Pricing

Commercial Licensing

$99

$249

$495

Causal Modeling

Capture causal relationships, treatments, and outcomes. Reduce complexity and aide communication within your team and the wider organization

Bias Identification and Conditioning

Analyze back door (indirect relationships) and front door (direct relationships) paths, identify confounders mitigate bias and enhance model validity

Knowledge Modeling

Model the taxonomies, ontologies and business rules of your data in a structured way to organizing and categorizing information and knowledge within an organization.

Low-Code ETL Environment

Leverage a comprehensive library of 4,000+ pre-built plug-ins to extract data from diverse sources, apply transformation for consistency and quality, and load it into your target systems

Causal Edge Strength Analysis

Assess and quantify the strength of causal relationships between variables in your causal models which, in turn, validates your models by confirming or refuting assumptions made in your models

Outlier Analysis

Identify and examine data points that significantly deviate from expected patterns. Supporting further model validity and the ability to mitigate or repeat their potential impact

Intervention Analysis

Intervention analysis in causal models allows you to estimate the potential impact of interventions or policy changes on a system, facilitating data-driven decision making.

Root Cause Analysis

Root cause analysis enables the identification of the fundamental cause of a problem or failure at a point in time, thus guiding effective solution development to prevent recurrence or, if the change was positive, an understanding about how to repeat it.

GPT Discovery Assistant

The GPT discovery assistant can perform a number of useful tasks including helping you identify causal variables and relationships relevant to your specific need and helping to identify unobserved variables when noise (typically unobserved variables) is found in your model.

Jupyter Notebook Integration

Using tools that are familiar to data scientists, the Jupyter Notebook integration allows direct integration from your causal models into Jupyter so you can explore your functions in an IDE.

Causal Micro-Services coming soon

Once the causal models are refined, you can deploy a set of micro-services representing each causal node. This set of services can be used for integration and if you are developing your own causal digital twin.