According to aws.amazon.com, AWS has published a three-part blog series demonstrating how to build no-code machine learning workflows using Snowflake, Amazon SageMaker Canvas, and Amazon QuickSight.
Part 1 covered the Snowflake database setup and established the foundational infrastructure for the no-code ML workflow, according to aws.amazon.com.
Part 2 demonstrates data preparation and model building using Amazon SageMaker Canvas, which aws.amazon.com describes as “a visual, no-code machine learning service that enables business analysts and domain experts to build accurate ML models and generate predictions.” According to the source, this section covers connecting directly to Snowflake data sources, transforming and preparing data using Data Wrangler’s visual transformations, and building a fraud detection model using the XGBoost algorithm.
Part 3 focuses on visualizing insights with Amazon QuickSight, now part of Amazon Quick, according to aws.amazon.com. This section covers importing SageMaker Canvas predictions into Amazon QuickSight as a dataset, building analysis dashboards, using generative BI capabilities to surface insights through natural language, and publishing those insights to stakeholders. According to the source, Amazon QuickSight is “a powerful business intelligence service” that enables teams to “build interactive dashboards, perform deep data analysis, and share insights across their organization.”
All three parts were published on August 20, 2026, according to aws.amazon.com.