Potato Lands $4.5M to Automate Lab Work with AI and Robots
Seattle-based startup Potato has raised $4.5 million in seed funding to accelerate development of its AI platform for automating scientific research. The company, founded in 2023 by neuroscientist Nick Edwards and technologist Ryan Kosai, is developing agent-driven systems to support a closed-loop model of science—from hypothesis generation to experimental execution and analysis.
The company name references the potato battery experiment—a nod to building complex tools from simple foundations.
Potato’s current platform functions as an AI research assistant capable of generating hypotheses, optimizing protocols, summarizing scientific literature, critiquing journal articles, and drafting manuscripts. The system uses large language models (LLMs) fine-tuned with retrieval-augmented generation (RAG) to ground outputs in verified literature.
Additional capabilities include automated review of uploaded papers—highlighting methods, evaluating controls, and suggesting follow-up experiments—as well as visualizing workflows by generating diagrams from text-based protocol descriptions. Researchers can also query the system on specific biology topics and receive chain-of-thought answers grounded in published work.
Through a partnership with Wiley, Potato integrates content from a major catalog of peer-reviewed scientific publications. It also draws on open-source databases and ontologies.
Features of the platform:
- Protocol generation and editing using open-access methods
- Automated review of uploaded papers (methods, controls, follow-ups)
- Biology Q&A with cited, literature-grounded answers
- Text-to-diagram workflow visualization
- Structured data extraction via API
- Pre-structured outputs for search, clustering, classification tasks
The company was also recently selected as a participant in the Merck Digital Sciences Studio accelerator program.The startup is now moving beyond computational support toward autonomous experimental execution. With support from Ginkgo Automation, Potato is developing robotic capabilities for lab benchwork.
Automated paper review; Source: Potato
The ultimate goal, according to Edwards, is a fully autonomous research cycle—where AI agents plan, run, and interpret experiments with scientists in the loop.
Reproducibility is central to the company’s mission. Edwards described Potato as a “reproducibility company”, aiming to address longstanding problems in research consistency by automating literature review and standardizing protocol design. The team sees its tools as reducing both the time and cost of generating reliable scientific results, particularly in underfunded or neglected research areas.
The platform is allegedly already deployed in labs across major institutions including Stanford, Harvard, MIT, UC San Diego, UC Berkeley, Scripps Research, and the University of Washington. While Potato is initially focused on life sciences, it plans to expand into material sciences and chemistry.
The seed round was led by Draper Associates, with participation from Dolby Family Ventures, Boost VC, Ensemble VC, Silicon Badia, Alumni Ventures, Defined, and The FounderVC. Strategic angel investors included Geoff Entress and Michael Liou. The company previously raised a $1 million pre-seed round in October 2024.
Potato’s five-person team is led by CEO Nick Edwards, PhD (formerly NIH, BCG, Illumina), and CTO Ryan Kosai, who has held senior engineering roles at Pioneer Square Labs, Attunely, ExtraHop, and others.
Topics: Startups & Deals
