DataRobot Introducing No Code App Building Blog V2.0 Background 2

Introducing No-Code AI Apps

June 15, 2021
by
· 4 min read

Announced at our recent AI Experience ‘21 conference and now in Release 7.1, we are thrilled to introduce No-Code AI Apps. This allows any user, regardless of their technical expertise, to quickly turn a deployed model into a rich AI application without requiring any coding. This means that any predictive model can become an AI app in minutes, putting the power of DataRobot directly in the hands of your front line decision-makers.

With simple, customizable drag-and-drop components, users can easily configure an app in any way they need. For example, app builders can choose features they want users to input and be displayed in the UI, the scenarios they want end users to explore, and the visual insights that support the decision-making use case. And thanks to how simple it is to socialize AI apps with the business community, through a variety of sharing options, scaling insights to drive AI powered decisions is easier than ever before. 

Getting Started

When you log in to DataRobot 7.1, you will notice a new UI called Current Applications when you click the Applications option at the top of your screen. From here, you will see all of the existing AI apps, as well as the relevant metadata associated with them. 

pasted image 0 18

You can take action on them as either a consumer or a builder, depending on your level of access to a given application.

Configuring Widgets

Thanks to the AI App Builder being entirely no-code, builders of any technical level can simply log in using Edit mode and begin dragging, dropping, and configuring the customizable widgets, as shown in the screenshot below. 

unnamed 1

With a variety of widget options, including new and improved versions of the Predictor, Optimizer, and What-if Scenario apps, you can build powerful applications with in-depth insights for the decision makers in your organization to use. 

Sharing applications on any device is also easy. Responsive design enables support for apps on desktops, laptops, tablets, and mobile devices.

pasted image 0 19

The simplicity with how you build, deploy, and share AI apps means that you can iterate and improve on your ML project and model results to drive business decisions more effectively and efficiently than ever before.

Trusted and Explainable AI That Is Close to Your Business

The assets you build with DataRobot’s No-Code AI Apps come with built-in explainability tools that app builders and decision-makers can use to dig into the details and explain how any prediction was made. This allows you to scale AI consumption across the entire organization by providing trusted decision-intelligence apps to every line of business. 

Prediction Explanations

Building an app that allows end users to make new predictions is easy and comes with out-of-the-box prediction explanations. Using customizable widgets, you are able to quickly build a UI that shows the impact of individual features and their values for every prediction made. This enables you to have a clear conversation with anyone wanting to understand why a certain decision was made.

unnamed 2 1

What-If Scenarios

Another critical capability supported by No-Code AI Apps is the ability to configure an app to perform what-if scenarios. This feature has also been componentized into a customizable widget that you can drag onto the app canvas. 

What-if scenarios allow users to make a base prediction, then change one or more inputs to create new scenarios and compare them side-by-side. This way you’ll be able to answer questions such as “Do changes in input values have the expected effect on the results?” Then you can select the option that provides the best outcome. For example, you could experiment with different term lengths and interest rates to figure out the right loan configuration for a new applicant that minimizes the chance of default.

App Builder Predictions Explanations 1

Optimizer

The No-Code AI Apps optimizer component is ideal for situations where your end user needs to run hundreds of simulations to identify the ideal combination of input values to maximize a target outcome (e.g., sales, profit, quality, cost, or speed). They can do this by specifying any constraints for the values to be optimized and applying filters to narrow down results and quickly identify the best scenario.

Screen Shot 2021 06 02 at 3.20.48 PM

Get Started with No-Code AI Apps Today

If you already have DataRobot, you can get started with No-Code AI Apps right away. The new capability is a part of our 7.1 release and is available for all editions and all deployment options on-premise and in the cloud. 

No-Code AI Apps works with your existing models and deployments and is accessible via the DataRobot UI. No additional licenses are needed to use it—just enable the feature in your settings. Your DataRobot account team can help you if you are running your DataRobot environment on-premise or in a VPC environment. If you are using the DataRobot Managed service, our customer support team will help you get it enabled.

In the DataRobot Community, we have also included videos and articles to explain No-Code AI Apps in more detail and help you build your first application. Contact us to request a personal demo.

We can’t wait to see what type of AI apps you will build!

Want to See No-Code AI Apps in Action?

Watch a video or Request a Demo. We can’t wait to see what type of AI apps you will build! 

Release 7.1
Explore the Latest DataRobot Release

Become AI-driven with these ground-breaking features

Learn More
About the author
Colleen Wilhide
Colleen Wilhide

Senior Product Manager, DataRobot

Colleen Wilhide is a Senior Product Manager on the DataRobot Business Operationalization team. Prior to joining DataRobot, Colleen worked for the Department of Defense supporting the acquisition lifecycle before later focusing on research and development, product performance, and risk analysis. Currently, Colleen works with clients across industries to continuously advance business performance by leveraging machine intelligence, helping provide business users of all skill levels the machine learning capabilities and inputs needed to improve operational decision-making. Colleen holds a BA from the University of Connecticut.

Meet Colleen Wilhide
  • Listen to the blog
     
  • Share this post
    Subscribe to DataRobot Blog
    Newsletter Subscription
    Subscribe to our Blog