Astraea

Roadmap & Position in Trial Biometrics

Automates clinical-trial biometrics into FDA-ready outputs.

Company Overview

Astraea is an AI-native biometrics platform that automates clinical data management, statistical programming, and FDA-ready reporting. The buyers are pharma sponsors and biotech biometrics teams; public customer names are not disclosed.

What They're Building

The company's public product roadmap & what they're committed to building.

Astraea Standards

Automates CDISC mapping, SDTM generation, ADaM transformation, Define-XML, aCRF, and eCRT work for regulated trial submissions.

Astraea Compliance

Handles desensitization, role controls, versioning, audit logs, and 21 CFR Part 11-style review gates for clinical workflows.

Astraea Evidence

Extracts study evidence from protocols, SAPs, CSRs, literature, and safety docs so biometrics teams can trace decisions back to source.

Astraea Stats

Generates SAP-driven TFLs, analysis datasets, statistical programs, and QC loops for clinical reporting.

Embedded Biometrics Teams

Pairs the platform with biostatistics, programming, and medical-writing support, a smart wedge for buyers who still want humans near the FDA package.

Latest Intelligence

Zeitgeist tracks private signals to determine where the company is heading strategically.

Submission Automation Is The Wedge

May 14, 2026

Confidence:

Medium

New Intel: Astraea’s public product surface centers on FDA-ready biometrics automation, especially SDTM, ADaM, TFLs, and validation. If it works, the budget target is CRO statistical programming spend, putting ICON and Saama in the exposed zone.

Founder and Key Execs

Joshua Wang

Co-Founder & CEO (Stanford math/CS, multi-agent systems and clinical data automation)

Sanmay Sarada

Co-Founder & CTO (Stanford CS/bio, clinical and hospital data infrastructure)

Founder Force Multiplier

Joshua Wang brings multi-agent systems and clinical data automation work from Stanford. Sanmay Sarada brings clinical and hospital data infrastructure experience. The pairing matches a market where the product has to move fast without spooking the QA team or the FDA reviewer.

Funding History

2026 | Founded
2026 | Accepted into Y Combinator Spring 2026; no other public funding found

Competitors

ICON WorkBench:

Large CRO-backed biometrics automation with deep services reach; Astraea is earlier and more software-native.

Saama Biometrics:

Clinical analytics incumbent automating SDTM, ADaM, and TLF workflows; Astraea competes on agent-first execution.

Clymb Clinical TFL Designer:

Focused on TFL design and clinical reporting templates; Astraea is aiming for a wider source-to-submission workflow.

Astraea

's Moat:

Defensibility is unproven at this stage. The likely path is workflow switching costs accumulating around sponsor-specific CDISC mappings, validation history, and audit trails.

How They're Leveraging AI

Document Understanding

AI-assisted evidence extraction links protocol, SAP, CSR, literature, and safety-document claims back to source text for biometrics review.

Agentic Workflow Automation

Schema-constrained agents turn protocols, SAPs, and raw trial data into SDTM, ADaM, TFLs, Define-XML, and aCRF outputs.

Simulation

Simulation support appears to test sample-size and adaptive-design choices before study plans harden into SAPs and reporting work.

AI Use Overview:

Astraea appears to run schema-constrained LLM agents over clinical documents and datasets, then validate outputs with CDISC rules and Pinnacle 21-style checks, which keeps the model honest in a regulated workflow.

More Similar Companies

10xScience

Turns weeks of manual protein analysis into minutes for drug development teams.

CellType

Simulates human biology with AI to predict drug effects and run virtual trials.

Google CEO Sundar Pichai highlighted their C2S-Scale 27B model for generating a novel cancer hypothesis that was later validated experimentally. CellType simulates human biology to predict drug effects using foundation models presented at ICML 2024, with all deals coming inbound from top-10 pharma. Yale professor turned down Google to build it.

Ditto Biosciences

Mines parasite genomes to discover protein therapeutics for autoimmune diseases.

Parasites evolved to suppress human immune responses over millions of years. Ditto mines their genomes for immunomodulatory proteins, and over 98% of those proteins remain uncharacterized. Three PhDs from Harvard, Berkeley, and UCSF with 40+ years of combined expertise in host-parasite biology.

Mango Medical

Automates surgical planning for orthopedic procedures from CT scans using agentic AI.

Surgical planning for shoulder replacements takes hours of manual CT scan interpretation. Mango automates it in seconds via API, already past $500K ARR before demo day, with an 8-figure LOI from a leading orthopedic company. Only company in YC W26 pursuing FDA 510(k) clearance.

Back To All Companies >