# 扣子Coze (@95479020377) on xiaohongshu

- id: koinon:creator:xiaohongshu_95479020377
- url: https://koinonlink.com/kol/xiaohongshu/95479020377
- schema_version: 1.3

## Identity
- platform: xiaohongshu
- handle: 95479020377
- platform_url: https://www.xiaohongshu.com/user/profile/66f4cb42000000001e00f796
- website: xhsdiscover://message/userPublicGroupList?user_id=66f4cb42000000001e00f796&username=TA
- country: China
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 23500
- posts_observed: 13
- verified: false
- size_tier: koc

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 0.00787
- best_post_interactions: 185
- measurement_source: cn_posts_max
- measurement_formula: likes + comments + shares (douyin) or likes + comments + collects (xiaohongshu), max over observed posts
- comparable_pool: peak_interactions
- status_note: We have only the single best observed post, so no mean exists. peak_post_engagement_rate is an UPPER BOUND, systematically higher than an average — never compare it against an average rate.
- 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: software
- subcategory: ai_tools
- category_confidence: 0.91
- category_source: derived_from_recent_content
- topics: Coze 3.0及团队版新功能, 金融投研Skill（国信、广发等）, 视频Agent与内容创作, 自媒体Skill与爆款灵感, 新模型接入（Kimi K3、豆包、GLM）, Agent协作与赛事活动
- bio: 新一代 AI 团队，从扣子开始。扣子提供全新的人和 Agent 协作方式，你可以在项目中和多人多 Agent 一起分工协作，推进编程开发、视频创作和行业复杂任务。
官网直达：coze.cn 合作邮箱：[contact removed]

## Audience (inferred)
- status: present
- description: Professionals using Coze to build AI Agents, primarily in financial research & analysis, self-media content creation, and daily workflow automation
- roles: automation
- seniority: practitioner
- pain_points: Fragmented data sources, inconsistent metrics, and rapidly changing market conditions make financial research data organization challenging, Lack of inspiration for viral content and professional writing references in self-media creation, Desire to codify work processes and personal habits into reusable Agents but lack the right tools, Need for quick integration of multiple models and specialized Skills to boost real-world productivity
- posts_analysed: 42
- confidence: 0.75

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

## Quality signals
- authenticity_score: 60
- authenticity_basis: engagement_observed
- credibility_score: 57
- 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_95479020377#7e7873dd] 拥有一个越来越懂你的智能体，是什么体验？ / 最近看到很多人用扣子探索出了不同的 Agent 玩法， (https://www.xiaohongshu.com/user/profile/66f4cb42000000001e00f796)
- [xiaohongshu_95479020377#024ca747] 当一个智能体越来越懂你，会解锁哪些新奇体验？
- [xiaohongshu_95479020377#92a50ec2] ✨长期记忆，是这种体验的开始
- [xiaohongshu_95479020377#f27e5db5] 在扣子里，Agent 可以记住你的偏好、习惯、长期目标和常用规则 / 扣子3.0正式上线：新一代Al团队由此开始 / 扣子 3.0 正式上线了！这一次，扣子带来了全新的人和 Agent 协作方式，并且在扣子网页端、电脑端、手机端三端全量更新，欢迎大家下载体验，你的 AI 团队可以真正进入工作现场了～
- [xiaohongshu_95479020377#aa9c963b] 全新的扣子有 / 你常用的扣子，已经有桌面端了！ / 今天，向大家正式介绍一下扣子桌面端～
- [xiaohongshu_95479020377#94bd13b1] 很多朋友和 Agent 协作，会从“上传文件”开始。
- [xiaohongshu_95479020377#f7461d40] 但真正的工作，往往都发生在电脑里：文件、资料和项目进度都在本地，想让 AI 搭把手，光聊天不够，它得真的能在 / 如何让AI来“参会”？扣子「旁听」限时免费 / 现在，在扣子 App 开启「旁听」，就能让 Agent 从会议开始一起听、一起记、一起理解，带着完整上下文继续推进后续任务。
- [xiaohongshu_95479020377#b6169629] 扣子旁听能帮你做什么👇

## 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=34, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=34, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=34, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=0, 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=0, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=40, 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=0.5, freshness_days=0, method=Starts at 60; interactions-per-follower on collected posts then adds or subtracts (large following with near-zero engagement is penalised heavily). — 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=40, method=llm_partner_fit_classifier + authenticity >= 55 AND fit_score >= 0.45 => A; authenticity >= 40 AND fit_score >= 0.3 => B; else C. authenticity < 30 or a promotional-pattern flag => quarantine. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=40, method=platform_profile

## Freshness
- profile_checked_days_ago: 40
- content_analysed_days_ago: 0
- audience_updated_days_ago: 34

## AI retrieval
- indexing_requests: 1
- user_triggered_requests: 0
- 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_95479020377
- Request removal: https://koinonlink.com/claim?k=xiaohongshu_95479020377
- Terms: https://koinonlink.com/for-ai