Verify Search Console Ownership with Vercel DNS
Find and fix failed Google Search Console TXT verification when a domain is registered externally but its DNS is delegated to Vercel.
Shiori
65 posts by Shiori
Ontology, Knowledge Graphs, RAG, and GraphRAG: How to Choose
A beginner-friendly comparison of ontology, knowledge graphs, RAG, and GraphRAG that explains each role and shows how to choose from where an answer lives.
WebMCP Explained: How AI Works with a Live Web Page
A beginner-friendly explanation of why WebMCP was proposed, its two ways to describe page features, how it differs from adjacent technologies, and how to test it safely.
Developing Palantir-Style AI Talent: An FDE/DS/GTM Playbook
A practical guide to the AI, engineering, and business-change skills required across FDE, Deployment Strategist, and GTM roles, with a 90-day program built around production work, evaluation, reuse, and internal ownership.
Palantir FDE, DS, and GTM: Consultants vs. Onsite Engineers
A comparison of Palantir's FDE, Deployment Strategist, and GTM responsibilities with consulting and onsite engineering, including global and Japanese trends, implementation risks, and an operating-model checklist.
Creative AI Governance: Production, Creation Records, and Distribution
A comparison of OpenMontage, AIFX, and AdCP across production work, finished-work creation records, and advertising distribution.
AIFX: Creation Records vs. Rights Review
A practical enterprise design that separates AIFX creation records and integrity checks from rights review and human release approval.
What Is AdCP? Governing AI Advertising from Creation to Delivery
A practical reading of AdCP Creative, Governance, and Trust specifications for connecting AI-generated ads to review, approval, and delivery.
Agent Observability Without Centralizing Conversation Content
A design for monitoring long-running agent behavior through minimal safety signals without centralizing conversations and documents.
Capability CI/CD: Verifying Agent Skills Before Distribution
A practical design for checking the structure, safety, overlap, effectiveness, and source record of an Agent Skill before production distribution.
Verification-First Agents: Validating Answers Through Evidence
A Verification-First design that links claims to evidence as they are produced and independently checks them before action.
What Is OpenMontage? Governing AI Video Production in the Enterprise
An explanation of OpenMontage as a way to organize the stages, responsibilities, approvals, and records of AI video production rather than as a list of code features.
What Is Palantir Ontology? Designing an Operational Layer
A guide to Palantir Ontology covering its origins, Objects, Links, Actions, Functions, permissions, applications, differences from knowledge graphs and RAG, and a practical PoC decision framework.
What Is Hermes Agent? Differences, Use Cases, and Extensions
A research-based overview of Hermes Agent covering framework differences, use cases, extensions, and considerations for organizational use.
What Is AI-DLC? Understanding AWS's Proposed Approach Through Examples
An explanation of AWS's AI-Driven Development Life Cycle through its current five phases, official examples, enterprise case, and adoption checklist.
AWS Ontology: An Introduction to Context Ontology Accelerator
Learn how AWS Context Ontology Accelerator differs from RAG and knowledge graphs, how it uses Neptune, OpenSearch, and Bedrock, and what to evaluate before enterprise adoption.
Managing Enterprise AI Coding Costs
A guide for IT administrators managing Claude, Codex, and GitHub Copilot costs, user selection, budget limits, adoption, and monthly license reviews.
What Is SkillOps? How Google Operates Agent Skills
Google revealed how it builds, tests, and scales Agent Skills on August 4, 2026. This article explains the concrete practices and a practical SkillOps adoption path.
/goal vs /plan in Codex and Claude Code: When to Use Each
Use /goal and /plan in Claude Code and Codex with model guidance, usage budgets, human checkpoints, and document and development workflows.
Choosing AI Agent Output: HTML or Markdown
Using the Claude Code team's HTML workflow as a starting point, this article separates when to use Markdown, HTML, XML, and JSON for AI agent outputs.
Designing Self-Healing Loops for Coding Agents
A practical guide to coding-agent self-healing loops based on 2026 research and official implementations from OpenAI, Google, and GitHub, covering layered verification, stop conditions, permission boundaries, and human approval.
What Is Generative UI? Architecture, Use Cases, and Constraints
An overview of Generative UI, where the AI generates the interface itself rather than text, covering how it works, use cases in the Vercel AI SDK and Claude, its potential, and points to check before adoption.
Claude Code vs Codex: How to Choose by Workflow Stage
How I choose between Claude Code and Codex in the same repository by comparing discussion, design, implementation, verification, and handoff work.
How AI Development Rules Protect Color Accessibility
How I am building a harness to reduce repeated color accessibility issues in UI components created through Vibe Coding, especially across light/dark themes, hover, selected, and focus states.
Codex Memories: What to Store and When to Reset
A practical guide to what Codex Memories are for, how they differ from AGENTS.md, and when to avoid, review, or reset memory behavior.
AI Agent Skills vs Instruction Files: When to Use Each
A practical comparison of Claude Code Skills, Codex Skills, GitHub Copilot Skills, Google Antigravity Skills, CLAUDE.md, AGENTS.md, GEMINI.md, and copilot-instructions.md, with guidance on what belongs where.
Claude Code to Codex Handoffs: Three Ways to Preserve Context
How I decide when to use Claude Code versus Codex in the same repository, and how I design handoff documents to transfer context across sessions.
How prebuild Normalization Prevents Validation-Order Failures
How I reduced recurring Astro build failures by moving automatic normalization into prebuild instead of treating each failure as a one-off fix.
How to Verify AI-Implemented UIs with Playwright
How AI Learning Playground positions Playwright alongside structural checks, URL verification, and human review.
Copyright and Publication Responsibility in AI-Assisted Writing
A summary of copyright, responsibility, and reader disclosure policy when using AI as a writing support tool.
A 12-Step Pre-Publication Review for AI Drafts
When using AI to draft blog posts, I separate structural checks from publication approval and keep new articles out of passed until human review is complete.
AWS AI BPR: A Strength-Based Workflow for Process Redesign
A plain-language information summary of AWS AI BPR, its four strength-based steps, and the questions to consider when evaluating it for AI projects.
Three Months of Vibe Coding: From Development to Maintenance
A look back at three months of building and running AI Learning Playground with Vibe Coding, organized around insights from the technical, design, and operational phases.
Claude Dynamic Workflows: Architecture and Parallel Task Design
A plain-language guide to Dynamic Workflows in Claude Code: how multiple AI workers divide a job, which tasks fit, and how to plan outputs, limits, costs, and resumption.
Claude Design: Workflow Roles vs Figma and Canva
A plain-language workflow for using Claude Design for early concepts and dividing later work among Figma, Canva, and Claude Code.
What Is Vibe Coding? Capabilities and Human Review Boundaries
A clear distinction between Vibe Coding and broader AI-assisted development, plus the human review needed for prototypes and production use.
Claude Code Hooks: Setup and Automated Check Examples
A plain-language guide to using Claude Code Hooks for repeated checks, including before-versus-after timing, human approval boundaries, and an adoption process.
How to Reduce Claude Code Token Use Without Losing Quality
Seven ways to reduce Claude Code input and output tokens while preserving required context, verification, and safety constraints.
AI Driven vs AI Native: Differences and When to Use Each
AI Driven and AI Native represent different starting points for how organizations design their relationship with AI. This article clarifies the distinction and what each approach means in practice.
How to Preserve AI Workflow Decisions in lessons.md
How to record an AI workflow problem, cause, resolution, and prevention in lessons.md as a decision history that later work can verify.
Approval Gates for AI Agent Build Commands
A record of how a production build command ran while I was asking AI to make a separate change, and the approval-required rule I put in place afterward.
How to Hand Off a Dirty Worktree Between AI Tools
A safe handoff process for uncommitted changes, separating what Codex Local, Worktree, and Cloud environments can see.
How to Validate AI-Suggested Reference URLs Automatically
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.
AI Article Citation Rules: Separating Experience from External Facts
Practical citation rules for AI-assisted blog writing: how to separate personal experience from external facts and decide where references are required.
How to Validate Internal Links Against Public URLs
A file exists in the repository but the link is broken — this happened on this site. Here is why verifying internal links by file path alone is insufficient, and how I addressed it.
How to Prevent Unrequested UI Changes in AI Development
While asking AI to add a blog article, I discovered that the navigation layout had also been changed without instruction. This article describes why that happened and how I addressed it with a rule in CLAUDE.md.
Building Validation Scripts with AI to Automate Manual Checks
Manually checking the consistency of configuration files has limits. This article covers the process of building a validation script with AI and why automated detection proved useful.
Automatic learning_time Normalization: Design and Implementation
I updated the learning_time workflow so docs articles normalize reading time during authoring, while dev:check and prebuild keep the same normalization as a safety net.
How to Prevent JA-EN Blog Drift with Structural Checks
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.
How to Build a Blog Writing Skill with Voice and Quality Rules
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.
What Is SKILL.md? Standardizing Repeatable AI Work
Repeating the same instructions to an AI every time is less stable than defining procedures as a skill file. This article covers how I designed SKILL.md files for this site and what changed as a result.
What Is Spec First? Reducing Rework in AI Implementation
Writing a specification before asking AI to implement reduces mismatches and repeated revisions. This article explains the Spec First principle and what to include in a simple specification.
Sharing Claude Code and Codex Rules in shared/
When the number of rule files for AI grows, knowing what is where becomes difficult. This article explains how I organized them into three categories—rules, skills, and workflows—using the shared/ directory.
What Is Harness Engineering? A Three-Layer AI Development System
AI gives different answers to the same question, and it does not remember previous sessions. This article explains how I use the term Harness Engineering for this site's AI operation practices.
How to Detect AI Agent Harness Drift Automatically
How harness drift separates shared rules from tool-specific configuration, and how synchronization checks detect the mismatch earlier.
Three Criteria for Evaluating Harness Engineering Benefits
A three-part framework—repeatability, specificity, and verifiability—for deciding which recurring AI workflow problems belong in a harness.
One Page, One Topic: How to Clarify Search Intent
Putting multiple topics into a single article makes it hard for readers to find what they need. This article explains why I introduced the one page, one topic policy on this site and what criteria I use to determine what counts as one topic.
AI Draft Review Workflow: Automated Checks and Human Judgment
Based on experience checking AI-created drafts with automated review before human review, this article clarifies what automated checks reliably detect and where human judgment remains necessary.
Review Criteria for Code Created by Coding Agents: Priorities by Change Type
A review table for code created by coding agents, separating external connections, data changes, calculation and transformation logic, and UI code by verification priority.
What Work to Delegate to AI: Three Decision Criteria
A pre-delegation risk check for AI tasks, using reversibility, scope of impact, ease of verification, and the human decisions that should remain under human control.
Four Rules for Editing AI Drafts into Business Japanese
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.
Five Causes of Mermaid Rendering Failures in AI Drafts
A record of five specific patterns where AI-assisted Mermaid diagrams failed to render correctly, including special characters, arrow direction, label length, Japanese text, and nested structures.
How to Write CLAUDE.md: Three Types of Effective Instructions
How to write CLAUDE.md to give Claude Code project context, with before-and-after examples and the boundary between guidance and enforcement.
How to Set Up and Verify Google Analytics on Vercel
A step-by-step guide to setting up Google Analytics in a Vercel environment, covering measurement IDs, environment variables, and an Astro component.
What Is AI Learning Playground? Practical Enterprise AI Learning
A guide to the structure of AI Learning Playground and where to start learning generative AI, organizational adoption, development, and governance.