A reference architecture for carrying approved versions and decision records from production through ad delivery, based on the roles and limits of OpenMontage, AIFX, and AdCP.
How AIFX and AIFI creation records and file checks differ from the rights review and release approval that organizations must perform separately.
Using the AdCP Creative, Governance, and Trust specifications, this article separates information the protocol can carry from the checks and management responsibilities organizations retain.
Using OpenMontage as an example, this article explains how to organize AI video production stages, responsibilities, approvals, records, and enterprise adoption checks.
Using the Claude Code team's HTML workflow as a starting point, this article explains when to use Markdown, HTML, XML, and JSON for AI agent outputs.
A summary of copyright, responsibility, and reader disclosure policy when using AI as a writing support tool.
A twelve-stage review for AI-drafted blog posts that separates structural checks from human approval and prevents the creating AI from approving its own draft.
AI can suggest reference URL candidates that do not actually exist. This article covers how the URL-checking script for this site works and how it classifies results before human source review.
Practical citation rules for AI-assisted blog writing: how to separate personal experience from external facts and decide where references are required.
This article explains the current workflow for synchronizing English articles from canonical Japanese, using three translation-drift patterns and a two-stage checklist. It separates differences that structural checks can surface from semantic differences that require human judgment.
When I use AI to draft articles, the author's voice can become hard to see. To address this, I defined writing style, prohibited expressions, and E-E-A-T review criteria in my-blog-writing SKILL. This article explains how the skill keeps drafts easier for the author to edit and review.
Criteria for keeping related material together or splitting it into separate articles, using the reader’s question, search intent, and update scope while retaining necessary supporting explanations.
AI-created Japanese drafts are often not suitable for business documents as-is. This article categorizes four common expression patterns and provides concrete rewriting examples for each.
