Hello Cloud Gurus. And welcome to another episode of AWS this week, where we process the goings on of the last week to bring you only the finest AWS news. SageMaker receives a whole load of updates, Secrets Manager, now sports rotation windows, Step Functions Local introduces mock responses, Amazon Fraud Detector now includes prediction explanations, and Amazon Lex supports alternate transcriptions. I'm Stephen Sennett here to bring you another episode of AWS this week, SageMaker continues to be a major area of focus for AWS, with several updates being released this week. SageMaker autopilot, which helps you build train and tune your models has had a couple of updates - Autopilot now supports Apache parquet files, and the maximum size for dataset have been raised from 10 gigabytes up to 100 gigabytes.

You can also lodge requests with AWS to consume even larger datasets through autopilot. SageMaker Data Wrangler, which helps streamline the processing for machine learning has also added supports for the popular JSON and ORC data formats, along with some new transformation capabilities. SageMaker jumpstart, which connects you to popular collections of machine learning models can now deploy their endpoints into a custom VPC and encrypt their data using custom KMS settings. These are really important considerations for large enterprise customers with complex architectures. AWS Secrets Manager now supports rotation windows for secrets that it manages.

Rotating secrets is crucial to ensuring our applications remain secure. Even when managed by a service like Secrets Manager, there's still opportunities for compromise. The challenge is that when we rotate our secrets, everything doesn't happen exactly the same time. There may be short periods where the application using these secrets don't match and cause the calls to be denied during the rotation. Rotation windows allow us to set specific times when we'd like our secrets to rotate during an expected maintenance window.

This means if we do have issues for a short period of time, that we can ensure it won't impact as many users. If your solution supports it, using alternating secrets in your rotation strategy can ensure higher reliability. But solutions where only a single secret is used, having a rotation window can make your solution more reliable. Step Functions has been getting a lot more love over the last few months. And now we have the latest update with the release of service integration response mocking for Step Functions Local. Last year,

AWS upgraded step functions to support more than 200 AWS services and thousands of API actions. The ability to mock the responses from these service integrations during local testing means you can more thoroughly test your Step Functions in a local development environment. Mock responses allow us to simulate the interactions we would have with these service integrations. Now these will only get us so far and as the excellent blog post by AWS points out, there are limitations such as Step Functions Local not validating the format of mock responses, but this does solve an existing gap when it comes to development of step functions. And overall I expect step functions are only going to get more powerful and more popular over time. Have you used step functions local previously,

and will this change your impression of it? Let us know in the comments. Fraud Detector has received a really interesting update with the addition of the new prediction explanations, like many machine lighting products, Fraud Detector has given you a list of results, which indicate the risk for potentially fraudulent activity. That's cool, but there's really no way to understand why it was determined to be fraudulent. It's the machine equivalent of asking someone a question and then responding with, "I just know." The inclusion of the new prediction explanations helps provide details into which particular variables impacted the prediction.

Knowing the underlying factors behind a prediction, both helps analysts assess the claim and architects develop more proactive countermeasures, just more proof that Amazon is continuing to invest in their managed machine learning services. This feature is already available for models generated after June 30th, 2021. If a model was generated before then, you'll need to retrain your model to access this feature. And if you're interested in exploring Amazon Fraud Detector, there's a great link to a talk from reinvent 2020 demonstrating into description below. Amazon Lex has released a new feature, allows multiple transcripts and confidence scoring of users' speech input.

We've all had irritating experiences with voice interfaces where you say one thing and the system interprets it as another. This is nearly as much of a frustration for the people who build these systems as the people who use them. The beauty of this new feature with Amazon Lex is that offers multiple suggestions of how to transcriber along with confidence scoring. With the confidence scoring in alternate interpretations, you can make your conversational interface a lot more robust either by asking for clarification when it's not very sure or by selecting a more likely alternate interpretation. Anytime you're working with voice interfaces, it always pays to take the time to refine it for a smooth user experience.

If you're using Lex speech input, this could be worth exploring as a refinement. If you're enjoying our content, consider checking out our free plan on our website, which includes access to rotating content, so you'll get something new every month. So until next time go forth and learn all the things and as always keeping awesome Cloud Gurus.