c24165b8bc
에이전트 8종(대화형/프로그래머 C·S/디자이너/설계자/기획자/QA/PD/PM)에게 [공통 기본 능력 + 롤별 Specialty] 2층으로 지식을 주입하기 위한 재분류. 문서 내용·포맷은 무수정, 폴더 이동만 (6,372개 문서 수 보존 확인). - Topic_Programming → Domain_Programming (내부 구조 보존) - Topic_Graphic → Domain_Design - Topic_Business → Domain_Product - Topic_General → Domain_General - _Common 신설: Math(구 Topic_Math_Specialty), Reasoning(구 General/From_Thinking & Reasoning), Reasoning_Creativity(구 General/From_창의성), Communication(Poetic_Blog_Writing + From_writing) - 타 도메인의 From_* 폴더는 유지 (출처 표기일 뿐, 이미 도메인에 맞게 분류된 문서) - 빈 폴더 정리 (memory/procedures) - 에이전트→폴더 매핑은 workspace의 .astra/agent-knowledge-map.json (9개 에이전트) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
5.2 KiB
5.2 KiB
id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, inferred_by, tech_stack
| id | title | category | status | canonical_id | aliases | duplicate_of | source_trust_level | confidence_score | verification_status | tags | raw_sources | last_reinforced | github_commit | inferred_by | tech_stack | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| wiki-2026-0508-ai-answer-engine-optimization | AI Answer Engine Optimization (AEO) | 10_Wiki/Topics | verified | self |
|
none | B | 0.85 | conceptual |
|
2026-05-09 | pending | Claude Opus 4.7 (manual cleanup 2026-05-09) |
|
AI Answer Engine Optimization (AEO)
📌 한 줄 통찰
"Search 의 click → AI answer 의 citation". ChatGPT / Perplexity / Google AI Overviews 의 매 brand 의 source 의 selection. SSR + JSON-LD + semantic HTML + Q&A format.
📖 핵심
매 search engine 의 evolution
- 옛 SEO: keyword + ranking → click.
- AEO: AI 의 answer 의 citation source.
- GEO (Generative Engine Optimization): same idea.
매 AI bot 의 behavior
- GPTBot, Claude-Web, PerplexityBot: crawl + summarize.
- JS execution X: cost. 매 SSR / SSG 의 essential.
- Cite recent sources: freshness.
- Trust signal: domain authority, structured data.
Core technique
1. SSR / SSG (JS Execution Wall 제거)
- 매 SPA 의 JS-only render = bot 의 invisible.
- 매 SSR (Next, Astro) = HTML 의 first paint.
2. Semantic HTML
<article>
<h1>Topic</h1>
<main>
<p>Direct answer in first paragraph.</p>
<h2>Question 1?</h2>
<p>Answer.</p>
</main>
</article>
3. JSON-LD structured data
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "Article",
"headline": "...",
"author": { "@type": "Person", "name": "..." },
"datePublished": "2026-05-09",
"mainEntity": {
"@type": "FAQPage",
"mainEntity": [{
"@type": "Question",
"name": "How to X?",
"acceptedAnswer": { "@type": "Answer", "text": "..." }
}]
}
}
</script>
4. Q&A format
- H2 = question.
- 매 H2 직후 = direct answer.
- 매 paragraph 의 self-contained.
5. Direct answer in lead
- 매 first 50 word 의 answer.
- 매 inverted pyramid (journalism).
6. Citation-friendly
- 매 specific number / fact.
- 매 source 의 explicit.
- 매 author 의 expertise.
7. llm.txt / robots.txt control
# llm.txt (proposal)
# Allow ChatGPT, Claude, Perplexity to cite.
User-agent: *
Allow: /
매 platform 의 difference
Google AI Overviews (SGE)
- 매 YMYL (Your Money Your Life) 의 strict.
- 매 E-E-A-T (Experience, Expertise, Authority, Trust).
- 매 traditional SEO 의 baseline.
ChatGPT / Claude / Perplexity
- Real-time web search.
- 매 cite source.
- Domain trust signal.
Bing Chat / Copilot
- Edge integration.
- 매 enterprise 친화.
💻 Code
Next.js SSR
// app/article/[slug]/page.tsx
export default async function ArticlePage({ params }) {
const article = await fetchArticle(params.slug);
return (
<>
<script type="application/ld+json" dangerouslySetInnerHTML={{ __html: JSON.stringify({
'@context': 'https://schema.org',
'@type': 'Article',
headline: article.title,
author: { '@type': 'Person', name: article.author },
datePublished: article.publishedAt,
})}} />
<article>
<h1>{article.title}</h1>
<p>{article.lead}</p>
<main>{article.content}</main>
</article>
</>
);
}
FAQ 의 schema
function FAQ({ items }: { items: { q: string; a: string }[] }) {
return (
<>
<script type="application/ld+json" dangerouslySetInnerHTML={{ __html: JSON.stringify({
'@context': 'https://schema.org',
'@type': 'FAQPage',
mainEntity: items.map(({ q, a }) => ({
'@type': 'Question',
name: q,
acceptedAnswer: { '@type': 'Answer', text: a },
})),
})}} />
<section>
{items.map(({ q, a }) => (
<>
<h2>{q}</h2>
<p>{a}</p>
</>
))}
</section>
</>
);
}
🤔 결정 기준
| 작업 | 추천 |
|---|---|
| Blog / docs | SSG + JSON-LD |
| 매 product page | SSR + Product schema |
| FAQ | FAQPage schema |
| 매 SPA | SSR fallback 추가 |
| 매 SaaS | E-E-A-T content |
기본값: SSR/SSG + JSON-LD + Q&A format + direct answer in lead.
🔗 Graph
- 부모: SEO · Generative-AI
- 변형: GEO
🤖 LLM 활용
언제: 매 content site 의 AI traffic 의 capture. 매 documentation site 의 visibility. 언제 X: 매 internal app. 매 content gating (paywalled).
❌ 안티패턴
- SPA + no SSR: bot 의 invisible.
- JSON-LD 의 fake: penalty.
- Click-bait title + AI 의 misalign: low citation rate.
- 모든 page 의 same FAQ: spam.
🧪 검증 / 중복
- Verified (concept).
- 신뢰도 B (Search Engine Journal, Schema.org docs).
- Related: AI-Search-Optimization, AI-Overviews-and-SGE.
🕓 Changelog
| 날짜 | 변경 | 처리 | 신뢰도 |
|---|---|---|---|
| 2026-05-08 | Phase 1 정규화 | UPDATE | A |
| 2026-05-09 | Manual cleanup — code + technique + 결정 + 안티패턴 | UPDATE | B |