[Claude Code] Building a Real-Time Agent Dashboard
How I built a real-time monitoring dashboard to visualize what 19 Claude Code subagents are doing – from a failed Gather Town experiment to a practical WebSocket-powered control center.
AI
[Claude Code] Designing an Expert Team with Subagents
How to build an expert team from planning to deployment by combining Claude Code’s Subagents, Skills, Rules, Hooks, and MCP Servers.
[Kiro] MCP Server Configuration
A guide on how to configure and manage MCP servers in Kiro, with practical examples.
[Kiro] Agent Configuration
A guide covering agent creation, configuration, prompt modularization, and sub-agent usage in Kiro.
[Kiro] CLI Installation and Settings
A guide on how to install Kiro CLI and the key configuration options in the cli.json settings file.
[Kiro] Kiro x Claude: 3-Tier AI Service Architecture
An analysis of how Kiro calls Claude models through a Client Layer + 3-Tier Service Layer, and why the same model delivers different performance depending on the App Provider.
[LLM] HyDE — Hypothetical Document Embeddings
An overview of HyDE (Hypothetical Document Embeddings), a technique for improving retrieval quality in RAG.
[LLM] LangChain Core Concepts — LCEL, Prompt Templates, Message Classes
An overview of LangChain’s LCEL, prompt templates, message classes, MessagesPlaceholder, and RunnableGenerator.
[LLM] Integrating LLMs with the Ollama Python Library
Using the Ollama Python library to connect to a remote LLM server, with generate, chat, and LangChain integration.
[MCP] Building an MCP Server for Scapple Diagrams
I built an MCP server that lets AI assistants read, write, and render Scapple files directly.
[LLM] Setting Up Ollama Remote Access
Configuring the OLLAMA_HOST environment variable and Windows Firewall to access a local LLM from other devices on the same network.
[LLM] Running Qwen3:8B with Ollama on Windows 11
A complete guide to installing Ollama and running the Qwen3:8B model locally on Windows 11.