> 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/help-center/getting-started/what-can-i-do-with-k-pro.md).

# What can I do with K-Pro?

{% hint style="info" %}
**What this article covers** This article introduces the core capabilities of K-Pro and explains the three ways you can interact with it to run analyses and generate insights.
{% endhint %}

K-Pro is an AI-powered research platform for cancer biology. When you type a question or request in natural language, K-Pro interprets your intent, routes it to the most appropriate tool or agent, runs the analysis, and returns an interactive result — no coding required.

### Three ways to interact with K-Pro

* **Co-pilot** — Ask a specific, targeted question and get a focused answer. Best for exploring a gene, a dataset, or a single hypothesis. *e.g. "Plot CTLA4 expression across cancer types in TCGA"*
* **Semi-autonomous** — Ask K-Pro to perform a multi-step analysis (e.g. characterising a tumour subtype across multiple modalities). K-Pro plans and executes a sequence of analyses. *e.g. "Run a multimodal characterisation of GBM subtypes using MOSAIC"*
* **Broad autonomous** — Give K-Pro a broad research objective and let it autonomously design and execute an investigation, synthesising findings across data and literature. *e.g. "Identify biomarker strategies for EGFR-driven lung adenocarcinoma across transcriptomics, proteomics and spatial data"*

### What tools are available?

K-Pro automatically selects the right tool based on your request. The main tools available to K-Pro free users are:

* **Discoverability** — Reference information about Owkin, MOSAIC, and TCGA — dataset descriptions, contacts, and related resources. Best for onboarding and dataset exploration before running analysis.
* **Bioknowledge Navigator** — Curated biological knowledge: protein families, localization, essentiality, oncogenicity, safety/toxicity data, and target tractability scores.
* **Plotter** — Generates interactive multi-omics visualisations from TCGA and MOSAIC Window data: gene expression, survival analysis, cell population comparisons, spatial transcriptomics, clinical correlations. Variants (`plotter-public` / `plotter-pro` / `plotter-compugen`) are enabled per organization.
* **Consensus** — AI-powered scientific literature search (consensus.app). Searches and synthesises published research to support or challenge a hypothesis.

Additional tools available as add-ons (subscription dependent):

* **Trials Navigator** — Clinical trials timeline visualisation and statistical projections for individual trials.
* **Reporter** — Generates structured Markdown reports synthesising artifacts from previous analyses.

{% hint style="info" %}
**Pathology AI is available outside K-Pro, not inside K-Pro chat.** Owkin's pathology model (HistoPLUS) is exposed as a featured MCP partner in ChatGPT (OpenAI Life Sciences) and via Anthropic. To use it, access those products directly.
{% endhint %}

{% hint style="success" %}
**Tip:** You don't need to specify which agent to use. Just describe what you want to know and K-Pro will route your request automatically. For best results, be specific about the gene, dataset, cancer indication, and type of analysis.
{% endhint %}

### What K-Pro is not designed for

* General-purpose web search or non-cancer-related queries
* Querying datasets or indications outside your subscription scope
* Clinical decision support — K-Pro is a research tool, not a medical device


---

# 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/help-center/getting-started/what-can-i-do-with-k-pro.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.