Amazon Augmented AI

Amazon Augmented AI (Amazon A2I) enables you to build the workflows required for human review of ML predictions. Amazon A2I brings human review to all developers, removing the undifferentiated heavy lifting associated with building human review systems or managing large numbers of human reviewers.

Developer Guide

Developer Guide

Provides a conceptual overview of Amazon A2I. Offers step-by-step instructions for using AI applications such as Amazon Rekognition, Amazon Textract, or your custom machine learning (ML) models to create workflows required for human review of ML predictions.

HTML PDF

API Reference

Amazon A2I Runtime Model

This API reference includes information about API actions and data types that you can use to interact with Amazon A2I programmatically.

Tutorials and Samples

Using Amazon A2I with Amazon Textract

Provides step-by-step instructions for using Amazon A2I with Amazon Textract.

HTML PDF

Reviewing Unsafe Content with Amazon A2I Using Amazon Rekognition

Provides step-by-step instructions for using Amazon A2I with Amazon Rekognition.

HTML PDF

Crowd HTML Elements Reference

Use HTML elements to create custom worker user interfaces (UIs) for your human review workflows.

HTML PDF

Sample Task User Interfaces (UIs)

A GitHub repository of example task UIs built using HTML crowd elements.

GitHub

Jupyter Notebook Demos

A GitHub repository of example Jupyter Notebooks that demonstrate how to integrate Amazon A2I in machine learning workflows.

GitHub

Related Links

AWS Glossary
Getting Started with AWS
SDKs & Tools
AWS General Reference
AWS Training
AWS Case Studies
AWS Whitepapers