Engineering 2026-05-28
AI Agent Self-Violation Visibility — Cycle Design Beyond Memory
Why memory rules fail to stop repeat violations, and how a retro-gate-pipeline cycle creates structural AI self-improvement.
TAG
#Claude Code
13 articles
Engineering 2026-05-27
HUMAN_INPUT Autofill Design: Classify SSOT vs. Experiential Facts
Two HUMAN_INPUT types: SSOT values filled by machine, experiential facts left for humans. This split scales your pipeline.
Engineering 2026-05-25
Deploying Claude Code for Non-Engineers: CLAUDE.md and Permission Pitfalls
Practical guide for tech leads to design safe Claude Code environments via CLAUDE.md scoping, skill I/O, and permission models.
Business 2026-05-24
Expanding blog-gate into a Strategic Gate — Moving from Cosmetic Detection to G-Rule Structuring
A pattern for extending blog-gate G-rules to structurally detect missing SEO, audience, and cluster information. This article outlines how to design systems that allow machines to catch architectural failures, such as missing pillar strategy layers, before content production begins.
Engineering 2026-05-24
Automating Brand Rule Checks — Context-Aware Detection of Self-Reference vs. External Reference
Prevent referring to Yakumo as a "company" with a context-aware gate. Learn to combine proximity analysis, allow-lists, and regex.
Engineering 2026-05-24
Bulk Video Production with Claude Code + Remotion — Full montage Pipeline Architecture
The montage design for bulk video production via 4-agent division and Remotion type definitions. Full disclosure of the pipeline DAG, Block Schema, and Zod validation.
Business 2026-05-23
Allow-list-driven Brand Check — SSOT Design for External Org Exceptions
How to centralize brand rule exception management in an SSOT. Defines allow-lists and reference patterns in brand.ts, with gate scripts referencing them.
Business 2026-05-23
Pre-publish Gate Design: Balancing False Positives and False Negatives
Learn how to design quality gates that balance strictness and flexibility using 3-level analysis and a two-stage fail/warn system.
Engineering 2026-05-23
Advancing Pre-publish Gates: From Plain Grep to Proximity Analysis
Fix false positives in quality gates using stripCodeContexts and proximity analysis to resolve self-contradictions.
Business 2026-05-22
Organizational Design for Non-Engineers Using Claude Code — Business Decisions and Delegation
Building 6 products without engineers: skill delegation, CLAUDE.md design, and staged authority handoff for executives and PMs.
Engineering 2026-05-22
AI Agent Harness Design Principles — Ownership, Skill Delegation, and Fallback
Principles for designing a harness that safely delegates work to AI agents. Covers director agents, skill delegation, fallback phases, and deterministic skills in Claude Code.
Engineering 2026-05-22
Synapse Agent Architecture — The {domain}-director Pattern
How to build a cross-functional agent organization on Claude Code. Full disclosure of the {domain}-director pattern, skill delegation, and .claude/agents/ structure. For senior engineers implementing AI agent harnesses.
Engineering 2026-05-21
Structural Design of mcluhan, an Owned Media Operations Engine — State Machine, Gate, SSOT, Retro Accumulation
Full disclosure of mcluhan's design: a 4-state machine, 10-item pre-publish Gate, and SSOT-backed rules that mechanically stop AI content quality failures before human review. Built from the wreckage of 11 failures in Phase 0.