Agent & AI Insights
Claude Code know-how, heterogeneous agents, harness engineering, and more. What the Marblo team measured running these, and what we learned adopting them in-house.
- AI Agents
Is a More Complex Agent Harness Better? Separate Cost from Parallel Work
Compare a fixed-model harness study with Agensh's 1,024-agent experiment. Understand their different conditions and measure quality, cost, time, and integration work before adoption.
- AI Briefing
Weekly AI Briefing 2026-W44: Team Agents, AI Contact Centers, and Inference Data Isolation
Seven AI news stories and five GitHub projects for enterprise AI adoption in week 44 of 2026. Explore Cursor Agent SDK, Copilot team automation, KT's contact center, Cloudflare's incident, and three videos with source links.
- AI Agents
agency-agents Deep Dive: Separate Development, Verification, and Operations by Role
Use agency-agents role definitions to connect UI and API work, review feature evidence, and examine advertising measurement. Includes selective installation, first conversations, official examples, and team adoption considerations.
- AI Agents
Everything Claude Code Deep Dive: Adding Rules, Verification, and Learning to Coding Agents
Explore ECC skills, rules, and hooks through research and planning, verification reports, and reusable development practices. Includes current installation paths, three scenarios, and team adoption considerations.
- AI Agents
UI UX Pro Max Deep Dive: Give Your Coding Agent Design Rules Before It Builds
Explore UI UX Pro Max through three scenarios: a new landing page, a dense operations dashboard, and retheming an existing app, with installation, first run, team fit, and licensing.
- AI Agents
Hermes Agent Deep Dive: Carry Recurring Work Through Memory and Skills
Explore Hermes Agent memory, reusable skills, and scheduled tasks through three practical scenarios, from CLI installation to session boundaries, tool selection, and team operations.
- AI Agents
Superpowers Deep Dive: Connect Agent Design, Tests, and Code Review
Explore Superpowers through three scenarios connecting requirements, implementation plans, debugging, tests, and review, with installation and practical adoption criteria for teams.
- AI Agents
DeepSeek Harness Deep Dive: Check Execution Boundaries Before Adding Plugins
Explore a repository, investigate failing tests, and design an internal tool connection with DeepSeek Harness, including workspace setup and plugin execution boundaries.
- AI Agents
mattpocock/skills Deep Dive: Turn Requirement Questions into Team Practices
Three ways to use mattpocock/skills: clarify a vague request, carry shared terminology into a specification, and test an observable behavior.
- AI Agents
OpenCode Deep Dive: Separate Planning from Changes in an Agent Pilot
Use OpenCode plan and build agents to explore unfamiliar code, make a small change, and review callers and tests, with permission and licensing checks for teams.
- AI Briefing
Weekly AI Briefing 2026-W43: Harness Tuning Without Retraining, Copilot Model Retirements, Korean LLM Agents
Week 43 of 2026 in AI, read from an enterprise AX angle: seven news items, five GitHub repositories whose stars grew fastest this week, new resource library entries, and two videos, each with a link to the original.
- AI Agents
Claude Code + MCP in Real Workflows: Notes from a Korean AI Studio
How a Seoul-based AI agency runs Claude Code with MCP servers across every project. The patterns that actually scale, the integrations that paid off, and the workflow tax we eliminated.
- AI Agents
Building Your First Multi-Agent System with Marblo — Hands-On Tutorial
Walk through building a real multi-agent workflow in Marblo, from blank board to production deploy in under thirty minutes. Researcher, writer, fact-checker — heterogeneous models, MCP tools, and observability included.
- AI Agents
MCP Servers in Production — Authentication, Rate Limits, and Observability
Building MCP (Model Context Protocol) servers for a hobby project is easy. Running them in production with real authentication, real rate limits, and traces you can debug at 2 AM is a different problem. This is what we learned.
- AI Agents
Heterogeneous Agents in Production — Why Single-Model Setups Fail at Scale
After running heterogeneous AI agents in production for 18 months, we measured what single-vendor setups give up. The cost premium, the failure modes, and the team-level patterns that only work when you mix models on purpose.
- AI Agents
AI Agent Orchestration Platforms in 2026 — LangGraph, CrewAI, AutoGen, and Marblo Compared
An engineering-grade comparison of the major AI agent orchestration platforms in 2026. Where each one shines, where each one breaks, and which choice fits which workload — from prototype to multi-team production.
- AI Agents
Model Context Protocol (MCP) Explained: The Standard for Tool-Wielding Agents
MCP gives AI agents standardized access to filesystems, databases, APIs, and Git. We unpack why MCP became the 'USB-C' of the AI agent industry and how to integrate it with internal company systems.
- AI Agents
Building AI Agents for the Korean Market: Platforms, Regulations, and Real-World Use Cases
How to build and deploy AI agents optimized for Korean business environments. Covers KakaoTalk integration, Korean NLP challenges, compliance requirements, and successful implementation strategies for international companies entering Korea.
- AI Agents
AI Agents for Business Automation: Complete Guide 2025
Learn how to automate customer service, sales, and marketing with AI agents using OpenAI's Agent Builder, Response API, and custom implementations.