> 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/what-you-can-do-with-k-pro/overview.md).
# How K Pro works
When you ask K Pro a question, it routes your request to the right agent, runs the analysis, and returns an interactive result. This page covers the three ways you can ask, the agents available to handle your request, and the role of skills.
### Three ways to ask K Pro a question
K Pro is designed as a no-code platform for wet-lab scientists and disease-area experts. It supports three modes of interaction along a spectrum of control, and a scientist moves between them as the task requires.
#### Co-pilot: Conversational exploration
**Ask. Explore. Iterate.**
Ask a question in natural language. Get back an interactive artifact you can click into, drill down, and build on.
Example: The scientist opens K Pro and asks a question in plain English: "Show me NECTIN4 expression across malignant cell types in MOSAIC bladder cancer cohorts, and compare to GTEx healthy tissues." K Pro returns an interactive cell-type expression plot, a healthy-tissue comparison heatmap, and a narrative summary linking to the underlying data slices.
The scientist can click any data point to see the patient-level data and the statistical test that produced the value. A plain-English follow-up ("Now show the spatial distribution of NECTIN4-expressing tumor cells relative to CD8+ T-cells") triggers the next analysis automatically.
#### Semi-autonomous: Skilled workflows
**Run expert workflows on demand.**
Trigger a skill (Owkin-certified or custom) for complex multi-step analyses where you want a constrained, reproducible workflow rather than free-form conversation.
Example: The scientist knows what analytical workflow they want and invokes a pre-built skill directly with a slash command: e.g. `/target-characterization NECTIN4 in BLCA` or `/drug-positioning in `. K Pro runs the full multi-step workflow end-to-end and returns a structured report. Skills come from three sources:
* Owkin-certified workflows built from a decade of pharma engagements
* KOL-derived skills encoding leading domain experts' methodologies
* Customer-authored skills built by client teams
#### Broad autonomous campaigns
**Scale across hypotheses.**
Launch multiple hypotheses in parallel through dedicated sandboxed agents — useful when you want to evaluate several strategies side by side.
Example: The scientist launches multiple hypotheses in parallel through sandboxed agents, each running the same skill or different skills against different parameters. Each agent produces its own report; results are aggregated for comparison. This is where K Pro scales beyond a single analysis to portfolio-level exploration.
In none of these modes does the scientist write code or specify which datasets to query. K Pro makes those decisions transparently and the scientist can audit any of them.
### What's behind K Pro
K Pro draws on a 104-hospital patient data network covering latest standard of care, with **1.2M patients** characterized across multimodal data (bulk, single-cell, spatial RNA, pathology, longitudinal follow-ups). Indications covered include oncology, immunology & inflammation, cardiometabolic, and neuro.
### Agents & tools available in K Pro Free
Each question is routed to the agent or tool best suited to handle it. The agents below are available in K Pro Free.
| **Agent / tool** | **What it does** |
| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Multi-Omics | Analyzes multi-omics data from MOSAIC and TCGA datasets. Handles gene expression, signatures, survival analysis, and visualization. |
| Consensus | AI-powered scientific search engine for finding relevant papers, literature-backed hypothesis validation, and scientific background research. |
| Literature Review | Retrieves scientific documents using semantic search over 30M+ PubMed abstracts. Answers scientific questions with cited sources. |
| Prior Knowledge | Queries gene-level features from public databases — protein families, localization, essentiality, oncogenicity, safety/toxicity, target tractability scores. |
| Discoverability | Reference information about Owkin, MOSAIC, and TCGA datasets — useful for onboarding and orienting before analysis. |
| Pathology Explorer (MCP) | Pathology AI capabilities: TCGA slide-level histomics, cell-type filtering, slide visualization, survival analysis on cell-type features. |
| Plotter | Generates plots/charts from your data, with schema inspection and SQL validation. |
### What is a skill?
A **skill** is a pre-packaged set of instructions and tools designed for a high-stakes task. When you trigger a skill, K Pro switches into a specific mode where it applies the right filters, checks the right thresholds, and returns a defined output format. Skills make analyses reproducible: same input, same kind of output, every time.
Three types of skills are available:
* **Owkin-certified skills:** validated scientific workflows built from Owkin projects.
* **KOL-derived skills**: domain experts' methods and reasoning encoded as executable workflows.
* **Your own skills**: your internal best practices, layered on top of the existing library.
###
---
# 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, and the optional `goal` query parameter:
```
GET https://docs.owkin.com/what-you-can-do-with-k-pro/overview.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.