Hyunjoong Kim's Technology Blog
Practical writing on AI agents, SDLC documentation automation, full-stack architecture, and product validation.
31 results
The 2026 Developer Productivity Stack: AI Code Review, Test Generation, and Intelligent CI
How AI is moving beyond code completion into pull request review, security fix suggestions, test generation, and CI recovery workflows.
Post-RAG Architecture: Practical Design for GraphRAG, Hybrid Retrieval, and Evaluation
Why vector-only RAG breaks in production, when GraphRAG is worth the complexity, and how to run a reliable evaluation loop across retrieval, generation, latency, and cost.
Claude Takes the Wheel on Your Mac: How Dispatch and Computer Use Redraw Agent Boundaries
In March 2026 Anthropic shipped Computer Use in Claude Cowork and Claude Code alongside Dispatch. This post ties official docs, press, and hands-on reviews into how it works, what it requires, and where the risks sit.
Agent Security Deep Dive: A Practical Playbook Beyond Prompt Injection
In agentic AI systems, behavior safety matters more than answer quality. This guide covers a layered threat model, control architecture, and operational checklist for secure deployment.
Task-Based Multi-Model Portfolio: Operating for Quality, Latency, and Cost
A single model strategy breaks at scale. This practical guide explains how to design a task-based multi-model portfolio with routing, fallback, and evaluation loops.
Running OpenClaw 24/7 on a Mac mini: Sleep Settings to Stable Operations
A practical runbook for operating OpenClaw 24/7 on a Mac mini. Learn the exact sleep settings, gateway health checks, and fast recovery routine for reliable uptime.