Mantis Biotechnology
Product & Competitive Intelligence
Unifies biomedical device testing and clinical trials with AI-powered digital twins.
Company Overview
Builds an AI-powered digital twin platform that integrates large language models with physics-based simulation to unify biomedical device testing, clinical trial analytics, synthetic data generation, and regulatory workflows for life sciences companies.
Competitive Advantage & Moat
Product Roadmap & Public Announcements
Mantis has publicly described its unified data platform connecting CAD design through FDA submission, physics-enhanced synthetic data generation for ML training, and LLM-powered querying across biomedical datasets. They've announced domain-aware data infrastructure that encodes biological and clinical meaning, and highlighted use in both medical device development and professional sports/human performance applications.
Signals & Private Analysis
Hiring patterns reveal heavy investment in bioinformatics, deep learning, and biostatistics talent, suggesting expansion of predictive modeling capabilities. NIH NHLBI grant activity points to cardiovascular digital twin development. GitHub and job postings indicate work on automated regulatory document generation and cross-system clinical data integration. The all-female team and Y Combinator pedigree position them for strong narrative-driven fundraising. Conference and community signals hint at partnerships with medical device OEMs and possible expansion into AI-driven clinical trial site selection.
Product Roadmap Priorities
Mantis uses physics-informed digital twins to generate high-fidelity synthetic biomedical datasets that train ML models for rare conditions and data-scarce clinical scenarios.
They build virtual copies of human biology to create fake-but-realistic patient data so AI can learn from millions of cases that would take decades to collect in real life.
It's like a flight simulator for biology—instead of crashing real planes to train pilots, you crash virtual hearts to train AI doctors.
Mantis integrates large language models into its platform to automate regulatory submission drafting, cross-reference clinical evidence, and enable natural-language querying across complex biomedical datasets.
They built an AI that reads and writes FDA paperwork so biomedical engineers can ask plain-English questions and get instant, citation-backed answers instead of spending months buried in regulatory documents.
It's like having a paralegal who has memorized every FDA filing ever made and can instantly draft your legal brief while showing their homework.
Mantis deploys patient-level digital twins to simulate clinical trial outcomes before enrollment begins, optimizing trial design, endpoint selection, and patient stratification using ML-driven virtual cohorts.
They create virtual versions of thousands of patients and run the clinical trial on computers first, so companies can fix problems in the trial design before spending hundreds of millions on the real thing.
It's like playing SimCity but for clinical trials—you build the whole city of patients on your computer, watch what breaks, fix the zoning laws, and only then start construction in the real world.
Company Overview
Key Team Members
- Georgia Witchel, Founder & CEO
Founder Force Multiplier
Georgia Witchel uniquely combines a CS degree from Harvey Mudd, computational math from Johns Hopkins, and a Master's in Bioengineering from UW with experience founding Louiza Labs (YC S25), a physics engine for digital twins in robotic surgery. This bridge between software engineering and biomedical science enables Mantis to build biologically meaningful synthetic data that competitors using purely statistical approaches cannot match.
Funding History
- 2025 | Georgia Witchel founds Mantis Biotechnology.
- Jan 2026 | $6.3M Seed round announced, led by Decibel Partners, with StoryHouse Ventures, Y Combinator, Pioneer Fund, Spot VC, and Fenwick.
- 2026 | Accepted into Y Combinator Winter 2026 batch.
- 2026 | Platform in active use for medical device and sports technology applications.
Competitors
- Digital Twin Platforms: Dassault Systèmes (SIMULIA Living Heart), Siemens Healthineers (digital twin initiatives).
- Clinical Trial Analytics: Medidata (Acorn AI), Veeva Systems, Flatiron Health.
- Synthetic Data for Life Sciences: Syntegra, MDClone, Gretel.ai.
- AI-Native Biomedical: Unlearn.AI (digital twin clinical trials), Twin Health (metabolic digital twins), Evidation Health.
