PulseAugur
EN
LIVE 02:19:15
日本語(JA) AIが無人で書き溜めた社内ドキュメント1,355本をDiátaxisで仕分けたら、3割が自社のドキュメントですらなかった

AI-generated documents analyzed: 32% were extraneous, tutorials absent

By PulseAugur Editorial · [1 sources] ·

An analysis of 1,355 internal documents generated by AI revealed that over 30% were not original content but rather tool-generated files. After removing these extraneous files, the remaining 917 documents were classified using the Diátaxis framework and a local LLM (qwen3.5:latest). The results showed a strong bias towards reference and explanation types, with a complete absence of tutorials, reflecting the AI agents' needs for factual retrieval and understanding rather than step-by-step learning. The process also uncovered a bug in the document processing script that incorrectly classified files within hidden directories. AI

IMPACT Highlights the nature of AI-generated content and the importance of data validation before analysis.

RANK_REASON Analysis of AI-generated content using a specific framework and LLM. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI-generated documents analyzed: 32% were extraneous, tutorials absent

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Analysis of AI-generated content using a specific framework and LLM. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
81 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 日本語(JA) · bigkijimon ·

    When 1,355 internal documents written by AI without human intervention were sorted with Diátaxis, 30% were not even company documents.

    <p>Claude Codeに無人でドキュメントを書かせ続けて数か月経つと、「うちのナレッジベースは今どんな型に偏っているのか」が気になった。答え合わせに <a href="https://diataxis.fr/" rel="noopener noreferrer">Diátaxis</a>（Tutorials / How-to guides / Technical reference / Explanation の4分類フレームワーク）を使い、自社リポジトリの Markdown をローカルLLMで全数分類した。結果は「tutorial型が0.0%」と…

RELATED ENTITIES

RELATED TOPICS