> For the complete documentation index, see [llms.txt](https://docs.owkin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.owkin.com/collaborate-and-share/k-pro-data-model-and-technical-references-1.md).

# Collaboration features

K Pro collaborative features are being built with the following principles in mind:

**Shared workspaces.** Project-level workspaces centralize a team's analytical work for a dedicated team, specific target, indication, or program. Cohort definitions are shared, versioned, and reusable across team members and analyses. Analytical artifacts (plots, reports, intermediate results) accumulate within a project as a shared body of evidence.

**Role-based access.** Our K-platform support fine-grained permissions, we are able to define roles such as Admin for an Organisation, Admin for a project and users within projects. Tiered access for collaborators (internal team members, external academic partners, CROs) is supported with strict level of isolation.

**Decision and audit trail.** All agent, users actions and tool invocations within a project are logged for audit purpose. Cohort and artifact version history are preserved. *"Why was this target prioritized?"* can be reconstructed from the audit trail at any point.

**Reporting.** Teams collaboratively assemble target assessment reports that combine K Pro's findings with team annotations and decisions. Reports export to standard formats for sharing with non-K Pro users.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.owkin.com/collaborate-and-share/k-pro-data-model-and-technical-references-1.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.