Projects provide organizational structure for your AI applications, allowing you to logically separate your observability data. This separation is essential for maintaining clarity and focus.With Projects, you can:
Segregate traces by environment (development, staging, production)
Isolate different applications or use cases
Track separate experiments without cross-contamination
Maintain dedicated evaluation spaces for specific initiatives
Create team-specific workspaces for collaborative analysis
Projects act as containers that keep related traces and conversations together while preventing them from interfering with unrelated work. This organization becomes increasingly valuable as you scale - allowing you to easily switch between contexts without losing your place or mixing data.You can customize each project with a description and gradient colors from the Project Settings tab, making it easier to identify and differentiate projects at a glance. Project Settings also surfaces an annotation summary for the project and lets an admin bulk-delete annotations by name (see Annotation summary and bulk delete below).The Project structure also enables comparative analysis across different implementations, models, or time periods. You can run parallel versions of your application in separate projects, then analyze the differences to identify improvements or regressions.
The Project Settings tab includes an annotation summary that lists every annotation name in the project alongside how many span, trace, and session annotations carry that name. It gives you an at-a-glance view of which annotations exist and how heavily each is used.From the same summary, an admin can bulk-delete every annotation with a given name across the project in a single action — useful for cleaning up a mislabeled or deprecated annotation without deleting rows one at a time. The delete can optionally be scoped to a time range so you only remove annotations created within a specific window.
Bulk deletion is destructive and cannot be undone, and is restricted to admins (when authentication is enabled). For removing individual annotations instead, use the per-row delete in the table view under the Annotations tab.
Try it out! Explore a live demo project to see how traces are organized in Phoenix.
Open Demo Project
View real traces and spans in an example Phoenix project
When you need data segmentation above the project level, for example by department or business unit, Arize AX provides Workspaces to isolate and scope access across organizational boundaries.
