Articles
In-depth articles on AI, web development, cloud native, and indie hacking.
Model Context Protocol (MCP) is Anthropic's "USB-C interface for AI applications." This article explains the host/client/server model, resources/tools/prompts, and JSON-RPC, then builds a TypeScript MCP Server for Claude Code from scratch.
"Agent ≠ multi-turn dialogue." Breaks down the four components of an AI Agent—planning, memory, tools, execution—and explains ReAct vs. Plan-Execute, short/long-term memory design, function calling engineering points, and pushing an Agent from demo to production via loop control, error recovery, and observability.
Putting documents in a vector database and using top-k retrieval is only RAG's "hello world." This article covers four levers for improving RAG quality: chunking, hybrid retrieval, reranking, and query rewriting, plus a reproducible evaluation method that takes RAG from "barely usable" to genuinely accurate.
After a user confirms a high-risk action once, repeated clicks, queue re-sends, and parameter substitution can all reuse the approval. This article closes those windows with a canonical action digest, one-time consumption, state versions, and idempotent execution.
Vibe Coding is not "letting AI write whatever it wants"; it is a new paradigm for driving engineering through natural language. Learn the mental-model shift, Claude Code's spec → plan → iterate workflow, context management, and which tasks suit vibe coding or require human oversight, turning AI coding from a "toy" into real productivity.
Server-side tests passing does not mean consumers still work. This article combines specification diffs, consumer contracts, cross-version replay, and migration windows into compatibility gates to constrain Agent modifications to REST, events, and message structures.
AI apps must call LLMs securely, stream tokens to the frontend in real time, and manage session state. This guide uses Next.js 16 App Router, Server Actions, and AI SDK to implement a clean, streamable AI chat page ready for production.
The most common problem in multi-agent systems isn't model capability, but incomplete inputs, unclear responsibility, and unverifiable results after task delegation. This article covers delegation contracts, result schemas, budget propagation, and recovery mechanisms.
The hardest part of indie development is not coding, but validating an idea at the lowest possible cost. AI has driven that cost to an unprecedented low. This article presents a closed-loop workflow from a one-sentence idea to the first real user feedback, showing what AI can handle at every step.
Letting agents freely fetch URLs turns the model into an intranet request proxy. This article covers URL normalization, full-address validation, connection IP pinning, per-hop redirect inspection, egress proxies, and an attack regression suite.
The previous article covered the MCP protocol; this one is hands-on. Build a production-ready MCP Server from scratch: pick a scenario, use the official SDK to implement resources and tools, deploy locally via stdio or remotely via HTTP, debug with MCP Inspector, then wire it into Claude Code and Cursor.
An agent's evaluation set determines what the team will optimize for. This article covers how to sample from real workflows, annotate observable outcomes, cover failure paths, and maintain versions, so evaluation results actually guide engineering decisions.