Hyunjoong Kim's Technology Blog

Practical writing on AI agents, SDLC documentation automation, full-stack architecture, and product validation.

29 results

19Insight
2026-03-26 · 14 min

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.

Read more
20Engineering
2026-03-23 · 12 min

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.

Read more
21Engineering
2026-03-20 · 10 min

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.

Read more
22Engineering
2026-03-19 · 9 min

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.

Read more
23Engineering
2026-02-24 · 12 min

Run OpenClaw with Near-Zero AI API Cost: agent-cli-to-api + Cursor CLI Setup

How to connect OpenClaw to a custom provider with agent-cli-to-api and Cursor CLI, so you can operate a fast and stable bot while minimizing external AI API cost.

Read more
24Engineering
2026-02-21 · 20 min

Essential Setup After Installing Claude Code: MCP, Oh My Claude, and Memory

You installed Claude Code — now what? From memory configuration to must-have MCPs and Oh My Claude, here's everything you need to set up right after installation.

Read more