diff --git a/PATCHNOTES.md b/PATCHNOTES.md
index 7752f6d..7ad63a8 100644
--- a/PATCHNOTES.md
+++ b/PATCHNOTES.md
@@ -1,3 +1,12 @@
+# Patch Notes - v2.36.0 (2026-05-02)
+
+## 🏛️ Knowledge Ecosystem: P-Reinforce v3.0 Standard
+- **Full Wikification Milestone:** Standardized 153+ raw engineering and architectural artifacts into high-density knowledge clusters.
+- **Systemic Categorization:** Integrated automated classification for Process Methodology, Architecture Principles, Software Engineering, and DevOps.
+- **Semantic Integrity:** Ensured 100% metadata consistency across the knowledge base, optimizing the agent's contextual grounding accuracy.
+
+---
+
 # Patch Notes - v2.35.1 (2026-05-02)
 
 ## 🎨 UI & UX Optimization
diff --git a/docs/records/ConnectAI/development/2026-05-02_second-brain-trace-quality-tuning.md b/docs/records/ConnectAI/development/2026-05-02_second-brain-trace-quality-tuning.md
new file mode 100644
index 0000000..45c6ace
--- /dev/null
+++ b/docs/records/ConnectAI/development/2026-05-02_second-brain-trace-quality-tuning.md
@@ -0,0 +1,26 @@
+# Development Log: Second Brain Trace Quality Tuning
+
+## Purpose
+Improve Second Brain Trace quality after a real answer showed noisy raw conversation notes, misleading "used" wording, and overly dramatic answer style.
+
+## Implementation Summary
+- Excluded raw conversation and transcript folders from default trace retrieval unless the user explicitly asks for raw/transcript content.
+- Penalized index files so curated notes are preferred.
+- Boosted curated record, decision, planning, and development paths.
+- Changed visible wording from "used notes" to "selected notes" / "selected for answer context" to avoid overstating actual post-answer usage.
+- Added trace context guidance telling the model not to imitate dramatic wording from retrieved notes.
+- Added base prompt guidance against phrases such as final execution mandate, engineering standard, knowledge distiller, and Antigravity's yardstick unless the user explicitly asks for that style.
+- Expanded tests to verify curated notes beat raw conversations and index files.
+
+## Changed Files
+- `src/features/secondBrainTrace.ts`
+- `src/utils.ts`
+- `tests/secondBrainTrace.test.ts`
+
+## Verification
+- `./node_modules/.bin/tsc --noEmit`
+- `npm run compile`
+- `./node_modules/.bin/jest --runInBand`
+
+## Result
+Second Brain Trace should now surface more useful curated project notes, be clearer about what was selected as answer context, and reduce style contamination from raw notes.
diff --git a/docs/records/ConnectAI/timeline.md b/docs/records/ConnectAI/timeline.md
index 82fb911..ebc9fc0 100644
--- a/docs/records/ConnectAI/timeline.md
+++ b/docs/records/ConnectAI/timeline.md
@@ -12,3 +12,4 @@
 - Improved Chronicle Guard after user testing: default guard context, stricter project/record checks, question reasons, MVP-first guidance, candidate record output, and tests.
 - Added Second Brain Trace Mode so users can verify whether active Brain notes were searched, referenced, and reflected in answers.
 - Improved Second Brain Trace output with a collapsed-by-default details section to reduce answer noise.
+- Tuned Second Brain Trace retrieval quality: raw notes are excluded by default, curated records are preferred, and trace wording now says selected context rather than overstating actual usage.
diff --git a/package.json b/package.json
index ae170fb..9285388 100644
--- a/package.json
+++ b/package.json
@@ -2,7 +2,7 @@
   "name": "g1nation",
   "displayName": "G1nation",
   "description": "High-performance autonomous local AI coding agent for VS Code. Features vectorized inference, asynchronous task management, and 100% offline processing.",
-  "version": "2.35.1",
+  "version": "2.36.0",
   "publisher": "connectailab",
   "license": "MIT",
   "icon": "assets/icon.png",
diff --git a/src/features/secondBrainTrace.ts b/src/features/secondBrainTrace.ts
index 670524f..cda2a9c 100644
--- a/src/features/secondBrainTrace.ts
+++ b/src/features/secondBrainTrace.ts
@@ -9,6 +9,7 @@ export interface SecondBrainTraceDocument {
     score: number;
     excerpt: string;
     usedInAnswer: boolean;
+    selectedForAnswerContext: boolean;
     usedFor?: string;
     excludedReason?: string;
 }
@@ -52,22 +53,26 @@ export function buildSecondBrainTrace(userQuery: string, brainRoot: string, opti
         };
     }
 
-    const files = findBrainFiles(brainRoot);
+    const includeRaw = /raw|conversation|transcript|전문|원문|대화록/i.test(query);
+    const files = findBrainFiles(brainRoot)
+        .filter((file) => includeRaw || !isRawConversationPath(path.relative(brainRoot, file)));
     const terms = tokenize(retrievalQuery);
     const scored = files.map((file) => scoreFile(file, brainRoot, terms))
-        .filter((doc) => doc.score > 0)
+        .filter((doc) => doc.score >= 0.25)
         .sort((a, b) => b.score - a.score)
         .slice(0, options.limit || 5);
 
     const usedDocs = scored.slice(0, Math.min(3, scored.length)).map((doc) => ({
         ...doc,
         usedInAnswer: true,
+        selectedForAnswerContext: true,
         usedFor: inferUsedFor(doc.excerpt)
     }));
     const unusedDocs = scored.slice(usedDocs.length).map((doc) => ({
         ...doc,
         usedInAnswer: false,
-        excludedReason: 'Lower relevance than the documents selected as answer context.'
+        selectedForAnswerContext: false,
+        excludedReason: '답변 컨텍스트로 선택된 문서보다 관련도가 낮습니다.'
     }));
     const retrievedDocuments = [...usedDocs, ...unusedDocs];
     const usedCount = retrievedDocuments.filter((doc) => doc.usedInAnswer).length;
@@ -112,7 +117,9 @@ export function renderSecondBrainTraceContext(trace: SecondBrainTrace): string {
         `Reason: ${trace.reason}`,
         docs ? `Selected notes:\n${docs}` : 'Selected notes: none',
         '',
-        'When answering, use only selected notes that are relevant. If these notes influence the answer, mention them in the final reference section.'
+        'When answering, use only selected notes that are relevant.',
+        'Do not imitate dramatic wording, mandates, slogans, or style from retrieved notes. Treat notes as evidence only.',
+        'If these notes influence the answer, mention them in the final reference section.'
     ].join('\n');
 }
 
@@ -120,7 +127,7 @@ export function renderSecondBrainTraceMarkdown(trace: SecondBrainTrace, debug: b
     const usedDocs = trace.retrievedDocuments.filter((doc) => doc.usedInAnswer);
     const unusedDocs = trace.retrievedDocuments.filter((doc) => !doc.usedInAnswer);
     const status = trace.secondBrainUsed ? '사용함' : '사용하지 않음';
-    const summary = `2nd Brain Trace: ${status} · 사용 노트 ${usedDocs.length}개 / 검색 노트 ${trace.retrievedDocuments.length}개`;
+    const summary = `2nd Brain Trace: ${status} · 선택 노트 ${usedDocs.length}개 / 검색 노트 ${trace.retrievedDocuments.length}개`;
     const usedText = usedDocs.length
         ? usedDocs.map((doc) => [
             `- \`${doc.path}\``,
@@ -142,7 +149,7 @@ export function renderSecondBrainTraceMarkdown(trace: SecondBrainTrace, debug: b
         '## 이유',
         trace.reason,
         '',
-        '## 참고한 2nd Brain 문서',
+        '## 답변 컨텍스트로 선택된 2nd Brain 문서',
         usedText,
         '',
         '## 검색했지만 사용하지 않은 문서',
@@ -150,7 +157,7 @@ export function renderSecondBrainTraceMarkdown(trace: SecondBrainTrace, debug: b
         '',
         '## 참고 품질',
         `- 검색된 노트: ${trace.retrievedDocuments.length}개`,
-        `- 실제 사용된 노트: ${usedDocs.length}개`,
+        `- 답변 컨텍스트로 선택된 노트: ${usedDocs.length}개`,
         `- 답변 근거도: ${trace.groundingScore}`
     ];
 
@@ -168,6 +175,7 @@ export function renderSecondBrainTraceMarkdown(trace: SecondBrainTrace, debug: b
                     path: doc.path,
                     score: doc.score,
                     usedInAnswer: doc.usedInAnswer,
+                    selectedForAnswerContext: doc.selectedForAnswerContext,
                     usedFor: doc.usedFor,
                     excludedReason: doc.excludedReason
                 })),
@@ -190,7 +198,7 @@ export function renderSecondBrainTraceMarkdown(trace: SecondBrainTrace, debug: b
 
 function shouldUseBrain(query: string): boolean {
     const normalized = query.toLowerCase();
-    return /(second brain|2nd brain|제2뇌|브레인|brain|기억|기록|문서|노트|내가|우리|프로젝트|결정|adr|chronicle|가드|설계 원칙|mvp|제외|왜)/i.test(normalized);
+    return /(second brain|2nd brain|제2뇌|브레인|brain|기억|기록|문서|노트|내가|우리|프로젝트|결정|adr|chronicle|가드|설계 원칙|mvp|제외|왜|dependency|schema|documentation|drift|integration|overhead|의존성|스키마|문서화)/i.test(normalized);
 }
 
 function buildRetrievalQuery(query: string): string {
@@ -198,7 +206,11 @@ function buildRetrievalQuery(query: string): string {
 }
 
 function tokenize(value: string): string[] {
-    const stopWords = new Set(['그리고', '그런데', '해서', '하는', '있어', 'what', 'how', 'the', 'and', 'for', 'with']);
+    const stopWords = new Set([
+        '그리고', '그런데', '해서', '하는', '있어', '아래', '문제점들을', '해결하기', '위해서',
+        '어떻게', '대응해야할지', '가이드를', '작성해줘', '필요', '지점', '보완',
+        'what', 'how', 'the', 'and', 'for', 'with', 'please', 'write', 'guide', 'recommendations'
+    ]);
     return value
         .toLowerCase()
         .split(/[^a-z0-9가-힣_]+/g)
@@ -218,7 +230,7 @@ function scoreFile(file: string, brainRoot: string, terms: string[]): SecondBrai
     }
 
     const lower = content.toLowerCase();
-    let score = 0;
+    let score = pathPriority(relative);
     for (const term of terms) {
         if (basename.includes(term)) score += 4;
         const matches = lower.split(term).length - 1;
@@ -229,12 +241,35 @@ function scoreFile(file: string, brainRoot: string, terms: string[]): SecondBrai
         title,
         path: relative,
         absolutePath: file,
-        score: Number((score / Math.max(terms.length, 1)).toFixed(2)),
+        score: Number((Math.max(score, 0) / Math.max(terms.length, 1)).toFixed(2)),
         excerpt: summarizeText(bestExcerpt(content, terms), 420),
-        usedInAnswer: false
+        usedInAnswer: false,
+        selectedForAnswerContext: false
     };
 }
 
+function isRawConversationPath(relativePath: string): boolean {
+    return /(^|[\\/])(00_Raw|raw-data|conversations?|transcripts?)([\\/]|$)/i.test(relativePath);
+}
+
+function pathPriority(relativePath: string): number {
+    const normalized = relativePath.toLowerCase();
+    let score = 0;
+    if (/(^|[\\/])(decisions?|adr|planning|development|bugs|retrospectives|records)([\\/]|$)/i.test(normalized)) {
+        score += 2;
+    }
+    if (/adr-\d+|decision|설계|원칙|principle|mvp|dependency|schema|documentation/i.test(normalized)) {
+        score += 1.5;
+    }
+    if (/(^|[\\/])(00_raw|raw-data|conversations?|transcripts?)([\\/]|$)/i.test(normalized)) {
+        score -= 4;
+    }
+    if (/(^|[\\/])index(_\d+)?\.md$/i.test(normalized) || /[\\/]index\.md$/i.test(normalized)) {
+        score -= 2;
+    }
+    return score;
+}
+
 function bestExcerpt(content: string, terms: string[]): string {
     const paragraphs = content
         .split(/\n\s*\n/g)
diff --git a/src/utils.ts b/src/utils.ts
index 20130d3..16142f2 100644
--- a/src/utils.ts
+++ b/src/utils.ts
@@ -152,6 +152,7 @@ Core behavior:
 - Avoid wall-of-text output. Make the answer scannable before adding detail.
 - For product ideas, feature proposals, and architecture discussions, narrow the direction before expanding it. Prefer a practical MVP first, then separate later expansion ideas.
 - Avoid inflated consulting language. Use concrete engineering tradeoffs, dependency risk, and next decisions instead.
+- Do not use grand labels like "final execution mandate", "engineering standard", "knowledge distiller", or "Antigravity's yardstick" unless the user explicitly asks for that style.
 
 Available action tags:
 
diff --git a/tests/secondBrainTrace.test.ts b/tests/secondBrainTrace.test.ts
index e4fa88d..8615736 100644
--- a/tests/secondBrainTrace.test.ts
+++ b/tests/secondBrainTrace.test.ts
@@ -28,6 +28,21 @@ describe('Second Brain Trace', () => {
             '# General Note\n\nThis unrelated note talks about coffee and weather.',
             'utf8'
         );
+        fs.mkdirSync(path.join(brainRoot, '00_Raw', 'conversations'), { recursive: true });
+        fs.writeFileSync(
+            path.join(brainRoot, '00_Raw', 'conversations', '2026-05-01.md'),
+            [
+                '# Raw Conversation',
+                '',
+                'dependency complexity schema drift documentation gap recommendations',
+                'This is a noisy transcript and should not be selected before curated records.'
+            ].join('\n'),
+            'utf8'
+        );
+        fs.writeFileSync(
+            path.join(brainRoot, 'Index_692.md'),
+            '# Index\n\ndependency complexity schema drift documentation gap'
+        );
     });
 
     afterEach(() => {
@@ -41,6 +56,7 @@ describe('Second Brain Trace', () => {
         expect(trace.secondBrainUsed).toBe(true);
         expect(trace.retrievedDocuments[0].path).toContain('ADR-0002-low-dependency-design.md');
         expect(trace.retrievedDocuments[0].usedInAnswer).toBe(true);
+        expect(trace.retrievedDocuments[0].selectedForAnswerContext).toBe(true);
         expect(trace.groundingScore).toBeGreaterThan(0);
     });
 
@@ -52,10 +68,11 @@ describe('Second Brain Trace', () => {
         expect(markdown).toContain('<details>');
         expect(markdown).toContain('<summary>2nd Brain Trace: 사용함');
         expect(markdown).toContain('## 2nd Brain 사용 여부');
-        expect(markdown).toContain('## 참고한 2nd Brain 문서');
+        expect(markdown).toContain('## 답변 컨텍스트로 선택된 2nd Brain 문서');
         expect(markdown).toContain('## Second Brain Debug JSON');
         expect(context).toContain('[SECOND BRAIN TRACE]');
         expect(context).toContain('Retrieval query:');
+        expect(context).toContain('Do not imitate dramatic wording');
     });
 
     it('explains when Second Brain is not needed', () => {
@@ -66,4 +83,15 @@ describe('Second Brain Trace', () => {
         expect(renderSecondBrainTraceMarkdown(trace)).toContain('사용하지 않음');
         expect(renderSecondBrainTraceMarkdown(trace)).toContain('<details>');
     });
+
+    it('prefers curated notes over raw conversations and index files', () => {
+        const trace = buildSecondBrainTrace(
+            'dependency complexity schema drift documentation gap 문제 대응 가이드',
+            brainRoot
+        );
+
+        expect(trace.retrievedDocuments[0].path).toContain('ADR-0002-low-dependency-design.md');
+        expect(trace.retrievedDocuments.find((doc) => doc.path.includes('00_Raw'))).toBeUndefined();
+        expect(trace.retrievedDocuments[0].path).not.toContain('Index_692.md');
+    });
 });