Analytics Projects Overview

An Analytics Project is a reusable analysis environment with its own datasets, collaborators, permissions, and lifecycle.

Use an Analytics Project when analysis needs to be repeated, shared, or maintained independently from day-to-day sample records. You normally work with it through an AI agent: describe the intended dataset or question, review what the agent discovers or proposes, and approve write operations only when the target is clear.

Lab Project or Analytics Project?

Use a Lab Project question when…	Use an Analytics Project when…
You need an immediate answer from existing PAWS data.	You need a reusable analysis dataset.
The answer is read-only.	Data will be loaded or maintained over time.
One Lab Project contains the required source data.	Several Lab Projects or external files may contribute data.
No separate collaborator roles are needed.	Readers, Writers, and Publishers need different access.

Linking a Lab Project records the relationship and data lineage. It does not automatically copy members or permissions into the Analytics Project.

Analytics roles

• Reader: discovers available data and runs read-only analysis.
• Writer: adds or updates rows in existing datasets and can run analysis.
• Publisher: creates and changes dataset structures and reusable views.
• Workspace Owner: creates Analytics Projects and manages their access.

Roles are independent. A Publisher who also needs to query or load data may need an additional Reader or Writer grant. Choose the smallest combination that allows a person to complete their work.

Before you begin

Analytics access has two parts:

1. your MCP token needs lab.analytics.read for queries or lab.analytics.write for changes; and
2. you need the appropriate role for the selected Analytics Project.

If either part is missing, ask the Workspace Owner or pilot coordinator to update your access. Do not create a broader token or role than the task requires.

Typical path

1. A Workspace Owner creates the Analytics Project and links relevant Lab Projects.
2. The owner grants Reader, Writer, and Publisher access.
3. A Publisher creates the dataset structure.
4. A Writer loads or maintains data.
5. Readers and Writers ask reproducible questions and review the query evidence.