Engineering
189 posts in engineering
Part 45 — FDE 面試指南 Part 45：Agent 工具鏈的間接提示詞注入防禦設計
深度解析間接提示詞注入（Indirect Prompt Injection）在 Agent 工具鏈的防禦架構，涵蓋雙模型特權分離、Cloud Run VPC 沙盒隔離、Pydantic Schema 強型別校驗，適合 Staff FDE 面試備考。
Part 46 — FDE 面試指南 Part 46：高規格金融業的數據無痕化與自主密鑰管理（BYOK / CMEK in GenAI）
深度剖析金融業在 Vertex AI 場景下導入 BYOK/CMEK 的完整架構：Cloud KMS + Cloud EKM 信封加密、DEK/KEK 職責分離、Dedicated Interconnect 專線優化、HSM 合規到 Memory Enclave 記憶體保護，兼顧主權資安與 <50ms 極限性能。
Part 47 — FDE 面試準備指南（四十七）：RKK 實戰——大模型與地端微型模型的智慧混合路由與冷啟動優化
深度拆解 Edge/On-Premise 小模型與雲端大模型的雙軌路由架構：基於 Token 概率熵值的早停路由（Early-Exit Confidence Routing）、vLLM logprobs API 整合、PII 強制本地路由、冷啟動優化策略，以及三個演進階段的完整系統設計
Part 48 — FDE 面試指南 Part 48：高可靠性 Agent Graph 的多重工具 Fallback 與自我修復機制
深入解析如何在 LangGraph 中設計 Compiler-Validator Pattern，透過 Pydantic 強型別校驗、Critic Agent 反思重寫、Circuit Breaker 與 Human-in-the-loop，打造能自我修復的高可靠性供應鏈 Agent 架構。
Part 49 — FDE Interview Guide Part 49：百萬級 RAG 系統的即時資料漂移與向量索引自動更新管線
深度解析企業 RAG 系統中的向量資料漂移問題：Lambda Vector Architecture、HNSW Graph Drift 監控、Blue-Green Index Deployment，以及如何在零停機的前提下維持百萬級知識庫的索引精準度。
Part 50 — FDE 面試指南 Part 50：生產環境 GenAI 自動化評估管線與 LLM-as-a-Judge 漂移監控
深度解析如何在生產環境中建立多階抽樣的 LLM 自動化評估管線，涵蓋分層抽樣、RAG 三元組評估、位置偏見消除、Drift Alert 設計，以及 95% 成本控制策略。Staff FDE 級別實戰解答。
Part 51 — FDE 面試指南 Part 51：百萬級多輪對話的 KV Cache 驅逐機制與記憶體架構優化
深度解析 B2B 長對話 SaaS 系統中 KV Cache 驅逐策略設計，涵蓋 L1 Redis、L2 Vertex AI Context Caching、L3 Firestore Snapshot 三層架構，以及 LRU 結合語義重要性評分的快取壓縮閘道，節省 80% 顯存開銷、帳單砍半的 Staff FDE 級解法。
Part 52 — FDE 面試指南 Part 52：百萬級 Agent Tool-Calling 的全域非同步並行優化與扇出控制
深度剖析 LangGraph Agent 在高並發場景下的 Tool Fan-Out 架構設計：Speculative Execution、Circuit Breaker、Graceful Degradation 與 Partial Rendering 的工程實踐，含三個演進階段與完整 Staff 級解答。
SpotifyMCP2: Control Spotify with Claude via the Model Context Protocol
A deep dive into SpotifyMCP2, an open-source Model Context Protocol server that integrates Claude with the Spotify Web API. Learn how it works, how to set it up, and how to extend it. Covers MCP architecture, OAuth2 flow, TypeScript design, and all 8 exposed tools.
finance_data: A Python Toolkit for Downloading SEC Financial Filings from EDGAR
A complete guide to the finance_data open-source project: a Python-based toolkit for downloading SEC EDGAR financial reports including 10-K annual reports, 10-Q quarterly filings, and 13-F institutional holdings. Covers setup, usage examples, and the underlying architecture.
InvestSkill: Professional Investment Analysis Plugin for Claude Code
Complete guide to InvestSkill, a Claude Code plugin that provides six powerful analytical tools for stock evaluation, fundamental analysis, technical analysis, economics research, portfolio review, and sector analysis. Learn how to integrate AI-powered financial analysis into your development environment.
Everything Claude Code: The Ultimate Production-Ready Plugin Collection Guide
Deep dive into the everything-claude-code repository by an Anthropic hackathon winner. Discover how to set up, customize, and leverage production-ready agents, skills, hooks, commands, and MCP configurations for maximum productivity with Claude Code.
Building a Sentiment-Driven US Stock Trading System with X.com Real-Time Analysis
Learn how to architect a production-ready sentiment-driven stock trading platform that streams X.com posts in real-time, analyzes market sentiment using AWS Bedrock and HuggingFace, and automatically executes trades on US stocks based on social media signals.
Building an Intelligent Bitcoin Trading System with AWS CDK and ML Models
Learn how to architect and deploy an intelligent cryptocurrency trading system on AWS using CDK, with historical price analysis, ML-powered predictions from AWS Bedrock and HuggingFace, and event-driven trade execution.
Building Centralized Grafana + Prometheus Monitoring with AWS CDK: Multi-Service Observability Platform
Comprehensive guide to architecting a production-ready centralized Prometheus + Grafana monitoring platform using AWS CDK that aggregates metrics from multiple services, clusters, and infrastructure components with federation, remote storage, and advanced alerting.
Building AI Music Generation Platform: AWS CDK Architecture with SageMaker and Bedrock Comparison
Complete guide to architecting a production-ready AI music generation platform on AWS using CDK, comparing SageMaker and Bedrock approaches with detailed pros, cons, and implementation strategies for generating music from text prompts.
Deploying Apache Superset at Scale: Production-Ready BI Platform with AWS CDK and ECS Fargate
Comprehensive guide to architecting a highly available, production-grade Apache Superset deployment using ECS Fargate, RDS PostgreSQL, and AWS CDK for enterprise business intelligence at scale.
Building a Centralized Monitoring System with AWS CloudWatch and Grafana using CDK
Design and implement a production-ready centralized monitoring and observability platform using AWS CloudWatch, Grafana, and CDK (TypeScript). Learn cross-service log aggregation, metric collection, IAM permissions, dashboard creation, and alerting strategies for monitoring distributed systems.
Building a Centralized User Access Control System with AWS Cognito and CDK
Design and implement a production-ready centralized authentication and authorization system using AWS Cognito and CDK (TypeScript). Learn multi-tenant strategies, user pool management, RBAC/ABAC patterns, and how to integrate with multiple services and applications.
Deploying Hugging Face Models to AWS: A Complete Guide with CDK, SageMaker, and Lambda
Learn how to deploy production-ready Hugging Face AI models to AWS using CDK (TypeScript), SageMaker, and Lambda. Comprehensive guide covering system design, infrastructure setup, model deployment, API creation, and best practices for scalable ML applications.
Express.js Best Practices: Building Production-Ready Node.js Backend Applications
Master Express.js development with comprehensive best practices covering configuration, middleware, routing, security, error handling, and performance optimization. Learn to build scalable, maintainable, and secure Node.js backend applications.
TypeScript Best Practices: A Comprehensive Guide to Type-Safe Development
Master TypeScript development with comprehensive best practices covering configuration, type system, design patterns, code style, and advanced techniques. Learn to write type-safe, maintainable, and scalable TypeScript applications.
Docker Mount Complete Guide: Volumes, Bind Mounts, and tmpfs Comparison
Comprehensive guide to Docker mount types including volumes, bind mounts, and tmpfs. Learn the differences, use cases, pros/cons, and best practices for persisting data in Docker containers with practical examples.
AWS Load Balancers: Complete Guide - Application, Network, Gateway, and Classic Load Balancers Comparison with Implementation
Master AWS Load Balancers with comprehensive comparisons of ALB, NLB, GWLB, and CLB. Learn when to use each type, advanced features, health checks, auto-scaling integration, and production-ready configurations with real-world examples.
AWS API Gateway: Complete Guide with Load Balancer Comparison, Microservices Architecture, and Java Implementation
Master AWS API Gateway with comprehensive comparisons to load balancers, microservices integration patterns, and production-ready Java implementations. Learn when to use API Gateway vs Load Balancer, security best practices, and scaling strategies.