Mission
Accelerating life sciences research with AI
Approach
We use LLMs to synthesize the literature, generate hypotheses, and see patterns at a scale no single researcher could.
Current Focus: Overview of Reviews
We are conducting an overview of reviews (umbrella review) to map existing evidence on automated certainty grading. Our goal is to identify durable methodological lessons and avoid redundant research.
Roadmap
- Phase 1: Protocol & Planning (Current) – Defining usage of PRIOR guidelines and AMSTAR 2 appraisal.
- Phase 2: Execution – Searching, screening, and appraising existing reviews.
- Phase 3: Synthesis & Reporting – Mapping evidence gaps and separating durable lessons from hype.
Practical Guide
How to design, run, and report an AI evaluation step-by-step
March 15, 2026
Brief Review
Reporting standards for LLM evaluations: a brief review
March 13, 2026
Commentary
From benchmarks to science: the case for eval reporting standards
March 12, 2026
Commentary
Autoresearch meets biology: curing diseases autonomously
March 12, 2026
Brief Review
LLM evals in epidemiology, biostatistics, and health research
March 9, 2026
Science Spotlight
What would it take to reverse biological age? A brief review of current candidates
February 12, 2026