> 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/getting-started/prompting-guide-and-prompt-library-1.md). # K Pro for your team K Pro is an AI scientist for biopharma R\&D. It works across multimodal data so your teams can move from question to evidence faster, without writing code. How you'll use K Pro depends on your role. Find your team below to see the workflows it supports and the kinds of decisions it helps with. *** ### Scientific & Translational teams **This is for you if** you work in translational medicine, biomarker sciences, precision medicine, computational biology, or discovery biology, and you sit where early discovery meets clinical development. **What you're working toward** * Discovering and validating biomarkers * Prioritizing targets * Connecting molecular biology to clinical outcomes **Where K Pro helps** * Test biomarker hypotheses across multiple modalities in hours instead of weeks * Work with curated multimodal data, including MOSAIC real patient data, without spending weeks getting it analysis-ready * Run cross-modality analysis in one place instead of stitching tools together, for example a spatial transcriptomics plot in about a minute rather than three days * Review the literature at scale * Produce publication-ready evidence packages, with outputs traceable back to their source **Challenges this addresses** * Exploring a single biomarker hypothesis across several modalities can take one to two months * Data is siloed and slow to bring to the right quality * Workflows are split across fragmented tools with no shared view * Literature review at scale is a bottleneck * Turning analysis into a clear evidence package adds days of effort *** ### Clinical Development & Medical teams **This is for you if** you lead clinical development or clinical science, work in medical affairs, or own clinical biomarker strategy, sitting between research and the clinic. **What you're working toward** * Increasing probability of success * Accelerating biomarker strategy * De-risking late-stage decisions **Where K Pro helps** * Build the multimodal patient evidence to define the right population before a trial starts, anchored on MOSAIC real patient data * Run responder analysis and multimodal feature discovery to understand who responds and why * Connect molecular signals to clinical outcomes without long bioinformatics turnaround * Assemble evidence packages for internal committees faster * Keep outputs interpretable and traceable to source data K Pro informs and accelerates clinical strategy. It does not replace regulatory validation. **Challenges this addresses** * Defining the right patient population often relies on incomplete biological evidence * Linking genomic features to response data can take months * Responder analysis is a bottleneck and expensive to outsource * Early go/no-go calls can feel like judgment calls without a real-world patient baseline * Evidence packages for committees take too long to assemble *** ### Strategy, BD & Portfolio teams **This is for you if** you work in portfolio strategy, external innovation, business development, or corporate strategy, bridging scientific teams and executive leadership. **What you're working toward** * Maximizing portfolio value by prioritizing the right assets * Sizing the opportunity and validating clinical viability * Building a differentiated, defensible position **Where K Pro helps** * Run competitive landscaping, indication expansion, and asset prioritization in one workflow * Turn weeks of manual diligence into structured, biology-grounded analysis * Surface white space by combining scientific, clinical, and competitive signals * Build investment cases faster, with outputs that are traceable, auditable, and ready to present to leadership **Challenges this addresses** * Asset diligence is slow and manual, stitching together fragmented sources * True white space is hard to find when signals live in different places * Portfolio prioritization is inconsistent across teams using different assumptions and datasets * Competitive intelligence is reactive rather than continuous * Building investment cases takes weeks AstraZeneca has licensed K Pro under a three-year agreement to build biopharma agents for competitive intelligence across pharmaceutical targets, assets, and trials. *** ### Data, IT & Digital teams **This is for you if** you lead data science, bioinformatics, AI/ML, or sit in data and digital leadership, owning how new platforms get integrated and governed. **What you're working toward** * Reducing data friction and time to insight * Deploying AI securely at enterprise scale * Enabling teams to run analyses autonomously **Where K Pro helps** * Deploy securely within your existing infrastructure * Integrate with your data stack as an intelligence layer rather than a replacement * Cut data onboarding from weeks to hours * Extend the platform with your own data (BYOD) * Keep work reproducible and auditable, with transparency and control over system behavior K Pro integrates within enterprise IT infrastructure and decision workflows, as in the three-year AstraZeneca licensing agreement. **Challenges this addresses** * Data preparation is the main bottleneck before any analysis can start * Every new tool adds integration, authentication, and governance work * Data science teams are overloaded with repetitive data requests * A lack of standardization across tools and data versions limits reproducibility and scale * Valuable internal datasets stay siloed and underused *** ### Executive Leadership **This is for you if** you sit at the top of the organization (CEO, CSO, CMO, EVP/SVP R\&D, CDO) with final authority over R\&D and AI strategy. **What you're working toward** * Maximizing portfolio value and R\&D productivity * Accelerating time to market * De-risking pipeline decisions to reduce late-stage failure **Where K Pro helps** * Turn fragmented scientific data into faster, higher-confidence decisions, for example up to 30x faster target prioritization * Surface signal earlier to support go/no-go calls * Show enterprise-wide impact rather than isolated use cases * Give leadership a clearer view of where data and AI are improving speed, probability of success, and cost efficiency **Challenges this addresses** * R\&D productivity is under pressure from rising costs and high clinical attrition * High-stakes portfolio decisions are made under persistent uncertainty * Pipeline value is lost through late-stage failures that better signal could have flagged earlier * AI and digital investments are fragmented and don't always translate into measurable impact * There's no consolidated view of where AI is materially moving the needle --- # 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/getting-started/prompting-guide-and-prompt-library-1.md?ask= ``` 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.