkDocs Material. Follow our complete guide for building a static site with preprocessing and multilingual support for easy GitHub Pages deployment.

- Tags: how-to-guide
- Published: 2026-07-29

### [What Is the Role of bojieli in the AI Agent Book Project?](/bojieli/ai-agent-book/role-of-bojieli-user-in-ai-agent-book-project)

Discover bojieli's crucial role as owner and lead maintainer of the AI Agent Book project. Learn how they manage manuscript curation, CI/CD, and experiment dependencies.

- Tags: article
- Published: 2026-07-29

### [How to Integrate Custom AI Models with the AI Agent Book: A Complete Guide](/bojieli/ai-agent-book/integrate-custom-ai-models-with-ai-agent-book)

Integrate custom AI models with the AI Agent Book easily. Learn to set environment variables, configure SDK clients, and extend mapping helpers for seamless integration. Get started now!

- Tags: how-to-guide
- Published: 2026-07-29

### [Best Practices for Developing with the AI Agent Book Codebase: A Complete Guide](/bojieli/ai-agent-book/best-practices-for-developing-with-ai-agent-book-codebase)

Master the AI Agent Book codebase with this guide. Learn modular architecture, safety-first patterns, config management, and unit testing for production-ready AI agents.

- Tags: best-practices
- Published: 2026-07-29

### [Development Goals for the AI Agent Book: From Theory to Production Engineering](/bojieli/ai-agent-book/development-goals-for-ai-agent-book)

Explore the AI Agent Book's development goals: master agent theory and build production ready systems with hands on labs and open source tools.

- Tags: getting-started
- Published: 2026-07-29

### [How to Run the AI Agent Book Examples: Complete Setup Guide](/bojieli/ai-agent-book/how-to-run-ai-agent-book-examples)

Easily run the AI agent book examples from bojieli/ai-agent-book. Follow this guide to clone the repo, install dependencies, set API keys, and run multi-agent experiments.

- Tags: how-to-guide
- Published: 2026-07-29

### [How Data Is Managed and Stored in the AI Agent Book: File-Based Persistence Architecture](/bojieli/ai-agent-book/data-management-in-ai-agent-book-project)

Discover how AI Agent Book manages data with a file-based persistence architecture. Learn about JSON file storage, atomic writes, and memory modes for robust data integrity. No external databases needed.

- Tags: architecture
- Published: 2026-07-29

### [Main Functionalities of the AI Agent Book: 10 Modular Building Blocks for LLM Agents](/bojieli/ai-agent-book/main-functionalities-of-ai-agent-book)

Explore the AI Agent Book's 10 modular functionalities, including web search, memory, code generation, and multi-agent collaboration. Learn to build powerful LLM agents with this practical guide.

- Tags: getting-started
- Published: 2026-07-29

### [Dependencies Required to Run the AI Agent Book Code: Complete Setup Guide](/bojieli/ai-agent-book/dependencies-for-ai-agent-book-code)

Discover the dependencies needed for the AI Agent Book code. This guide breaks down chapter-specific requirements.txt files and top-level setup for running the AI agent book.

- Tags: how-to-guide
- Published: 2026-07-29

### [Understanding the Architecture of the AI Agent Book: A Modular Framework for LLM Agents](/bojieli/ai-agent-book/architecture-of-ai-agent-book)

Explore the AI Agent Book's layered architecture: LLM + Context + Tools. This modular framework guides you through progressive agent capabilities from basic ReAct loops to multi-agent collaboration.

- Tags: architecture
- Published: 2026-07-29

### [How to Contribute to the AI Agent Book Project: 5 Ways to Get Involved](/bojieli/ai-agent-book/how-to-contribute-to-ai-agent-book-project)

Contribute to the AI Agent Book project! Submit pull requests for content, code, figures, or translations to help build this collaborative AI resource. Follow our GitHub workflow.

- Tags: getting-started
- Published: 2026-07-29

### [Which Programming Languages and Frameworks Are Used in the AI Agent Book Project?](/bojieli/ai-agent-book/programming-languages-and-frameworks-used-in-ai-agent-book)

Discover the programming languages and frameworks driving the AI Agent Book project. Learn about Python FastAPI PyTorch and JavaScript Nextjs React for AI development.

- Tags: getting-started
- Published: 2026-07-29

### [Core Components of the AI Agent Book Repository: A Deep Dive into bojieli/ai-agent-book](/bojieli/ai-agent-book/core-components-of-ai-agent-book-repository)

Explore the core components of the bojieli/ai-agent-book repository, from source code to documentation. Understand the AI agent learning ecosystem and how to implement it.

- Tags: deep-dive
- Published: 2026-07-29

### [How to Set Up the AI Agent Book Project Locally: Complete Installation Guide](/bojieli/ai-agent-book/how-to-set-up-ai-agent-book-locally)

Learn how to set up the AI agent book project locally. Follow our complete installation guide to clone the repository, install dependencies, configure keys, and run experiments.

- Tags: how-to-guide
- Published: 2026-07-28

### [Is the AI Agent Book Available in Other Formats? PDF, EPUB, and Build Guide](/bojieli/ai-agent-book/is-the-ai-agent-book-available-in-other-formats)

Get the AI Agent Book in PDF and EPUB formats for offline reading. Access the online HTML version and build guides in eight languages. Download your copy today.

- Tags: faq
- Published: 2026-07-27

### [Who Is the AI Agent Book Author? Exploring the bojieli/ai-agent-book Repository](/bojieli/ai-agent-book/who-is-the-author-of-the-ai-agent-book)

Discover the author behind the AI Agent book. Explore the bojieli/ai-agent-book repository on GitHub to learn more about creator Bo Ji and his contributions to AI.

- Tags: getting-started
- Published: 2026-07-27

### [Does the AI Agent Book Cover Multi-Agent Systems? A Deep Dive into Chapter 10](/bojieli/ai-agent-book/does-the-book-cover-multi-agent-systems)

Discover if the AI Agent Book covers multi-agent systems. Chapter 10 details collaboration and architecting shared and non-shared contexts.

- Tags: deep-dive
- Published: 2026-07-27

### [What AI Frameworks and Libraries Are Used in the AI Agent Book?](/bojieli/ai-agent-book/what-ai-frameworks-or-libraries-are-discussed-in-the-book)

Explore AI frameworks and libraries used in the AI Agent Book from bojieli GitHub. Learn about OpenAI API, LangChain, Azure OpenAI, Pydantic, and more for powerful AI agent development.

- Tags: deep-dive
- Published: 2026-07-27

### [AI Agent Book Structure: A Comprehensive 10-Chapter Architecture Guide](/bojieli/ai-agent-book/how-is-the-ai-agent-book-structured)

Explore the AI Agent book structure a 10 chapter guide covering Agent=LLM+Context+Tools. Learn theory to multi agent systems with runnable code. Get the architecture.

- Tags: architecture
- Published: 2026-07-27

### [What Is the License for the AI Agent Book?](/bojieli/ai-agent-book/what-is-the-license-for-the-ai-agent-book)

Understand the Apache License 2.0 for the AI Agent Book. Freely use, modify, and distribute this open-source work with clear terms.

- Tags: licensing
- Published: 2026-07-27

### [Can I Contribute to the AI Agent Book? A Complete Guide to Open Source Contributions](/bojieli/ai-agent-book/can-i-contribute-to-the-ai-agent-book)

Learn how to contribute to the AI Agent Book. Submit pull requests for content, code, translations, or build system updates to the bojieli/ai-agent-book repository.

- Tags: how-to-guide
- Published: 2026-07-27

### [Prerequisites for Understanding the AI Agent Book: A Complete Technical Guide](/bojieli/ai-agent-book/what-are-the-prerequisites-for-understanding-the-ai-agent-book)

Master the AI Agent book by bojieli. Learn essential prerequisites including Python, LLM concepts, prompt engineering, command-line use, and API keys for a complete technical guide.

- Tags: getting-started
- Published: 2026-07-27

### [Is AI Agents in Depth a Beginner's Guide to AI Agents? Complete Review](/bojieli/ai-agent-book/is-this-book-a-beginners-guide-to-ai-agents)

Explore AI Agents in Depth, a comprehensive guide for beginners and advanced engineers. Learn LLM, context, tools, reinforcement learning, and multi-agent systems.

- Tags: review
- Published: 2026-07-27

### [Where to Find the Table of Contents for the AI Agent Book](/bojieli/ai-agent-book/where-can-i-find-the-table-of-contents-for-the-ai-agent-book)

Find the AI Agent book table of contents. It's defined in the nav section of mkdocs.yml in the bojieli/ai-agent-book repository and appears as the site navigation sidebar.

- Tags: getting-started
- Published: 2026-07-27

### [What Topics Are Covered in the AI Agent Book? A Complete Chapter-by-Chapter Breakdown](/bojieli/ai-agent-book/what-topics-are-covered-in-the-ai-agent-book)

Explore the AI Agent Book's chapter breakdown. Discover foundational concepts, multimodal interaction, multi-agent collaboration, and future AI trajectories.

- Tags: getting-started
- Published: 2026-07-27

### [How to Implement Structured Knowledge Extraction from Documents: A Complete Two-Stage Pipeline](/bojieli/ai-agent-book/implement-structured-knowledge-extraction-documents)

Implement structured knowledge extraction from documents with a two-stage pipeline. Discover schemas and extract JSON fact cards using tailored LLM prompts.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Analyze and Optimize Agent API Costs: A Complete Guide to Token Tracking](/bojieli/ai-agent-book/how-to-analyze-optimize-agent-api-costs)

Analyze and optimize agent API costs effectively. Implement automatic token tracking with TokenCost to monitor LLM usage, calculate real-time expenses, and identify costly models for smarter spending.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Implement Real-Time Speech Synthesis for AI Agents: A Complete Guide](/bojieli/ai-agent-book/how-to-implement-real-time-speech-synthesis-agents)

Learn how to implement real-time speech synthesis for AI agents. Discover the cascaded pipeline for low-latency voice interaction, essential for responsive AI.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Implement Browser Automation with AI Agents: A Complete Guide to Learning and Replay](/bojieli/ai-agent-book/how-to-implement-browser-automation-ai-agents)

Implement browser automation with AI agents using a two-phase architecture. Learn tasks with LLMs and replay workflows with Playwright for 75% faster execution.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Use Knowledge Graphs for RAG (GraphRAG): A Complete Implementation Guide](/bojieli/ai-agent-book/how-to-use-knowledge-graphs-rag-graphrag)

Implement GraphRAG to boost RAG performance. Leverage knowledge graphs for multi-hop reasoning and hierarchical summarization, going beyond vector search.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Implement Log Sanitization for Privacy: A Rule-Based Approach for AI Agents](/bojieli/ai-agent-book/how-to-implement-log-sanitization-privacy)

Implement log sanitization for privacy by removing PII and secrets with a rule-based regex engine. Learn this offline, ML-free approach for AI agents.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Defend Against Prompt Injection Attacks in AI Agents: A Layered Defense Strategy](/bojieli/ai-agent-book/how-to-defend-against-prompt-injection-attacks)

Learn how to defend against prompt injection attacks with a layered defense strategy. Protect your AI agents by sanitizing inputs, isolating instructions, validating calls, and monitoring behavior.

- Tags: best-practices
- Published: 2026-07-26

### [How to Build Multi-Agent Collaboration Systems: Architecture and Implementation Guide](/bojieli/ai-agent-book/how-to-build-multi-agent-collaboration-systems)

Learn how to build multi-agent collaboration systems using a unified agent model, LLM reasoning, and coordination patterns. Explore architecture and implementation in this AI Agent Book guide.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Implement Multimodal Agents with Vision Capabilities: A Complete Guide to AI-Agent-Book](/bojieli/ai-agent-book/how-to-implement-multimodal-agents-vision-capabilities)

Implement multimodal agents with vision capabilities by setting use_vision=True in the Agent class. This guide shows how to inject screenshots for advanced AI interactions.

- Tags: how-to-guide
- Published: 2026-07-26

### [SFT vs RL for Agent Post-Training: Implementation Guide with TRL](/bojieli/ai-agent-book/how-to-implement-sft-vs-rl-agent-post-training)

Learn to implement SFT vs RL for agent post-training using the TRL library. This guide offers a clear comparison and implementation steps for optimizing your language models.

- Tags: how-to-guide
- Published: 2026-07-26

### [Best Metrics for Evaluating AI Agent Performance: A Complete Technical Guide](/bojieli/ai-agent-book/best-metrics-evaluating-ai-agent-performance)

Discover the best metrics for evaluating AI agent performance. This technical guide covers outcome, compliance, and quality scoring, referencing the bojieli/ai-agent-book repository for practical implementation.

- Tags: best-practices
- Published: 2026-07-26

### [How to Use Code Execution for Mathematical Reasoning: A Sandbox Approach](/bojieli/ai-agent-book/how-to-use-code-execution-mathematical-reasoning)

Unlock powerful mathematical reasoning with a sandboxed Python interpreter. Learn the think-code-check loop for accurate calculations and enhanced AI problem solving.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Build a Production-Ready Coding Agent: Architecture Patterns from the AI Agent Book](/bojieli/ai-agent-book/how-to-build-production-ready-coding-agent)

Build a production-ready coding agent with modular architecture and LLM clients. Learn patterns for safety, streaming, and tool integration from the AI Agent Book.

- Tags: architecture
- Published: 2026-07-26

### [How to Implement Active Tool Discovery and Selection in Self-Evolving AI Agents](/bojieli/ai-agent-book/how-to-implement-active-tool-discovery-selection)

Learn to implement active tool discovery and selection for AI agents. Automatically search, reuse, and create tools for self-evolving capabilities and eliminate redundant computation.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Build an Event-Driven Asynchronous AI Agent](/bojieli/ai-agent-book/build-event-driven-asynchronous-ai-agent)

Learn to build an event-driven asynchronous AI agent using asyncio coroutines and unified Message objects. Create responsive, non-blocking AI architectures with elegant event subscription.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Implement the MCP Protocol for Tool Integration](/bojieli/ai-agent-book/how-to-implement-mcp-protocol-tool-integration)

Learn how to implement the MCP protocol for seamless tool integration with LLM agents. Discover, invoke, and manage tools using a standardized JSON schema and HTTP API.

- Tags: how-to-guide
- Published: 2026-07-26

### [Agentic RAG vs Traditional RAG: Core Architectural Differences Explained](/bojieli/ai-agent-book/agentic-rag-vs-traditional-rag)

Discover the core architectural differences between Agentic RAG and traditional RAG. Understand how Agentic RAG's iterative ReAct loop revolutionizes retrieval compared to static pipelines.

- Tags: architecture
- Published: 2026-07-26

### [How to Implement RAG with Dense and Sparse Embeddings: A Complete Guide](/bojieli/ai-agent-book/how-to-implement-rag-dense-sparse-embeddings)

Implement RAG with dense and sparse embeddings. Combine semantic search and BM25, fuse results with RRF, and rerank with cross-encoders for enhanced AI generation.

- Tags: how-to-guide
- Published: 2026-07-26

### [How to Build a User Memory System That Persists Across Sessions: A Modular Guide](/bojieli/ai-agent-book/build-user-memory-system-persists-sessions)

Build a user memory system that persists across sessions. Learn how this modular guide stores facts as JSON for automatic loading and durability with abstract managers.

- Tags: how-to-guide
- Published: 2026-07-26

### [Context Compression Strategies for Long Conversations: A Deep Dive into the AI-Agent-Book Implementation](/bojieli/ai-agent-book/context-compression-strategies-long-conversations)

Explore effective context compression strategies for long AI conversations. Learn how the AI-Agent-Book uses semantic compression, LLMLingua, and truncation to maintain fidelity within token limits.

- Tags: deep-dive
- Published: 2026-07-26

### [How to Implement Agent Skills with the Progressive Disclosure Pattern](/bojieli/ai-agent-book/implement-agent-skills-progressive-disclosure-pattern)

Learn to implement Agent Skills using progressive disclosure. This pattern efficiently loads skills in layers, keeping prompts compact for complex, multi-step AI workflows.

- Tags: how-to-guide
- Published: 2026-07-26

### [Best Prompt Engineering Techniques for AI Agents: From System Prompts to Automated Optimization](/bojieli/ai-agent-book/best-prompt-engineering-techniques-ai-agents)

Discover the best prompt engineering techniques for AI agents. Master system prompts, structured instructions, tool docs, and automated optimization for superior AI performance.

- Tags: best-practices
- Published: 2026-07-26

### [How to Implement KV Cache Optimization for LLM Context Management](/bojieli/ai-agent-book/how-to-implement-kv-cache-optimization-llm-context-management)

Boost LLM performance with KV cache optimization. Reduce latency and costs by reusing key-value pairs for context management. Learn how to implement this essential technique for faster AI responses.

- Tags: tutorial
- Published: 2026-07-26

### [Evaluation Benchmarks for Coding Agents: From SWE-bench to Terminal-Bench](/bojieli/ai-agent-book/evaluation-benchmarks-coding-agents-swe-bench)

Explore evaluation benchmarks for coding agents like SWE-bench. Discover objective frameworks for automated code generation, editing, and execution testing LLM systems.

- Tags: deep-dive
- Published: 2026-07-25

### [How Prompt Distillation Enables AI Agent Skill Transfer](/bojieli/ai-agent-book/prompt-distillation-agent-skill-transfer)

Discover how prompt distillation transfers AI agent skills to lighter models. Learn to train student models with label-only outputs for efficient inference without complex prompts.

- Tags: deep-dive
- Published: 2026-07-25

### [Key Security Considerations for AI Agent Tool Systems: 9 Critical Architectural Pillars](/bojieli/ai-agent-book/security-considerations-ai-agent-tool-systems)

Discover key security considerations for AI agent tool systems. Learn about 9 critical architectural pillars including sandboxes, access controls, and secret management to protect against threats.

- Tags: architecture
- Published: 2026-07-25

### [How to Optimize KV Cache for Efficient Context Window Utilization in LLMs](/bojieli/ai-agent-book/optimize-kv-cache-context-window-efficiency)

Optimize KV Cache for efficient context window utilization by keeping prompts static and reusing cached attention keys and values. Avoid recomputation and enhance LLM performance.

- Tags: deep-dive
- Published: 2026-07-25

### [What Is the ReAct Pattern? A Deep Dive into Agent Reasoning and Action](/bojieli/ai-agent-book/react-pattern-agent-reasoning-action)

Explore the ReAct pattern, an iterative Reason → Act → Observe loop that empowers LLMs to tackle complex tasks. Learn how it combines reasoning and tool calls, as seen in bojieli/ai-agent-book.

- Tags: deep-dive
- Published: 2026-07-25

### [Context Sharing and Isolation in Multi-Agent Systems: Architecture Patterns from ai-agent-book](/bojieli/ai-agent-book/context-sharing-isolation-multi-agent-systems)

Discover context sharing and isolation techniques in multi-agent systems from ai-agent-book. Learn how conversation history is sandboxed by default and shared deliberately.

- Tags: architecture
- Published: 2026-07-25

### [Multi-Agent Collaboration Frameworks for Emergent Agent Societies: A Deep Dive into AWorld](/bojieli/ai-agent-book/multi-agent-collaboration-frameworks-emergent-societies)

Explore multi-agent collaboration frameworks like AWorld which support emergent agent societies. Discover unified interfaces, trajectory recording, and decentralized coordination.

- Tags: deep-dive
- Published: 2026-07-25

### [How Computer Use Enables Browser Automation for AI Agents](/bojieli/ai-agent-book/computer-use-feature-browser-automation-agents)

Discover how Computer Use enables AI agents to automate browsers. Learn about GUI automation, web interface perception, and precise browser actions with the Browser-Use framework.

- Tags: deep-dive
- Published: 2026-07-25

### [Three Paradigms for Voice Interaction in Multimodal AI Agents: Cascaded, End-to-End, and Full-Duplex Explained](/bojieli/ai-agent-book/three-paradigms-voice-interaction-multimodal-agents)

Explore three voice interaction paradigms for AI agents: Cascaded, End-to-End, and Full-Duplex. Understand their trade-offs in latency, modularity, and paralinguistic cue preservation.

- Tags: deep-dive
- Published: 2026-07-25

### [How to Implement Continuous Evolution for AI Agents from Runtime Data](/bojieli/ai-agent-book/implement-continuous-evolution-agents-runtime-data)

Discover how to implement continuous evolution for AI agents using runtime data. Close the feedback loop to automatically update agent knowledge, prompts, and tools for ongoing improvement.

- Tags: how-to-guide
- Published: 2026-07-25

### [SFT vs RL for Training AI Agents: Key Differences Explained](/bojieli/ai-agent-book/difference-sft-rl-training-ai-agents)

Discover the key differences between SFT and RL for training AI agents. Understand how SFT uses labeled data while RL optimizes for reward, enabling broader strategy generalization.

- Tags: deep-dive
- Published: 2026-07-25

### [How to Evaluate AI Agent Performance Using Benchmarks and Metrics: A Complete Guide](/bojieli/ai-agent-book/evaluate-agent-performance-benchmarks-metrics)

Learn how to evaluate AI agent performance with benchmarks and metrics. Master controlled environments, datasets, and quantitative measures like Pass@k for capability and reliability.

- Tags: how-to-guide
- Published: 2026-07-25

### [Best Practices for Developing Production-Ready Coding Agents: A Complete Guide](/bojieli/ai-agent-book/best-practices-developing-production-coding-agents)

Discover best practices for production-ready coding agents. Learn about modular architecture, streaming LLM APIs, state tracking, and safety guards for reliable AI development.

- Tags: best-practices
- Published: 2026-07-25

### [How Knowledge Graphs Enhance AI Agent Knowledge Management: A GraphRAG Deep Dive](/bojieli/ai-agent-book/knowledge-graphs-enhance-agent-knowledge-management)

Discover how knowledge graphs elevate AI agent knowledge management. Learn about GraphRAG and its advanced capabilities for structured data, multi-hop reasoning, and semantic retrieval beyond vector search.

- Tags: deep-dive
- Published: 2026-07-25

### [How Retrieval Augmented Generation (RAG) Powers AI Agent Systems: A Deep Dive into AI-Agent-Book](/bojieli/ai-agent-book/retrieval-augmented-generation-rag-applied-agent-systems)

Learn how Retrieval Augmented Generation RAG enhances AI agent systems by combining LLM reasoning with external knowledge. Explore the ReAct architecture and various backends.

- Tags: deep-dive
- Published: 2026-07-25

### [How to Implement User Memory and Knowledge Bases for Persistent Agent Context](/bojieli/ai-agent-book/implement-user-memory-knowledge-bases-persistent-agent-context)

Implement user memory and knowledge bases for persistent agent context. Store interaction histories and external documents in indexes for seamless retrieval. Learn how to bridge information with a contextual pipeline.

- Tags: how-to-guide
- Published: 2026-07-25

### [Active Tool Discovery in Large-Scale LLM Agent Systems: 3 Strategies Explained](/bojieli/ai-agent-book/strategies-active-tool-discovery-large-agent-systems)

Discover 3 effective strategies for active tool discovery in large-scale LLM agent systems. Reduce token usage and maintain 100% recall with dynamic tool requests.

- Tags: deep-dive
- Published: 2026-07-25

### [How Tool Granularity Affects AI Agent Performance and Scalability](/bojieli/ai-agent-book/tool-granularity-effect-agent-performance-scalability)

Discover how tool granularity impacts AI agent latency, token efficiency, and scalability. Learn how fine-grained tools boost linear growth and overcome coarse-grained limitations.

- Tags: performance
- Published: 2026-07-25

### [How to Implement an Event-Driven Asynchronous Architecture for AI Agents](/bojieli/ai-agent-book/implementing-event-driven-async-agent-architecture)

Learn to build scalable, non-blocking AI systems by wrapping agent interactions in asynchronous event objects and orchestrating agents with event buses and callbacks.

- Tags: how-to-guide
- Published: 2026-07-25

### [What is the Model Context Protocol (MCP) and Its Role in AI Tool Ecosystems?](/bojieli/ai-agent-book/model-context-protocol-mcp-tool-ecosystems)

Discover the Model Context Protocol (MCP), an open standard enabling AI agents to seamlessly discover and use external tools. Achieve 'develop once, use everywhere' interoperability across AI frameworks and agents.

- Tags: deep-dive
- Published: 2026-07-25

### [How Tool Descriptions Are Designed for Optimal LLM Agent Performance](/bojieli/ai-agent-book/designing-tool-descriptions-llm-agents)

Learn how to design effective tool descriptions for LLM agents. Use concise phrasing, keywords, and JSON-Schema for optimal accuracy and performance.

- Tags: best-practices
- Published: 2026-07-25

### [What Is Context Engineering and How It Impacts AI Agent Capabilities](/bojieli/ai-agent-book/context-engineering-impact-agent-capabilities)

Discover context engineering and how it enhances AI agent capabilities. Learn to structure prompts for accurate reasoning, less token use, and better memory with this essential technique.

- Tags: deep-dive
- Published: 2026-07-25

### [How the Agent = LLM + Context + Tools Formula Guides AI Agent Development](/bojieli/ai-agent-book/agent-formula-llm-context-tools-guide)

Master AI agent development with the Agent = LLM + Context + Tools formula. Understand how this framework builds modular, traceable, and extensible AI systems for better performance and control.

- Tags: tutorial
- Published: 2026-07-25

### [How to Implement Error Handling and Recovery in AI Agent Tool Execution](/bojieli/ai-agent-book/error-handling-recovery-agent-tool-execution)

Learn to implement error handling and recovery in AI Agent tool execution. Validate code, sandbox execution, detect errors, and enable retry logic or human intervention for robust performance.

- Tags: how-to-guide
- Published: 2026-07-22

### [How to Optimize AI Agent Inference Latency for Real-Time Interaction](/bojieli/ai-agent-book/optimize-agent-inference-latency-real-time-interaction)

Cut AI agent inference latency to sub-second with fast model selection, native optimizations, half-precision, KV-caching, streaming I/O, and local metadata caching. Achieve real-time interaction.

- Tags: performance
- Published: 2026-07-22

### [Security Considerations for AI Agent Tools with Elevated Permissions: A Deep Dive into bojieli/ai-agent-book](/bojieli/ai-agent-book/security-considerations-agent-tools-elevated-permissions)

Explore security considerations for AI agent tools with elevated permissions. Learn about permission models, input validation, and operation separation to protect your system.

- Tags: deep-dive
- Published: 2026-07-22

### [How to Implement AI Agent Self-Evolution and Experience Learning: A Complete Guide](/bojieli/ai-agent-book/implement-agent-self-evolution-experience-learning)

Implement AI agent self evolution and experience learning with a closed-loop architecture for continuous autonomous improvement through persistent experience storage dynamic tool synthesis and meta learning

- Tags: how-to-guide
- Published: 2026-07-22

### [How to Design Effective AI Agent Evaluation Rubrics: A Step-by-Step Guide](/bojieli/ai-agent-book/design-effective-agent-evaluation-rubrics)

Design effective AI agent evaluation rubrics with our step-by-step guide. Learn to create objective metrics and prevent reward hacking using weighted dimensions and veto mechanisms.

- Tags: how-to-guide
- Published: 2026-07-22

### [How to Evaluate AI Agent Performance Using Metrics and Statistical Significance](/bojieli/ai-agent-book/evaluate-agent-performance-metrics-statistical-significance)

Master your AI agent's performance with our guide on metrics and statistical significance. Learn to measure correctness, tool discovery, and reuse for impactful results.

- Tags: best-practices
- Published: 2026-07-22

### [Best Practices for Building Production-Ready AI Coding Agents: A Complete Guide](/bojieli/ai-agent-book/best-practices-production-coding-agents)

Master production-ready AI coding agents. Learn modular architecture, streaming responses, safe tool execution, and dynamic context injection for peak reliability.

- Tags: best-practices
- Published: 2026-07-22

### [How to Design Effective Tool Descriptions for LLM Tool Calling in AI Agents](/bojieli/ai-agent-book/design-tool-descriptions-llm-tool-calling-agents)

Design effective tool descriptions for LLM tool calling in AI agents. Learn to use purpose-first phrasing, JSON-Schema, and negative examples for reliable, secure, and efficient tool invocation.

- Tags: tutorial
- Published: 2026-07-22

### [How MCP (Model Context Protocol) Standardizes AI Agent Tool Integration](/bojieli/ai-agent-book/mcp-standardize-agent-tool-integration)

Discover how MCP standardizes AI agent tool integration through a unified JSON-schema contract simplifying remote calls into native Python methods.

- Tags: deep-dive
- Published: 2026-07-22

### [6 Types of AI Agent Tools and When to Use Them: A Complete Guide to the ai-agent-book Framework](/bojieli/ai-agent-book/ai-agent-tool-types-and-usage)

Explore 6 types of AI agent tools, from coding assistants to RPA, in the ai-agent-book framework. Learn when to use each for optimal results.

- Tags: guide
- Published: 2026-07-22

### [How to Implement Context Engineering for Better AI Agent Performance](/bojieli/ai-agent-book/implement-context-engineering-better-agent-performance)

Learn how to implement context engineering to significantly boost AI agent performance. Discover techniques for managing token budgets and optimizing information context for better results.

- Tags: how-to-guide
- Published: 2026-07-22

### [Harness Engineering for AI Agents: The Four-Layer Evaluation Framework](/bojieli/ai-agent-book/what-is-harness-engineering-and-why-important-ai-agents)

Discover harness engineering a four-layer AI agent evaluation framework for task correctness, tool discovery, quality, and reuse. Ensure thorough testing for autonomous systems.

- Tags: deep-dive
- Published: 2026-07-22

### [Efficient RL Frameworks for LLM Training: PPO, GRPO, and DAPO Implementation Guide](/bojieli/ai-agent-book/efficient-rl-frameworks-llm-training)

Master efficient RL frameworks like PPO, GRPO, and DAPO for LLM training. Explore modular implementations and tool-aware rewards for autonomous agent development.

- Tags: how-to-guide
- Published: 2026-07-21

### [Evaluation Benchmarks for AI Agents: A Complete Guide to SWE-bench, GAIA, and OSWorld](/bojieli/ai-agent-book/evaluation-benchmarks-ai-agents-swe-bench-gaia-osworld)

Master AI agent evaluation with SWE-bench, GAIA, and OSWorld benchmarks. This guide covers real-world code repair, multimodal reasoning, and OS control. Explore production-ready tools and wrappers to effectively assess AI agent...

- Tags: tutorial
- Published: 2026-07-21

### [KV Cache Management for AI Agents: Performance Optimization Strategies](/bojieli/ai-agent-book/kv-cache-management-ai-agent-performance)

Optimize KV cache management for AI agents to halve inference latency slash token costs by 70% and execute more reasoning steps. Discover performance strategies for your AI agent book.

- Tags: performance
- Published: 2026-07-21

### [Cross-Session User Memory Retrieval and Personalization Strategies in AI Agents](/bojieli/ai-agent-book/strategies-cross-session-user-memory-retrieval-personalization)

Discover effective strategies for cross-session user memory retrieval and AI agent personalization. Learn how to maintain context and enhance user experience across conversations.

- Tags: deep-dive
- Published: 2026-07-20

### [How to Build a Production-Grade Coding Agent with Tool Calling Capabilities](/bojieli/ai-agent-book/build-production-grade-coding-agent-tool-calling)

Build a production-grade coding agent using LLMs, state management, a tool registry, and ReAct loop for Python function execution. Master structured tool calls.

- Tags: how-to-guide
- Published: 2026-07-20

### [How to Implement Prompt Injection Attacks and Defense Mechanisms in LLM Agents](/bojieli/ai-agent-book/implement-prompt-injection-attacks-defense-mechanisms-llm-agents)

Learn to implement prompt injection attacks and defenses in LLM agents. Discover deterministic scenarios, layered mitigations like prompt hardening, and reproducible experimental benchmarking.

- Tags: how-to-guide
- Published: 2026-07-20