Google Cloud Platform (GCP) is a great cloud computing option for enterprise workloads. Google Vertex AI is a good tool for developers who are comfortable working with containers and GCP developer tools.
Domino runs natively on Google Kubernetes Engine (GKE). It connects seamlessly with Google data sources such as Big Query. Domino delivers best-in-class reproducibility, collaboration, and project management tools, for machine learning you can trust.
Integrated Governance & Reproducibility
Collaboration and reuse of work unlock innovation at scale, preventing diminishing returns as you grow your team. While solutions like Vertex AI make it easy for data scientists to “spin the meter” in their own workspaces, Domino is uniquely focused on helping teams work better together.
Domino automatically tracks and versions all project assets, including data, code, software, compute, experiments, models, batch jobs, and apps. You can instantly roll back to or recreate the exact environment used to create a model to streamline audit, governance, compliance, and regulatory reporting.
Domino Projects allow you to easily set goals, track progress, and resolve blockers. Git and Jira integration makes it easy to integrate data science into broader enterprise project processes. With Domino, your scientists collaborate with one another for improved model quality and productivity.
Choice of Cutting Edge Development Tools
Compute Environments in Domino allow data scientists to customize the packages and tools they use to unlock innovation with sandboxes that can be secured, audited, and shared.
Domino is open and flexible with support for more data science development tools, not just Jupyter. Domino supports Jupyter, JupyterHub, RStudio, SAS, MATLAB, VS Code, and more. Plus, Domino can access data wherever it lives, including Amazon RedShift, Google BigQuery, Azure Data Lake, Databricks, Snowflake, and many others.
On-demand distributed compute clusters in Spark, Ray, Dask, and MPI let data scientists speed up computationally intensive work by a factor of 10 to 100 or more.
Enables Faster and Smoother Cloud Migrations
Domino’s unique kubernetes native, open architecture is the foundation for a modern cloud-based computational research platform. Domino makes it easier to bring legacy compute workloads to the cloud! Most enterprises have legacy analytics tools such as MATLAB or SAS. Domino makes it seamless to move these tools to the cloud, without needing to build a new cloud stack for them. With Domino, teams across the enterprise using different tools get a unified portal with turnkey, self-serve infrastructure that’s easy to govern and secure.
Integrated Model Deployment and Monitoring
Domino provides you with many deployment options, including prediction APIs, apps, and batch jobs. You can also export models as Docker images to CI/CD pipelines, AWS, or other infrastructure. Interactive apps created with Shiny, Dash, and Flask allow non-technical users to interact with models.
Models don’t work well forever – they degrade over time. That’s why it’s critical to monitor your models in production. Domino automatically collects instrumented prediction and ground truth data so you can monitor deployed models for data drift and accuracy. You can set notifications when quality checks exceed thresholds. When a model drifts, you can easily drill down into model features to quickly modify, retrain and redeploy models.