community-automations/vector-anomaly

研究與情報

PublicClaude 子代理

向量異常偵測

在大規模資料中，那筆預示著詐騙或資料源異常的怪異紀錄，看起來跟周圍數百萬筆資料毫無二致。這套流程透過相似度而非規則來找出異常值。

sonnet1 週PineconePythonscikit-learnKafka
ClaudeClaude
ROI for
README.md

為什麼選擇此子代理

在大規模資料中，那筆預示著詐騙或資料源異常的怪異紀錄，看起來跟周圍數百萬筆資料毫無二致。這套流程透過相似度而非規則來找出異常值。

每筆紀錄都會經過向量化並建立索引；KNN 查詢會測量它與鄰近資料的距離，任何超過閾值的紀錄都會被標記。被標記的資料點會連同其最近鄰的紀錄一起回傳，為下游的代理程式提供判斷脈絡，分辨它究竟是不是真正的異常。

運作方式

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

輸出範例

json
// Sample output
// (generated when the pipeline finishes)

Embed each record, run KNN, and flag points whose neighbor distance exceeds the threshold, with neighbor context attached.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.