---
title: "Comment by Kartik N V J K on \"Observability That Thinks: AI for Pipeline Monitoring\" | Hashnode"
description: "Median/MAD over mean plus stddev is the right call for pipeline metrics, since one giant batch or a retry storm wrecks a z-score but barely moves the median. Th"
url: "https://hashnode.com/posts/ai-pipeline-observability-databricks/6a6b0cc2003aaae589fc7b02/comment/6a6bad8541fb5fc9e66b97da"
---

[Discussion](https://hashnode.com/posts/ai-pipeline-observability-databricks/6a6b0cc2003aaae589fc7b02)

Comment [Observability That Thinks: AI for Pipeline Monitoring](https://hashnode.com/posts/ai-pipeline-observability-databricks/6a6b0cc2003aaae589fc7b02)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Jul 30](https://hashnode.com/posts/ai-pipeline-observability-databricks/6a6b0cc2003aaae589fc7b02/comment/6a6bad8541fb5fc9e66b97da)

Median/MAD over mean plus stddev is the right call for pipeline metrics, since one giant batch or a retry storm wrecks a z-score but barely moves the median. The same-weekday baseline is the detail I'd steal, because a Monday reprocessing job looks nothing like a Sunday and averaging across the week hides both. How do you handle holidays and one-off backfills, do they poison the trailing-8 window, or do you exclude them explicitly?