DEV Community

Jangwook Kim profile picture

Jangwook Kim

404 bio not found

Joined Joined on  Personal website https://effloow.com
MCP-Persona: Tiny Personalized Tool-Use Evaluation
jangwook_kim_e31e7291ad98 profile

MCP-Persona: Tiny Personalized Tool-Use Evaluation

#mcppersona #mcp #agentevaluation #openai
Comments
9 min read
OpenAI Agent Builder and Evals Winddown Migration Checklist
jangwook_kim_e31e7291ad98 profile

OpenAI Agent Builder and Evals Winddown Migration Checklist

#openai #agentbuilder #evals #agentssdk
Comments
11 min read
Claude Code June 2026 Update: Safe Mode, Opus 4.8, and Doubled Rate Limits
jangwook_kim_e31e7291ad98 profile

Claude Code June 2026 Update: Safe Mode, Opus 4.8, and Doubled Rate Limits

Comments
7 min read
Drizzle ORM Complete Guide: Type-Safe TypeScript DB Layer
jangwook_kim_e31e7291ad98 profile

Drizzle ORM Complete Guide: Type-Safe TypeScript DB Layer

Comments
8 min read
GitHub Agent Tasks REST API: Safe Automation Launcher PoC
jangwook_kim_e31e7291ad98 profile

GitHub Agent Tasks REST API: Safe Automation Launcher PoC

#githubcopilot #agenttasks #restapi #developertools
Comments
9 min read
Node.js Built-in SQLite: A Practical Guide — No npm Install Required
jangwook_kim_e31e7291ad98 profile

Node.js Built-in SQLite: A Practical Guide — No npm Install Required

#node #sqlite #builtinmodule
Comments
7 min read
OpenAI Apps SDK: Internal MCP App Readiness Checklist for ChatGPT
jangwook_kim_e31e7291ad98 profile

OpenAI Apps SDK: Internal MCP App Readiness Checklist for ChatGPT

#openaiappssdk #chatgptapps #mcp #developermode
1
Comments
11 min read
Audit Copilot Cloud Agent Config with the REST API
jangwook_kim_e31e7291ad98 profile

Audit Copilot Cloud Agent Config with the REST API

#githubcopilot #cloudagent #restapi #mcp
Comments
9 min read
GitHub Copilot SDK: Governed Agent Runtime PoC
jangwook_kim_e31e7291ad98 profile

GitHub Copilot SDK: Governed Agent Runtime PoC

#githubcopilot #copilotsdk #aiagents #mcp
Comments
8 min read
LlamaIndex vs LangChain vs Haystack — RAG Framework Comparison 2026
jangwook_kim_e31e7291ad98 profile

LlamaIndex vs LangChain vs Haystack — RAG Framework Comparison 2026

Comments
8 min read
GitHub Copilot AI Credits: Usage-Based Billing Guide
jangwook_kim_e31e7291ad98 profile

GitHub Copilot AI Credits: Usage-Based Billing Guide

#githubcopilot #aibilling #developertools #aicredits
Comments
9 min read
Amazon Kiro Analysis — Can a Spec-Driven AI IDE Replace Claude Code?
jangwook_kim_e31e7291ad98 profile

Amazon Kiro Analysis — Can a Spec-Driven AI IDE Replace Claude Code?

Comments
6 min read
BAGEN: LLM Agents Waste 44% of Tokens on Tasks They'll Fail
jangwook_kim_e31e7291ad98 profile

BAGEN: LLM Agents Waste 44% of Tokens on Tasks They'll Fail

#llmagents #tokenoptimization #paperpoc #aicost
Comments
9 min read
MCP Goes Stateless: What the 2026-07-28 RC Means for Servers
jangwook_kim_e31e7291ad98 profile

MCP Goes Stateless: What the 2026-07-28 RC Means for Servers

#mcp #modelcontextprotocol #statelesshttp #aiagents
Comments
9 min read
Project Polaris: GitHub Copilot's New MoE Coding Model
jangwook_kim_e31e7291ad98 profile

Project Polaris: GitHub Copilot's New MoE Coding Model

#githubcopilot #projectpolaris #microsoftbuild2026 #mixtureofexperts
Comments
9 min read
Deno 2 vs Bun 1.3 — Node.js Runtime Alternatives Compared in 2026: TypeScript, Speed, and Security
jangwook_kim_e31e7291ad98 profile

Deno 2 vs Bun 1.3 — Node.js Runtime Alternatives Compared in 2026: TypeScript, Speed, and Security

#deno #bunjs #typescript #node
Comments
8 min read
Microsoft ASSERT: Turn Agent Policies Into Executable Evals
jangwook_kim_e31e7291ad98 profile

Microsoft ASSERT: Turn Agent Policies Into Executable Evals

#microsoft #aievaluation #agentsafety #opensource
Comments
9 min read
Microsoft ACS SDK: Agent Control Sandbox PoC
jangwook_kim_e31e7291ad98 profile

Microsoft ACS SDK: Agent Control Sandbox PoC

#microsoft #acs #agentgovernance #aiagents
1
Comments
10 min read
Microsoft Build 2026: Windows Agent Runtime and Project Polaris
jangwook_kim_e31e7291ad98 profile

Microsoft Build 2026: Windows Agent Runtime and Project Polaris

#microsoft #windowsagentruntime #projectpolaris #wsl3
Comments
10 min read
Building an Edge REST API with Hono.js + TypeScript — From Bun Local Server to Cloudflare Workers
jangwook_kim_e31e7291ad98 profile

Building an Edge REST API with Hono.js + TypeScript — From Bun Local Server to Cloudflare Workers

#hono #typescript #restapi #cloudflareworkers
Comments
9 min read
Constraint Decay: Why LLM Agents Fail at Real Backend Code
jangwook_kim_e31e7291ad98 profile

Constraint Decay: Why LLM Agents Fail at Real Backend Code

#airesearch #paperpoc #llm #2026
Comments
9 min read
OpenTelemetry GenAI: Trace LLM Agent Tool Calls
jangwook_kim_e31e7291ad98 profile

OpenTelemetry GenAI: Trace LLM Agent Tool Calls

#opentelemetry #genai #observability #llmagents
Comments
9 min read
Amazon OpenSearch Agentic AI: Investigation Agent Guide
jangwook_kim_e31e7291ad98 profile

Amazon OpenSearch Agentic AI: Investigation Agent Guide

#amazonopensearch #agenticai #observability #incidentresponse
Comments
9 min read
SciAgentGYM: 1,780 Scientific Tools, One Hard Benchmark
jangwook_kim_e31e7291ad98 profile

SciAgentGYM: 1,780 Scientific Tools, One Hard Benchmark

#llmagents #benchmarks #scientificai #tooluse
Comments
9 min read
LangGraph Platform GA: Studio v2, One-Click Deploy Guide
jangwook_kim_e31e7291ad98 profile

LangGraph Platform GA: Studio v2, One-Click Deploy Guide

#langgraph #agentdeployment #aiframeworks #developertools
Comments
10 min read
TypeScript Zod v4 + Claude API: A Complete Guide to Type-Safe LLM Response Parsing
jangwook_kim_e31e7291ad98 profile

TypeScript Zod v4 + Claude API: A Complete Guide to Type-Safe LLM Response Parsing

#typescript #zod #claudeapi
Comments
11 min read
Testing AI Agents with Vitest 4 — Mocking LLM Calls and Streaming Responses in Practice
jangwook_kim_e31e7291ad98 profile

Testing AI Agents with Vitest 4 — Mocking LLM Calls and Streaming Responses in Practice

#vitest #agents #typescript
Comments
6 min read
Building Your Own MCP Server with TypeScript — A Practical @modelcontextprotocol/sdk Tutorial
jangwook_kim_e31e7291ad98 profile

Building Your Own MCP Server with TypeScript — A Practical @modelcontextprotocol/sdk Tutorial

#mcp #typescript #tutorial
Comments
12 min read
Gemini API Managed Agents Practical Guide — Run AI Agents in an Isolated Sandbox with One Call
jangwook_kim_e31e7291ad98 profile

Gemini API Managed Agents Practical Guide — Run AI Agents in an Isolated Sandbox with One Call

#geminiapi #aiagents #googleio2026
Comments 1
11 min read
AWS MCP Server GA: Secure AWS API Access for AI Agents
jangwook_kim_e31e7291ad98 profile

AWS MCP Server GA: Secure AWS API Access for AI Agents

#awsmcp #mcp #aiagents #aws
Comments
14 min read
Claude Opus 4.8 Dynamic Workflows: 1,000 Parallel Agents and Fast Mode in Practice
jangwook_kim_e31e7291ad98 profile

Claude Opus 4.8 Dynamic Workflows: 1,000 Parallel Agents and Fast Mode in Practice

#claude #aiagents #anthropic
Comments 1
9 min read
WebMCP PoC: Expose Browser Tools to AI Agents
jangwook_kim_e31e7291ad98 profile

WebMCP PoC: Expose Browser Tools to AI Agents

#webmcp #mcp #browseragents #agenticweb
Comments
8 min read
Qwen3.7-Max: Alibaba's Agent-First 1M-Context LLM Developer Guide
jangwook_kim_e31e7291ad98 profile

Qwen3.7-Max: Alibaba's Agent-First 1M-Context LLM Developer Guide

#qwen #alibaba #agenticcoding #llm
Comments
11 min read
Building a Local LLM API Server with Ollama + FastAPI — From Dev to Docker Deployment
jangwook_kim_e31e7291ad98 profile

Building a Local LLM API Server with Ollama + FastAPI — From Dev to Docker Deployment

#ollama #fastapi #localllm #python
Comments
8 min read
RL Doesn't Teach LLMs New Reasoning — It Fixes 1-3% of Tokens
jangwook_kim_e31e7291ad98 profile

RL Doesn't Teach LLMs New Reasoning — It Fixes 1-3% of Tokens

#reinforcementlearning #llmreasoning #paperpoc #rlvr
Comments
8 min read
Genkit 2.0 GA: Build and Deploy a TypeScript MCP Server to Cloud Run
jangwook_kim_e31e7291ad98 profile

Genkit 2.0 GA: Build and Deploy a TypeScript MCP Server to Cloud Run

#genkit #mcp #cloudrun #typescript
1
Comments
8 min read
Codex Goal Mode: Run Long-Horizon AI Coding Tasks for Hours or Days
jangwook_kim_e31e7291ad98 profile

Codex Goal Mode: Run Long-Horizon AI Coding Tasks for Hours or Days

#openai #codex #agenticcoding #developertools
Comments
9 min read
MCP Remote HTTP Server Deployment Patterns — A Practical Guide to Moving from stdio to Streamable HTTP
jangwook_kim_e31e7291ad98 profile

MCP Remote HTTP Server Deployment Patterns — A Practical Guide to Moving from stdio to Streamable HTTP

Comments
7 min read
ARTIST: RL-Powered Tool Use for LLM Agents Explained
jangwook_kim_e31e7291ad98 profile

ARTIST: RL-Powered Tool Use for LLM Agents Explained

#reinforcementlearning #llmagents #tooluse #agenticai
Comments
9 min read
Genkit 2.0 GA: Firebase AI, MCP, and Cloud Run
jangwook_kim_e31e7291ad98 profile

Genkit 2.0 GA: Firebase AI, MCP, and Cloud Run

#genkit #firebase #mcp #cloudrun
Comments
8 min read
NVIDIA Nemotron 3 Nano Omni: Multimodal Agent Dev Guide
jangwook_kim_e31e7291ad98 profile

NVIDIA Nemotron 3 Nano Omni: Multimodal Agent Dev Guide

#nvidia #nemotron #multimodal #opensource
Comments
10 min read
Migrating from Jest to Vitest 4: A Complete 2026 Guide
jangwook_kim_e31e7291ad98 profile

Migrating from Jest to Vitest 4: A Complete 2026 Guide

#vitest #jest #typescript
Comments
6 min read
AgentAtlas: LLM Agent Benchmarks Need More Than Accuracy
jangwook_kim_e31e7291ad98 profile

AgentAtlas: LLM Agent Benchmarks Need More Than Accuracy

#llmagents #benchmarking #evaluation #aidevelopment
Comments
8 min read
Claude MCP Tunnels: Private MCP Access for Agents
jangwook_kim_e31e7291ad98 profile

Claude MCP Tunnels: Private MCP Access for Agents

#claude #anthropic #mcp #managedagents
Comments
10 min read
SubQ: Sub-Quadratic LLM with 12M Token Context — 2026 Guide
jangwook_kim_e31e7291ad98 profile

SubQ: Sub-Quadratic LLM with 12M Token Context — 2026 Guide

#subq #subquadratic #longcontextllm #sparseattention
Comments
8 min read
Building Automation Scripts with Bun Shell — From Setup to Real-World Patterns
jangwook_kim_e31e7291ad98 profile

Building Automation Scripts with Bun Shell — From Setup to Real-World Patterns

#bunjs #typescript #automation #shell
Comments
7 min read
Reward Hacking in LLM Agents: What the RHB Benchmark Reveals
jangwook_kim_e31e7291ad98 profile

Reward Hacking in LLM Agents: What the RHB Benchmark Reveals

#aisafety #llmagents #reinforcementlearning #benchmarks
Comments
7 min read
Google Managed Agents: Gemini API Runtime Guide 2026
jangwook_kim_e31e7291ad98 profile

Google Managed Agents: Gemini API Runtime Guide 2026

#gemini #managedagents #antigravity #interactionsapi
Comments
9 min read
Claude Design: Developer Guide to Anthropic's Prototyping Tool
jangwook_kim_e31e7291ad98 profile

Claude Design: Developer Guide to Anthropic's Prototyping Tool

#claude #anthropic #designtools #prototyping
Comments
11 min read
Gemini API Model Selection Guide 2026 — Speed, Cost, and Quality Trade-offs Measured Directly from Flash-Lite to 3.5 Flash
jangwook_kim_e31e7291ad98 profile

Gemini API Model Selection Guide 2026 — Speed, Cost, and Quality Trade-offs Measured Directly from Flash-Lite to 3.5 Flash

#gemini #api #llm #benchmark
Comments
8 min read
AutoExperiment: Testing AI Agents on Research Replication
jangwook_kim_e31e7291ad98 profile

AutoExperiment: Testing AI Agents on Research Replication

#aiagents #benchmarks #researchreplication #paperpoc
Comments
13 min read
AI Pair Programming to Autonomous Teams: A 2026 Workflow
jangwook_kim_e31e7291ad98 profile

AI Pair Programming to Autonomous Teams: A 2026 Workflow

#aicoding #autonomousagents #developerworkflow #codereview
Comments
10 min read
Code with Claude 2026: Managed Agents, Dreaming & AWS
jangwook_kim_e31e7291ad98 profile

Code with Claude 2026: Managed Agents, Dreaming & AWS

#anthropic #claude #managedagents #developerconference
Comments
10 min read
Vector DB Comparison 2026 — Qdrant vs ChromaDB vs pgvector: What the Benchmarks Actually Show
jangwook_kim_e31e7291ad98 profile

Vector DB Comparison 2026 — Qdrant vs ChromaDB vs pgvector: What the Benchmarks Actually Show

Comments
9 min read
Multi-Agent LLM Topology Diagnostics with Successor Representation
jangwook_kim_e31e7291ad98 profile

Multi-Agent LLM Topology Diagnostics with Successor Representation

#multiagent #llmagents #paperpoc #spectralanalysis
Comments
10 min read
Computer-Use Agents in 2026: From Demo to Developer Tool
jangwook_kim_e31e7291ad98 profile

Computer-Use Agents in 2026: From Demo to Developer Tool

#computeruse #aiagents #browserautomation #playwright
Comments
9 min read
LMR-BENCH: Can LLM Agents Reproduce NLP Research Code? (EMNLP 2025)
jangwook_kim_e31e7291ad98 profile

LMR-BENCH: Can LLM Agents Reproduce NLP Research Code? (EMNLP 2025)

#benchmark #researchreproducibility #llmagents #paperpoc
Comments
5 min read
Microsoft Agent Framework 1.6 with Anthropic: Python PoC
jangwook_kim_e31e7291ad98 profile

Microsoft Agent Framework 1.6 with Anthropic: Python PoC

#microsoftagentframework #anthropic #python #multiagent
Comments
5 min read
DeepSeek V4-Pro: MIT Frontier Model Developer Guide 2026
jangwook_kim_e31e7291ad98 profile

DeepSeek V4-Pro: MIT Frontier Model Developer Guide 2026

#deepseek #opensourcellm #mitlicense #aitools
Comments
10 min read
I Tried RTK (Rust Token Killer) — A CLI Proxy That Cuts LLM Token Costs 60–90%
jangwook_kim_e31e7291ad98 profile

I Tried RTK (Rust Token Killer) — A CLI Proxy That Cuts LLM Token Costs 60–90%

Comments
7 min read
loading...