# Did You Know SageMaker Unified Studio Can Now Spot Data Anomalies Without Thresholds?

Hey, it's Shiichan! Today I found a data quality update for Amazon SageMaker Unified Studio, so let me walk you through it.

## What was announced?

According to AWS's What's New, Amazon SageMaker Unified Studio now supports **data profiling** and **anomaly detection**, powered by AWS Glue Data Quality under the hood. Data stewards, engineers, and analysts can now generate statistical profiles of their data to understand its shape and completeness, and track how those statistics change over time.

## Why it matters

The more complex your data pipelines get, the harder it is to shake the worry that "this table might have picked up weird values without me noticing." Until now, catching anomalies meant defining your own thresholds or rules — which takes effort, and those rules can go stale quickly if the expected range of values shifts over time. That's exactly why anomaly detection that doesn't require you to set your own thresholds is such a big deal.

## What changes

Data engineers and analysts can now notice "hey, this data looks off" without having to build rules up front. Being able to keep an eye on data quality more easily and continuously is the real win here.

## Dive Deep

Two kinds of data are covered:

- **Data at rest in catalog tables**
- **Data in transit within Visual ETL jobs** (via the Evaluate Data Quality transform)

For catalog tables, there's now a dedicated **Data profile tab** that computes dataset-level and column-level statistics, either on demand or on a schedule. As the profile history builds up, it automatically forms a baseline of "what's normal," and data points that fall outside that predicted range get flagged.

On the Visual ETL side, the same profiling statistics and anomaly detection show up on the results page of any job that includes an Evaluate Data Quality transform.

This feature is available in every AWS Region where Amazon SageMaker Unified Studio is available. Check the official documentation for more details.

## Wrap-up

- SageMaker Unified Studio now supports data profiling and anomaly detection, powered by AWS Glue Data Quality
- It covers both data at rest in catalog tables and data in transit within Visual ETL jobs
- The Data profile tab supports on-demand and scheduled profiling, and automatically builds a baseline from the stats to flag anomalies
- Great for data engineers and analysts who want continuous data quality monitoring without hand-crafting thresholds and rules!