DavidChan's Blog
I hear and I forget.
I see and I remember.
I write and I understand.
×
Home
Archive
Guestbook
Agentic Engineering in Practice (1): Building a Reusable Pipeline from Requirements to Release
Agentic Engineering in Practice (2): Evals, Regression, and Release Gates
Agentic Engineering in Practice (3): Observability, Rollbacks, and Team Postmortems
AI Gateway: Building a Governed Gateway Layer for LLM Calls (Auth, Rate Limits, Caching, Audit)
RAG 2.0: From Vectors to Structured Knowledge, Graphs, and Permission-Aware Retrieval
Agent Observability (AgentOps) Part 1/3: Turn Prompts, Tools, and Memory into Traces
MCP: Connecting Agents to Tools and Data—Safely
Bootstrapping Indie Products with GPT Agents
Optimizing LLM Inference Microservices for Performance and Cost
Performance Budgets and Adaptive Optimization in the Age of AI
Hardening a Hexo Blog: SEO, Performance, and AdSense Tune-Up
Choosing Your Vibe Coding Agent: Google Jules vs OpenAI Codex vs Claude Code
Composable Architectures for Serverless and Edge Deployments
