這個 AI 代理會讀取每則回饋,依類型分流:Bug 和請求以使用者的原話建立成 Linear issue,讚美會被記錄,流失風險則在 Slack 通知客戶負責人。沒有有價值的訊息會被漏掉,產品團隊終於看見客戶真正在要什麼。
運作方式
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.
將每筆回饋分類為錯誤回報、新功能建議、讚賞或流失風險。
pending
針對錯誤回報與新功能建議,使用使用者的原話建立或更新 Linear 上的對應 Issue。
pending
將有流失風險的回饋,立刻透過 Slack 轉報給負責帳號經理。
pending
輸出範例
json
// Sample output
// (generated when the pipeline finishes)
Classify a feedback item into bug, feature, praise, or churn risk, and return the routing target and a short rationale.
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.