# Funmaker (@Funmaker) on wechat

- id: koinon:creator:wechat_funmaker
- url: https://koinonlink.com/kol/wechat/Funmaker
- schema_version: 1.4

## Identity
- platform: wechat
- handle: Funmaker
- platform_url: https://weixin.sogou.com/weixin?type=1&query=Funmaker
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- posts_observed: 16
- verified: false
- size_tier: nano

## Engagement
- status: not_measurable_on_platform
- status_note: This platform publishes no follower count, so an engagement RATE has no denominator here. No amount of further collection can produce one — it is a property of the platform, not a gap in our data.
- 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: 0.95
- category_source: derived_from_recent_content
- topics: CrewAI多智能体协作, ChromaDB向量数据库与Agent记忆, vLLM高性能推理引擎, Ollama本地部署与量化, LoRA模型微调

## Audience (inferred)
- status: present
- description: AI developers and Agent builders focused on local deployment, large model optimization, and multi-agent system construction
- roles: automation
- seniority: practitioner
- pain_points: Slow local inference and high GPU memory usage make it hard to run smoothly on consumer-grade hardware, AI Agents lack long-term memory and persistent storage, making context management challenging, Building multi-agent collaboration frameworks is complex, with difficulty in achieving task division and integration with enterprise systems, High barriers to fine-tuning and quantized deployment of open-source models, with limited production-ready guidance available
- posts_analysed: 7
- confidence: 0.4

## 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: platform_default
- 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
- [wechat_funmaker#3a687ede] AI教程第21期:CrewAI多智能体协作——让多个AI像团队一样分工合作 (https://weixin.sogou.com/weixin?type=1&query=Funmaker)
- [wechat_funmaker#f6f467c6] AI教程第27期:给AI Agent装上长期记忆——用ChromaDB实现向量数据库持久化
- [wechat_funmaker#91b36d25] AI教程第18期:vLLM——高性能大模型推理引擎,从Ollama进阶到生产级部署
- [wechat_funmaker#c46bfc95] AI教程第30期:vLLM让本地大模型推理速度翻倍——告别Ollama的“假快”
- [wechat_funmaker#57d88c64] AI教程第28期:把ChromaDB记忆Agent接入企业微信——打造专属AI同事
- [wechat_funmaker#0402a1c0] AI教程第20期:LoRA微调入门,用一张显卡把开源模型驯化成你的专属AI
- [wechat_funmaker#a05f8b61] AI教程第29期:Ollama模型量化实战——让7B模型在8GB笔记本上流畅运行
- [wechat_funmaker#3f61ca9f] AI教程第26期:Ollama Function Calling + FastAPI——10分钟搭建AI Agent微服务

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

- audience.description: source_type=ai_inferred, confidence=0.4, freshness_days=76, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.4, freshness_days=76, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.4, freshness_days=76, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=63, 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=63, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=51, 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=63, method=Fixed value 60. This platform exposes no public follower count, so no authenticity heuristic is run at all. The number is a placeholder, 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=51, 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=51, method=platform_profile

## Freshness
- profile_checked_days_ago: 51
- content_analysed_days_ago: 63
- audience_updated_days_ago: 76

## AI retrieval
- indexing_requests: 11
- 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=wechat_funmaker
- Request removal: https://koinonlink.com/claim?k=wechat_funmaker
- Terms: https://koinonlink.com/for-ai