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
13 articles
Why memory rules fail to stop repeat violations, and how a retro-gate-pipeline cycle creates structural AI self-improvement.
Wire advisor agents into pipeline phase 0 or they stay silent. Brief YAML as hub propagates SEO strategy to writing and review.
Two HUMAN_INPUT types: SSOT values filled by machine, experiential facts left for humans. This split scales your pipeline.
How to diagnose pillar quality across three layers—structure, vocabulary, and prose density—and when to reclassify a cluster.
No inline code and business-decision subjects: two must_avoid constraints that preserve prose density in business-cluster pillars.
Adding sister_pillar_slug to brief YAML separates sister pillars from spokes, aligning graph generation and cross-link skills.
Three Phase A rules prevent breaking changes at Phase B: tenantId in all API args, adapter DI, and cancelToken HMAC hashing.
Implement cluster SEO by using pillar primary keywords as the cluster axis and passing them down to spokes as secondary keywords.
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.
A hybrid design for detecting corporate terms using forbiddenWords and proximity rules to protect the solo practitioner narrative.
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.
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.
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.