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
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 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
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
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
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.