# 南道山| AI Agent 实验室 (@950140946) on xiaohongshu

- id: koinon:creator:xiaohongshu_950140946
- url: https://koinonlink.com/kol/xiaohongshu/950140946
- schema_version: 1.4

## Identity
- platform: xiaohongshu
- handle: 950140946
- platform_url: https://www.xiaohongshu.com/user/profile/59de6f9751783a268b0fa112
- country: China
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 3500
- posts_observed: 7
- verified: false
- size_tier: nano

## Engagement
- status: not_collected
- status_note: Engagement has not been collected for this creator yet. This is a gap in our collection, NOT a statement that the creator has no engagement. Follower count is known, so it is measurable.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: finance
- subcategory: investing
- category_confidence: 0.9
- category_source: derived_from_recent_content
- topics: AI Agent投研团队搭建, 缠论与艾略特波浪Skill, DCF估值与投行模型蒸馏, 量化策略回测与数据源, 财报排雷与股权尽调Skill
- bio: RED ID: 950140946

## Audience (inferred)
- status: present
- description: Individual investors and quantitative professionals using AI Agents for quantitative trading, investment research, and stock valuation
- roles: automation
- seniority: practitioner
- pain_points: Manually reading financial statements and conducting valuations is time-consuming and error-prone, Backtesting platforms have limited quotas and restricted APIs, preventing local experimentation, Technical analysis methods like Chan Theory and Elliott Wave are highly subjective, leading to self-deception, Quantitative strategies look great in backtests but fail to perform consistently in live trading
- posts_analysed: 40
- confidence: 0.75

## Commercial (inferred)
- audience_buyer_fit: 0.8
- promotion_intent: 0.9
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 58
- authenticity_basis: platform_default
- credibility_score: 38
- flagged_for_review: false
- koinon_bd_grade: A — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [xiaohongshu_950140946#e726477a] 花费上亿token，终于炼化出了缠论skill！ / 缠论，A 股最出名、也最常被骂"玄学"的技术分析。分型、笔、线段、中枢、背驰、三类买卖点……概念一大堆，学起来劝退，用起来又最容易自欺：多少人把"MACD 底背离"当买点、把"突破"当三买，结果在震荡 / 公开艾略特波浪交易skill ，让交易技术平权 / 「艾略特波浪交易研究」是一款面向股票、指数及其他流动市场的技术结构研究 Skill。它把常被主观化的“数浪”过程，整理成一套可复核的分析流程：先冻结数据截止时间，再识别已经确认的结构拐点；先生成多种可 / 蒸馏了全球顶级对冲基金投研 Agent / (https://www.xiaohongshu.com/user/profile/59de6f9751783a268b0fa112)
- [xiaohongshu_950140946#148db684] 官方给它的定位非常直接：让投资人把原本需要数小时的探索性研究，压缩到分钟级完成。
- [xiaohongshu_950140946#f6d3ba54] 但真正让我震撼 / 全球顶级对冲基金之一，桥水到底是怎么搭建投研 Agent 的？
- [xiaohongshu_950140946#a8d4ee17] 真正值得关注的，不是它用了哪个大模型，而是桥水把投资研究做成了一套可编译、可验证、可持续学习的系统：Research Agent 负 / 蒸馏了全球顶级对冲基金桥水投研Agent / 爆火的机构投资级股票估值Skill 开源了 / #REDSkill[话题]# #AI工作流[话题]# #数据分析[话题]# #财务分析[话题]# #商业分析[话题]# #量化[话题]# #量化投资[话题]# #股票[话题]#  #估值[话题]# # / 输入生日与目标年份，数境会生成主宰数、生日数、九宫图与周期观察，并把年度主题拆成可以实践的小行动。所有计算都能复算，来源与
- [xiaohongshu_950140946#d465511a] #vibe / 你的生日，藏着怎样的数字结构？

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.75, freshness_days=71, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=71, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=71, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=71, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=71, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=90, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.25, freshness_days=71, method=Fixed value 58, pending engagement collection. Not a measurement. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=90, method=llm_partner_fit_classifier + fit_score >= 0.5 => A; >= 0.35 => B; else C. authenticity is not an input. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=90, method=platform_profile

## Freshness
- profile_checked_days_ago: 90
- content_analysed_days_ago: 71
- audience_updated_days_ago: 71

## AI retrieval
- indexing_requests: 7
- user_triggered_requests: 1
- last_user_triggered_day: 2026-09-01
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=xiaohongshu_950140946
- Request removal: https://koinonlink.com/claim?k=xiaohongshu_950140946
- Terms: https://koinonlink.com/for-ai