Latent Labs has launched LatentX, a web-based AI model for programming biology. The tool lets users design novel proteins with natural language right in their browser.
The model just came out of stealth after raising $50 million. It’s claiming state-of-the-art results on multiple protein design metrics, validated in a physical lab.
Latent Labs CEO Simon Kohl, who co-led DeepMind’s AlphaFold protein design team, explained the difference between LatentX and AlphaFold: 
“AlphaFold is a model for protein structure prediction. So it allows you to visualize existing structures, but it doesn’t, it doesn’t let you generate new proteins,” Kohl said.
LatentX designs proteins unseen in nature, including nanobodies and antibodies, speeding up therapeutic discovery. Unlike AI drug discovery firms like Xaira or Isomorphic Labs, Latent Labs focuses on licensing its model rather than developing its own medicines.
Kohl told TechCrunch:
“We have computational ways of assessing how good the designs are,” he said, adding that a high percentage of proteins the model creates will be viable when tested in the lab.
“Not every company is in a position to build their own AI models, to have their own AI infrastructure, and to have their own AI teams,” he added.
LatentX is free to use now but will introduce paid advanced features later. The company is backed by Radical Ventures, Sofinnova Partners, Jeff Dean, Dario Amodei, and Mati Staniszewski.
The launch puts Latent Labs in direct competition with open-source AI drug discovery players like Chai Discovery and EvolutionaryScale.
The model’s browser-based access aims to democratize biology programming for academic, biotech, and pharma users.
TechCrunch event: San Francisco, October 27-29, 2025.
