AUTHENTICATION

Plug into your enterprise-wide SSO mechanism for watertight identity and access management, with roles assigned in the AD and fine-grain permissions being configured in TRAC. Azure AD, SAML and OpenID are supported out of the box. Other solutions can be accomodated using plug-ins.

MODEL REPOSITORIES

To enable the virtual deployment method, TRAC uses an external repository to store model code. Integratation for standard version control systems, including GitHub, GitLab and Nexus are available as standard. Custom model repositories can also be accommodated using plug-ins.

DEVELOPER TOOLS AND IDEs

Deploy the TRAC (python) runtime library to your IDE and enjoy the type safety of production during the development process. This allows you to build models which can be deployed to production with a single click and without code modification.

DATA LAYER

TRAC manages the data layer for you, using regular cloud buckets (AWS, GCP or Azure) for scalable, resilient, and cost-effective storage. Integrations with on-premises data solutions - including Hadoop - are also avaialable.

EXECUTION SERVICE

TRAC uses an external compute service to execute jobs. For cloud deployments, we provide a Kubernetes pattern which can support both single-node and distributed (Spark) capabilities. Other compute services are available for on-premises deployments.