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
Measured
Resume Flags Differ Per Harness, and Getting Them Wrong Kills the Process
Measured session-resume contracts for Codex, Grok, and Claude Code, with the versions they were measured on. The flag names look alike, the behavior does not, and failure is instant death rather than a warning. Plus the bug where one CLI's session IDs were fed to another.
- AI Agents
Measured
Your Cost Table Is Empty and Both the Parser and the Router Are Correct
Wiring a new harness into per-agent cost tracking has three attachment points, not two. The third fails silently. Here is the diagnostic fingerprint for a bug you cannot find by reading the code, plus how unregistered model IDs invent charges.
- AI Agents
Measured
How Do You Know an Agent Is Working? PTY Output Is Wrong in Both Directions
Treat terminal bytes as proof of work and finished agents look busy while working agents look idle. The load average hit 44 on a 12-core machine with 11 zombies while the cleanup tool reported nothing to reclaim. Define turns by boundaries, not noise.
- AI Agents
Marblo Build Notes 10 — Why Telegram Sending Failed While Receiving Worked
Telegram messages arrived, but sending failed with ETIMEDOUT. Trace the IPv6 path, IPv4 connection latency, and Node's connection attempt timeout, with a diagnostic sequence builders can reuse.
- AI Agents
Marblo Build Notes 11 — Merged, So Why Isn't It DONE?
A merge records that code was integrated. How Marblo verifies the combined result, keeps a signed record, and checks remaining work before completion, plus the human cost of a conservative gate.
- 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
Omarchy Deep Dive: A Builder's Linux Workspace with Arch and Hyprland
Explore Omarchy through a fresh development machine, AI coding, and a move from macOS. Covers ISO installation, disk erasure, developer tools, keyboard navigation, themes, updates, and recovery.
- 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
From PHP2Shell to Laravel and WordPress Plugins: October 2026 PHP Security Issues and How to Check Your Servers
A source-backed rundown of October 2026 PHP security issues: the PHP core remote code execution flaws (PHP2Shell), the follow-up session issue, the Laravel TokenGuard authentication bypass and the WordPress Bricksforge file upload flaw, with read-only checks and immediate steps.
- 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 Agents
Introducing the Hypemarc Builder Community — What We Share Every Week
The channels and cadence of Hypemarc's community for builders working with AI agents: how we pick items for the Weekly AI Briefing and the resource library, and how to join through open chat, RSS, and YouTube.
- 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
Marblo Build Notes 1 — The Closed Loop Release
From the closed loop to Orchebrain, Web Tabs, and risk-based independent testers. Eight new features in this Marblo release, plus a preview of Marblo CI.
- AI Agents
Marblo Build Notes 2 — Completing a Mission with the Closed Loop
The October 2026 hypemarc.com improvements: how a mission progressed from orchestrator reviews and ticket assignments to worker PRs, independent testing, merge gates, and production deployment confirmation.
- AI Agents
Marblo Build Notes 3 — Watching Work with Agent Mosaic
Agent Mosaic brings working agents' terminals onto one screen in real time. How teams, leaders, and developers can use it to follow what several AI agents are doing.
- AI Agents
Marblo Build Notes 4 — Following Mission Progress with Orchebrain
Orchebrain groups scattered tickets into missions and shows progress through a summary card and development, testing, and review dots. How teams can use its autonomous progress limits and intake rate controls.
- AI Agents
Marblo Build Notes 5 — Delegating Logged-In Services through Web Tabs
Opening, reading, filling, and testing pages through Marblo Web Tabs. What delegating logged-in services without exposing cookies or passwords means, and when to use it.
- AI Agents
Marblo Build Notes 6 — Integrating Verified PRs with Merge Train
Merge queues and repeated CI after parallel work. How Marblo Merge Train groups verified PRs into a single CI run before applying them to main, and when that is useful.
- AI Agents
Marblo Build Notes 7 — Distributing Work Across Multiple AI Accounts
Marblo distributes work across Claude, GPT, and other accounts by remaining allowance. In the hypemarc.com work, a Claude account fell below the reserve threshold and a new task went to a Codex account.
- AI Agents
Marblo Build Notes 8 — Independent Testers for Important Changes
A separate AI tester verifies important payment, permission, and deployment changes, including counterexamples. The hypemarc.com work shows independent security handoffs, orchestrator reviews, and a build note PR returned for corrections.
- AI Agents
Marblo Build Notes 9 — Setting Direction through Telegram
Give instructions to the orchestrator through Telegram and receive progress and problem-cause reports. In the hypemarc.com work, the CEO's direction led to updated examples, build notes, version labels, and a deployment report.
- AI Agents
Make Three Models Refute Your Hypothesis: the Marblo Adversarial Verification Board
Ask an AI and it usually says 'great idea.' What you actually need is refutation. Here's a Marblo recipe that makes different-vendor agents attack one hypothesis, design, or decision from different angles, so only the conclusions that survive get adopted.
- AI Agents
Plan → Code → Review → Test on One Board: Running a Dev Pipeline in Marblo
Coding got faster but shipping didn't, and the reason is usually the steps around the code and the human handoffs between them. Here's a Marblo dev-pipeline recipe that splits task breakdown, implementation, review, and testing across agents while the team collaborates on one board.
- AI Agents
Turning an Inbox Flood Into 3-Agent Triage: Automating First-Line CS With a Marblo Board
Many of your daily tickets are the same repeat questions with fixed answers. Here's a Marblo board recipe that splits classification, drafting, and safety-checking across separate agents, so your reps only handle what needs judgment.
- AI Agents
Automating the Weekly Marketing Report With a Marblo Board
Still copy-pasting GA4, Naver, and Meta numbers into a report every week? Here's a step-by-step Marblo board recipe that splits collection, analysis, writing, and verification across separate agents.
- 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
Codex 5.5 GOAL Mode: Agents That Work From a Goal
OpenAI Codex's latest GOAL mode changes how autonomous agents are used. We analyze the shift from imperative commands to goal-driven execution, and how it compares to Marblo's natural language orchestrator.
- AI Agents
Why Heterogeneous AI Agents Beat a Single Model: Claude, Codex, and Grok on One Board
Why we recommend heterogeneous agent orchestration over single-vendor setups. The quality and cost benefits of splitting reasoning, generation, and verification across models by strength.
- 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
Claude Code Subagents vs. Real Multi-Agent Orchestration: What's the Difference?
We dissect the gap between Claude Code's 'subagent' pattern and genuine heterogeneous multi-agent orchestration. Single-model N agents vs. heterogeneous N agents, CLI vs. kanban board, shared context vs. physical isolation.
- AI Agents
5 Principles for In-house AI Agent Governance — Design the Trust Hierarchy First
When you adopt AI agents internally, the first question is 'Who is responsible for code an agent wrote?' This article lays out 5 governance principles: privilege separation, audit logs, rollback paths, measurable KPIs, and team training.
- 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.
- SEO/GEO
GEO Optimization Checklist: How to Get Cited by AI Search Engines
A comprehensive checklist for optimizing your content to get cited by Google AI Overview, Perplexity, ChatGPT Search, and other AI search engines. 25 actionable items you can implement today.
- AI Agents
AI-Powered Customer Service: Complete ROI Analysis for 2025
A detailed ROI analysis comparing AI-powered customer service with traditional support teams. Includes example cost breakdowns, satisfaction considerations, an implementation roadmap, and scaling scenarios.
- GA4/BigQuery
Building a Marketing Dashboard with GA4 and BigQuery
Go beyond GA4's limitations by connecting it to BigQuery. Learn how to build a real-time marketing dashboard with unlimited segments, automated alerts, and AI-powered insights.
- 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.