AI with Alex's Blog

• Introduction
• Environment Setup
  • Installing Miniconda and Creating the Environment
  • Installing Dependencies and Configuring API Keys
  • Verification and Checklist
• What Is LangGraph
  • LangChain vs. LangGraph
• Core Concepts: The Three Elements and the Runtime Model
  • State, Node, Edge
  • The Superstep Execution Model
  • The Checkpoint Snapshot Sequence
• Graph API vs Functional API
• Your First Graph: Define, Compile, Invoke
  • Building a State Graph in Three Steps
  • Graph Visualization
• State Management
  • Three Ways to Define a Schema
  • Validation Behavior Compared
  • State Reducers: How Updates Are Merged
  • Default Overwrite Behavior and the Overwrite Wrapper
  • Multi Schema: Input, Output, and Private State
  • Predefined States: MessagesState and AgentState
• Control Flow
  • Sequential Structure
  • Branching
    • Parallel Nodes
    • Conditional Branching: add_conditional_edges
    • Deferred Nodes: defer
    • Dynamic Fan-out: Send
    • Dynamic Jumping: Command(goto)
  • Fan-in: Merging Multiple Branches
    • Static Fan-in: AND Trigger vs. OR Trigger
    • Dynamic Fan-in: The MapReduce Pattern
  • Loops: The ReAct Pattern
    • Static vs. Dynamic Implementation
    • Recursion Limits and Graceful Exit
• Edges: A Systematic Summary
• Node Execution and Fault Tolerance
  • Retries: RetryPolicy
  • Default Retry Rules: default_retry_on
  • Timeouts and Error Handling
  • Node Caching: CachePolicy
• Best Practices
• FAQ
• Summary

• Introduction
• What Is a Skill
• Why Skills Matter
• Anatomy of a Skill
  • The SKILL.md File
  • The Supporting Cast
• Build Your Own: From Simple to Complete
  • Git Commit Messages: Just SKILL.md
  • API Endpoint Generator: Add a Config
  • React Component Generator: Scripts and Templates
  • Security Audit: Reference Documents
  • Which Structure Do You Need?
• Find Ready-Made Skills
  • Official Libraries
  • The Skills CLI
  • Community Libraries
  • Safety Before You Install
• Integrating Skills Into Your Workflow
• Iterating and Versioning
• Best Practices
• FAQ
• Summary

• Introduction
• The Big Picture: Seven Layers of Extension
• Choosing the Right Model
  • Model Comparison
  • Four Ways to Switch Models
  • Settings File Hierarchy
• Core Configuration
  • settings.json: Permissions and Defaults
  • CLAUDE.md: The Project Handbook
  • Three Layers of Memory
  • .claudeignore
• Daily Commands and Interactions
  • Slash Command Cheat Sheet
  • The Four Commands You Must Master
  • Keyboard Shortcuts
  • Power Interactions: !, @, and Images
• The Right Workflow: Explore, Plan, Implement, Commit
  • Plan Mode and the Three Operating Modes
  • When to Plan and When to Just Do It
  • Walkthrough: Building a Hello API with Express
• Best Practices
  • Prompt Writing Principles
  • Context Management
  • Git Is Your Save Point
  • Controlling Costs
  • Working in Large Codebases
  • Three Overlooked Advanced Tips
• Starter Kit for New Projects
• FAQ
• Summary

Anthropic released a blog sharing six money-saving tips for Claude Code: clear the conversation with /clear after completing a task; lock the model and reasoning intensity at the start to avoid invalidating the prompt cache by switching; use @ to reference files instead of typing paths manually; add silent parameters to commands that generate a lot of output; run /compact before taking a break; assign large output tasks to sub-agents.

• Introduction
  • The Capability Paradox
  • Three Acts of This Article
• Post-Training: Baking Capability Into Parameters
  • The Three-Stage Pipeline
  • SFT Memorizes, RL Generalizes
  • When to Choose SFT vs RL
  • Reward Design: From Scalar to Generative
  • RLVP: Reward the Outcome, Penalize the Path
  • Data and Environment Matter More Than Algorithms
  • The Practical Takeaway
• Self-Evolving Agents: Learning From Experience
  • Preserving Experience Is Not Learning
  • Three-Layer Verification
  • Four Update Carriers
  • Dual-Loop Architecture
  • When Done Does Not Mean Progress
  • Safety Boundaries for Continual Evolution
• Real-Time Perception and Multimodal Interaction
  • Why Real-Time Changes Everything
  • Voice: Cascaded to End-to-End to Full-Duplex
  • Computer Use: The Perceive-Think-Act Loop
  • Robotics: VLA, Action Chunking, and Sim2Real
  • The Unifying Theme: Fast-Slow Architecture
• Putting It Together: The Full Stack of a Modern Agent
• Best Practices
• FAQ
• Summary

• Introduction
• What: The Three-Layer Model of Agent Intelligence
• Tools: The Agent’s Hands, Feet, and Senses
  • Tool Classification: Five Categories
  • Universal Principles of Tool Design
  • The MCP Ecosystem and the Challenge of Tool Selection
  • Execution Security: Proposer-Reviewer and Sidecar
  • Event-Driven Asynchronous Agents
  • Proactive Tool Discovery and Skills
• Coding Agent: Code as the Meta-Capability
  • The Seven Core Tools and the File System Hub
  • Security: The Lethal Triad and Trust Boundaries
  • Harness Engineering for Coding Agents
  • Failure and Error Recovery
  • Six Directions of Code as Meta-Capability
• Evaluation: Knowing Whether It Actually Works
  • A Concrete Example
  • Automated Evaluation Environments
  • Designing Evaluation Datasets
  • The Metrics System: Pass@k vs Pass^k
  • LLM-as-a-Judge and Rubrics
  • Pairwise Comparison and Model Ranking
  • Statistical Significance
  • From Benchmark to System Improvement
• Example: An End-to-End Mini-Case
• Best Practices
• FAQ
• Summary
• Appendix