User Interface and Workflows
Leverage powerful, AI-guided product development workflows without writing a line of code.
THE IMPORTANCE OF USABILITY
Materials and chemicals datasets are small and sparse. So, to use AI effectively, you need to leverage the expert knowledge on your team. Usability and collaboration are at the forefront of the Citrine Platform so that your whole team can build AI-guided workflows and contribute their domain knowledge. The intuitive graphical user interface is complimented by a comprehensive Python API.
WORKFLOWS
Researchers are guided through a clear workflow to configure their data, AI models, search spaces, and candidates. On the project overview page, digital assets are laid out in branches as they explore different options with status bars showing progress as they go.
NO CODE AI MODELS
At the simplest level, a new AI model can be created by using check boxes to choose inputs to be considered and a drop-down box to choose the property you want the model to predict. More sophistication can be added using the graphical AI model builder, to add expressions, processors and featurizers, but the starting point is simple.
Data scientists can use the Python API to tailor models even more.
NO CODE SEARCH SPACE DEFINITION
Researchers can use sliders to select upper and lower bounds for each ingredient and processing parameter. (Data Scientists can also use the Python API to set up both continuous and enumerated design spaces.)
INTERPRETABLE MODELS
The graphical AI Model builder enables the team to see how pieces of the model fit together.
The feature importance list lets researchers see which inputs are having the most effect on the predictions of the model.
INSIGHTFUL VISUALIZATIONS
Candidate materials can be filtered, color-coded, labelled and compared. Clear charts show how candidates compare to targets and to existing materials.
Researchers can use these charts to communicate progress and collaborate within a team.
PYTHON API
Consistent – stable – comprehensive, rely on the Citrine Platform Python API as you roll out AI for materials and chemicals across your organization. The API allows python users to structure, reuse, automate, and share interaction pathways, enabling efficient deployment of AI@Scale.
