Concepts

Tables

Data tables are flexible, structured schemas defined at the workspace level. They provide a central way to store and manage data that is accessible across all projects within a given workspace. These tables can be configured either by an admin or with help from Cradle’s customer success team. They enable you to upload raw or processed data in different formats, including formats that match your LIMS system or lab machine output.

Because they are version-controlled and fully traceable, tables support evolving scientific workflows while maintaining a history of changes and ensuring consistent data quality over time.

Views

Data views offer a way to explore and interact with tables by allowing users to create and save tailored perspectives on the data. A view might filter rows, hide or reorder columns, or sort the data in a way that’s meaningful for a specific task or workflow. They are useful for narrowing down data for specific tasks. This makes it easy for different users to see and use just the slice of data that’s relevant to them without altering the underlying table itself.

Tasks

Tasks are the core execution units in Cradle. Each task represents a specific scientific action—such as training a machine learning model, analyzing an experimental dataset, generating new sequences, or selecting candidates for synthesis.

Tasks can take different forms depending on their type, but all share a common structure: they have inputs (such as configuration settings or source data), and they produce outputs, known as artifacts. Tasks are versioned and repeatable, making them a foundational building block for traceable R&D processes.

Artifacts

Artifacts are the outputs produced by tasks. These include items such as trained models, performance evaluations, intermediate datasets, or generated sequences. Every artifact is directly linked to the task that created it, ensuring that results are reproducible and the full context of how they were generated is preserved.

Artifacts can be reused across workflows, referenced in discussions, and compared across versions to support scientific decision-making.

Reports

Reports are structured summaries that present the outputs of tasks in a clear, interpretable format. They help teams evaluate and communicate the results of scientific work, including data quality assessments, model performance metrics, and final candidate sequences.

While current reports are generated automatically by Cradle, future versions will allow users to annotate, edit, and share these reports to support decision-making and collaboration.

Organizing your work

When using Cradle you can organize your work through:

• Workspaces. The home for all your data, projects and users for your organization. Data in the workspace will be private to your organization only. Learn more Workspaces.
• Projects. Within each workspace you can set up projects. Each project works towards one optimization goal, such as developing a binder for a specific target or optimizing an enzyme for a specific catalysis. Learn more Projects.
• Rounds. Within a project, you use a round to represent one cycle of generating sequences and testing them in the lab for a specific experimental goal. Rounds help you track which sequences have been tested and connect your computational work to lab workflows. Learn more in Rounds.

Get started

To get started with using Cradle, learn how you can set up your first Round.