AWS: Lots of Excel tables in companies – GenAI applications can help

Amazon calls its new service App Studio, which allows users to create business applications using generative AI. AWS is clearly aiming the service at regular users, not developers – although users should have a technical understanding, they need not have any programming experience. The finished web application should be ready to use after just a few minutes.

Advertisement

First GenAI, then drag-and-drop and low code

To get started, you choose a data source: it can be an AWS service, connectors for S3, Aurora, DynamoDB & Co are already available. The same applies to Salesforce; according to the announcement, App Studio also integrates hundreds of third-party services via API. Those responsible can already install connectors for their employees, which are then available to the whole group. How these connections work should not concern users – let AI take care of the integration.

Then, in App Studio, as in other GenAI services, users enter a prompt that describes the finished application. The system then translates this input into a detailed description that can be further edited. App Studio then produces an initial demo. Here the user gets a GUI in which he can adjust the structure of the program using drag-and-drop. Additional input and output fields can also be added here.

In addition, users can further customize the data sources and storage location for the application’s data here. Finally, App Studio also provides an overview of the application’s logic, which can also be further edited. It also does not require any programming knowledge: instead, AWS provides a low-code environment in which users can drag and drop individual elements into the program flow and customize them according to their needs using simple commands.

App Studio vs. Excel Spreadsheet

Once you have completed your application, there are three more stages: In the development environment it is in a sandbox at this point, it is not yet connected to real data sources; instead, App Studio generates the appropriate data so users can test your application at this point. The subsequent testing stage has access to the set data sources, staff can try out the application at this point and provide feedback. Once this is complete, publishing to the production environment is done.

However, in its examples, AWS also shows that it is not enough to describe any application of AI on a single sign – knowledge of your own technical infrastructure is required. Accordingly, Amazon is not targeting its new App Studio to regular corporate users; rather, project managers should replace processes for which Excel tables were previously used, for example, with such applications.

Obviously, this goal is not new: low-code tools come with similar promises. However, AWS sees them as much more restrictive. The barriers to entry are much higher, users have to acquire platform-specific knowledge and IT managers usually block such applications for security reasons. It is not clear from the announcement why things should be different with App Studio.

Highly used applications are becoming more expensive

As with any cloud service, the question of fees remains: Amazon relies on a model typical for the cloud – customers pay for what they actually use. Accordingly, creating company applications using App Studio is free, instead, AWS charges for the time users spend in the application; this should save customers up to 80 percent in costs compared to low-code tools. Amazon does not provide any information on how this was calculated.

Initially, App Studio is in preview in the US West (Oregon) region. AWS has already made the GenAI service available to large companies and institutions. More details can be found In the announcement on Amazon,

(For)

C++20: Cooperative interruption of a thread with callback