> 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.md).

# Customize K Pro

K Pro is customizable at three levels.

**User specific, Per-team and per-org via custom skills.** Skills are both how users invoke complete multi-step workflows and how customer bioinformatics and biology teams encode internal best practice. Customer-specific skills can capture internal scoring methodologies, naming conventions, regulatory submission templates, or the methodologies of internal KOLs. Custom skills are versioned, promoted through a publish-and-review lifecycle, and can take precedence over Owkin-built skills under per-customer governance.

**Custom data and tool integration.** Proprietary datasets connect via the BYOD pattern (data lake, MCP server wrapping an internal database). Internal tools (compound libraries, biomarker pipelines, RWD systems) register as MCP servers and become first-class agents in K Pro's orchestrator. Custom scoring dimensions can be added through internal MCP servers (e.g. "K Pro, also penalize targets that failed our internal toxicity screen").

**Custom views and reports.** Filter and re-rank dynamically. Export to report formats matching your team's structure or branding. Persistent project workspaces with custom dashboards.

Skill authoring today benefits from Owkin-side support during onboarding. We are investing in self-service skill-creation tooling so customer teams can author skills directly. Status: in active development.


---

# 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.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.