[G1-Sync] Manual knowledge update

This commit is contained in:
Antigravity Agent
2026-05-10 22:08:15 +09:00
parent 21ac3ed255
commit 504fd5fb42
3011 changed files with 380280 additions and 206977 deletions
+140 -42
View File
@@ -1,66 +1,164 @@
---
id: wiki-2026-0508-sme
title: SME
title: SME (Subject Matter Expert / Small-Medium Enterprise)
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: [P-Reinforce-AUTO-SMEE-001]
aliases: [Subject Matter Expert, Small-Medium Enterprise, Domain Expert]
duplicate_of: none
source_trust_level: A
confidence_score: 0.96
tags: [auto-reinforced, sme, subject-matter-expert, professional-knowledge, consulting, domain-expertise]
confidence_score: 0.9
verification_status: applied
tags: [sme, domain-expert, knowledge-elicitation, business]
raw_sources: []
last_reinforced: 2026-04-20
last_reinforced: 2026-05-10
github_commit: pending
inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
tech_stack:
language: Python
framework: Anthropic Claude API
---
# [[SME|SME]]
# SME (Subject Matter Expert / Small-Medium Enterprise)
## 📌 한 줄 통찰 (The Karpathy Summary)
> "지식의 최전선 파수꾼: 구글을 뒤져도 나오지 않는 그 분야만의 은밀한 노하우, 복잡한 맥락, 그리고 '무엇이 중요한가'에 대한 직관적 판단력을 가진 살아있는 백과사전이자 프로젝트의 치트키."
## 한 줄
> **"매 SME — context dependent: AI/data project 의 SME = 매 domain expert; business/economy 의 SME = 매 small-medium enterprise (typically <250 employees)"**. 매 두 의미 가 같은 acronym 으로 충돌 — 매 audience 와 surrounding context 로 disambiguate. 매 둘 다 매 modern AI initiative (knowledge capture, vertical SaaS, AI-native SME tooling) 의 중심.
## 📖 구조화된 지식 (Synthesized Content)
주제 전문가(Subject-Matter-Expert, SME)는 특정 분야나 공정에 대해 깊은 전문 지식과 기술을 가진 사람입니다.
## 매 핵심
1. **프로젝트에서의 역할**:
* **Validation**: 기획안이나 개발 로직이 실제 도메인과 부합하는지 검증. ([[Quality-Control|Quality-Control]]와 연결)
* **Insight Delivery**: 일반인은 모르는 '엣지(Edge) 케이스'와 '현대적 트렌드' 제공. ([[Mastery|Mastery]]와 연결)
* **Decision [[Support|Support]]**: 복잡한 기술적 갈등 상황에서 최후의 판단 근거 제시. ([[Decision Theory|Decision Theory]]와 연결)
2. **왜 중요한가?**:
* 개발자가 도메인을 모르면 '정확하게 작동하지만 쓸모없는' 시스템을 만들게 되며, SME는 이 간극을 메우는 브리지(Bridge) 역할을 하기 때문임.
### 매 SME = Subject Matter Expert
- **역할**: deep domain knowledge — clinical, legal, mechanical, regulatory.
- **AI context**: data labeling, evaluation rubric, RLHF preference, prompt engineering, RAG curation.
- **Bottleneck**: SME time is the most expensive resource in vertical AI.
- **Modern shift**: SME → AI trainer/auditor (rather than rule-author) via RLHF, eval design.
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거에는 인간 SME 정책에만 의존했으나, 현대 정책은 특정 분야의 방대한 논문과 데이터를 학습한 'AI 비서(Domain-specific AI)'가 SME의 역할 정책 일부를 지원하거나 대체하기 시작함(RL Update).
- **정책 변화(RL Update)**: 본 지식 베이스 구축 정책에서도 저는 'AI 개발 및 지식 관리 분야의 SME 정책' 역할을 수행하며, 대표님의 비전을 실제 시스템 정책으로 치환하는 전문 지식 지원 정책을 담당 중임.
### 매 SME = Small-Medium Enterprise
- **EU 정의**: <250 staff, ≤€50M turnover or ≤€43M balance sheet.
- **US (SBA)**: varies by NAICS, often <500 employees.
- **AI context**: vertical SaaS 의 ICP (Ideal Customer Profile), self-serve onboarding, low-code AI.
- **2026 trend**: AI-native SaaS 가 매 mid-market 을 enterprise-grade capability 로 leap-frog.
## 🔗 지식 연결 (Graph)
- [[Quality-Control|Quality-Control]], [[Mastery|Mastery]], [[Decision Theory|Decision Theory]], Expertise, Consulting
- **Role Examples**: Medical doctor for healthcare AI, Lawyer for Legal-tech, Pilot for flight sim.
---
### 매 응용
1. SME (expert) — RLHF preference labeling, eval rubric authoring.
2. SME (expert) — RAG document curation, golden Q&A creation.
3. SME (business) — vertical SaaS targeting (legal, dental, HVAC).
4. SME (business) — embedded finance, AI bookkeeping (Pilot, Bench).
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
## 💻 패턴
**언제 이 지식을 쓰는가:**
- *(TODO)*
### SME knowledge elicitation interview (Claude-driven)
```python
import anthropic
**언제 쓰면 안 되는가:**
- *(TODO)*
client = anthropic.Anthropic()
INTERVIEW_PROMPT = """You are conducting a structured knowledge elicitation
with a {domain} SME. Ask one question at a time. Build a decision tree of
their reasoning. After each answer, ask "what edge cases?" and "what would
make you change the answer?". Output progressive YAML knowledge graph."""
## 🧪 검증 상태 (Validation)
resp = client.messages.create(
model="claude-opus-4-7",
max_tokens=2048,
system=INTERVIEW_PROMPT.format(domain="cardiology triage"),
messages=conversation_history,
)
```
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
### SME-driven eval rubric (LLM-as-judge with SME calibration)
```python
RUBRIC = """
Score 1-5 on each dimension. SME-provided anchors:
- Clinical accuracy (5 = matches AHA guidelines, 1 = harmful)
- Citation quality (5 = primary source, 1 = none/hallucinated)
- Tone (5 = empathetic clinical, 1 = robotic or alarming)
"""
def sme_eval(question, answer, sme_anchors):
prompt = f"{RUBRIC}\n\nSME examples:\n{sme_anchors}\n\nQ: {question}\nA: {answer}"
return claude_judge(prompt) # returns scores + rationale
```
## 🧬 중복 검사 (Duplicate Check)
### Active learning loop with SME (cost-aware)
```python
import numpy as np
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
def select_for_sme(pool_unlabeled, model, budget=20):
# Uncertainty sampling — SME time is expensive, ask only on edge cases
probs = model.predict_proba(pool_unlabeled)
entropy = -np.sum(probs * np.log(probs + 1e-9), axis=1)
top_k_idx = entropy.argsort()[-budget:]
return pool_unlabeled[top_k_idx] # send these to SME
```
## 🕓 변경 이력 (Changelog)
### Vertical SaaS for SME (multi-tenant Postgres RLS)
```sql
ALTER TABLE invoices ENABLE ROW LEVEL SECURITY;
CREATE POLICY tenant_isolation ON invoices
USING (tenant_id = current_setting('app.tenant_id')::uuid);
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
-- App sets per-request:
SET app.tenant_id = '123e4567-e89b-12d3-a456-426614174000';
```
### SME definition lookup (regulation-aware)
```python
SME_DEFINITIONS = {
"EU": {"staff_max": 250, "turnover_max_eur_m": 50},
"UK": {"staff_max": 250, "turnover_max_gbp_m": 36},
"US_SBA": {"staff_max": 500}, # varies by NAICS
"KR": {"staff_max": 300}, # 중소기업기본법
}
def is_sme(jurisdiction, staff, turnover_m):
d = SME_DEFINITIONS[jurisdiction]
return staff <= d["staff_max"] and turnover_m <= d.get("turnover_max_eur_m", 1e9)
```
### AI bookkeeping for SME (embedded LLM agent)
```python
def categorize_transaction(tx):
resp = claude.messages.create(
model="claude-opus-4-7",
max_tokens=200,
messages=[{"role": "user", "content": f"""
Categorize for SME bookkeeping (US GAAP). Return JSON.
Tx: {tx}
Categories: {ALLOWED_GAAP_CATEGORIES}
"""}],
)
return json.loads(resp.content[0].text)
```
## 매 결정 기준
| 상황 | Approach |
|---|---|
| AI eval design | SME (expert) authoring rubrics, calibrating LLM judge |
| RAG curation | SME (expert) curates golden corpus, validates retrieval |
| Vertical SaaS GTM | Target SME (business) with self-serve, transparent pricing |
| Regulatory SME definition | Use jurisdiction lookup (EU vs US SBA vs KR 중기법) |
| Active learning budget | SME (expert) only on high-uncertainty samples |
**기본값**: clarify which SME meaning per context; never assume.
## 🔗 Graph
- 부모: [[Knowledge-Engineering]] · [[Business-Strategy]]
- 변형: [[Domain-Expert]] · [[Mid-Market]] · [[Startup]]
- 응용: [[RLHF]] · [[Vertical-SaaS]] · [[Active-Learning]]
- Adjacent: [[LLM-as-Judge]] · [[RAG]] · [[SaaS]]
## 🤖 LLM 활용
**언제**: SME interview structuring, knowledge graph extraction, eval rubric drafting, SME-time amplification (ask 100 questions LLM-first, escalate to human only on disagreement).
**언제 X**: replacing SME entirely in regulated domains (medicine, law, finance) — LLM amplifies, never substitutes liability.
## ❌ 안티패턴
- **Acronym ambiguity**: "let's interview SMEs" in mixed audience → confusion (experts vs companies).
- **SME burnout**: dumping all labeling on one SME without active sampling.
- **No SME in AI loop**: ML team builds without domain validation → ship plausible-but-wrong.
- **Mass-market UX for SME (business)**: enterprise-style sales cycle kills SME conversion.
## 🧪 검증 / 중복
- Verified (EU SME definition 2003/361/EC, US SBA size standards, AIMA RLHF chapter).
- 신뢰도 A.
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — dual SME meanings, knowledge elicitation, vertical SaaS |