PathOS™ Platform
pipeline
Pathos is redefining DRUG DEVELOPMENT
starting IN Oncology.
The PathOS™ platform is a flywheel powered by one shared AI core, Foundry, that drives Scout and Sprint . Scout prioritizes the most promising assets from multimodal evidence. Sprint translates them into faster clinical learning. Foundry learns from every program, so each new asset starts stronger than the last.
To train the best AI models, you need the best data.
We have access to >200 petabytes of multimodal oncology data linked to patient outcomes.
This is 50x the size of The Cancer Genome Atlas (TCGA), the largest public genome dataset in oncology.
Pathos is transforming drug development through AI—integrating discovery, data, and clinical translation into one continuously learning system. With data and insight building impact, every stage of the process is connected, accelerated, and designed to reach patients faster.
Pathos three Core Engines
Scout uses advanced AI to identify he therapies most likely to help patients who don’t respond to today’s standard of care.
- Scans all investigational therapies
- Matches each therapy to the patient subgroup most likely to benefit
- Ranks opportunities to focus development on the highest-confidence bets
SCOUT
Scout uses advanced AI to identify drugs most likely to benefit patients who don’t respond to the current standard of care.
- Scans the data for all investigational therapies
- Matches each therapy to the patient subgroup most likely to respond
- Produces a ranked list with the highest priority therapies
AI-Enabled Asset Selection Engine
SPRINT
AI-Enabled Clinical Execution Engine
Once Scout brings in an asset it hands it off to a Sprint Pod, a small autonomous team that operates like an independent biotech company inside Pathos.
- Sprint Pods utilize the Pathos platform to design clinical trials that won’t fail
- AI Scientists and AI Engineers are core team members
- Sprint Pods are focused on moving the asset from A to B (e.g. from Ph1 to Ph2, from Ph2 to Ph3 ready)
Once Scout selects an asset, it moves into a Sprint Pod, a small autonomous team that operates like an independent biotech company inside Pathos.
- Uses the PathOS™ platform to design biomarker-driven trials and accelerate Go/No-Go decisions
- AI scientists and engineers work alongside clinical and translational leaders
- Each Sprint Pod has one mission: move a specific asset from one milestone to the next (e.g., Phase I→II, Phase II→III-ready).
FOUNDRY
Foundry’s backbone is the Oncology Foundation Model we are building in partnership with Tempus and AstraZeneca — the largest model of its kind in the world.
But Foundry is more than just a model. It leverages Pathos' wetlab to implement insight into the clinical validation lab-in-the-loop system.
The AI core that compounds learning across every program
Foundry is the shared AI core that powers Scout and Sprint. Its backbone is the largest oncology foundation model in the industry. Beyond the model, Foundry connects to Pathos’ lab-in-the-loop validation system, so insights get tested, refined, and reused across every program
Together, these three engines create a learning flywheel, so each program starts smarter and precision therapies reach patients sooner
Explore the therapies advancing through our AI-powered pipeline
