SandboxAQ brings drug discovery models to Claude — no PhD in computing required

At a glance:

• SandboxAQ integrates its physics-grounded AI models directly into Anthropic's Claude platform
• The integration eliminates the need for specialized computing infrastructure to access advanced drug discovery tools
• SandboxAQ's Large Quantitative Models (LQMs) simulate molecular dynamics and microkinetics for biopharma and materials research

The Challenge of Drug Discovery

Drug discovery remains one of the most expensive and time-consuming pursuits in modern industry. Finding a single viable molecule can take up to a decade and cost billions of dollars, with most candidates ultimately failing to reach the market. A generation of AI startups has emerged promising to streamline this process, but most have focused on making existing tools more usable for researchers who are already technically sophisticated.

A Different Approach to Accessibility

While competitors like Chai Discovery and Isomorphic Labs have concentrated on improving the underlying scientific models, SandboxAQ has identified a different bottleneck: the interface. The company, founded roughly five years ago as an Alphabet spinout with Eric Schmidt (Google's former CEO) as chairman, believes the real barrier to adoption isn't the complexity of the models themselves but the complexity of accessing them. SandboxAQ has raised more than $950 million from investors and has expanded beyond drug discovery to include cybersecurity and other business lines.

The Power of Large Quantitative Models

SandboxAQ has developed proprietary Large Quantitative Models (LQMs) that are "physics-grounded," built on the rules of the physical world rather than just patterns in text. These models can perform quantum chemistry calculations and simulate both molecular dynamics and microkinetics—the study of how chemical reactions unfold at the molecular level. This capability allows researchers to predict how candidate molecules are likely to behave before conducting physical experiments. "Trained on real-world lab data and scientific equations, LQMs are AI models engineered for the quantitative economy, a $50+ trillion sector spanning biopharma, financial services, energy, and advanced materials," the company explained.

Integration with Claude

The company's recent partnership with Anthropic represents a significant shift in accessibility. By integrating these scientific AI models directly into Claude, SandboxAQ is putting powerful drug discovery and materials science tools behind a conversational interface that requires no specialized computing infrastructure to use. "For the first time, we have a frontier [quantitative] model on a frontier LLM that someone can access in natural language," explained Nadia Harhen, SandboxAQ's general manager of AI simulation. Previously, users of SandboxAQ's LQMs would have had to provide their own digital infrastructure to run the models.

Targeting the Pharmaceutical and Materials Industries

SandboxAQ's customers typically include computational scientists, research scientists, and experimentalists working at large pharmaceutical or industrial companies searching for new materials that can become marketable products. "Our customers come to us because they've tried all the other software out there, and the complexity of their problem is such that it didn't work or didn't yield positive results for them when that translation went to take place in the real world," Harhen noted. This focus on practical application differentiates SandboxAQ from competitors who have concentrated solely on model improvements.

Beyond Drug Discovery

While drug discovery represents a significant application for SandboxAQ's technology, the company has expanded its focus to other sectors of the "quantitative economy"—a $50+ trillion sector spanning biopharma, financial services, energy, and advanced materials. This broader vision suggests SandboxAQ isn't just building another chatbot or code assistant; it's targeting the fundamental economic sectors that AI is expected to transform. The integration with Claude represents just one step in making these powerful quantitative models accessible to a broader range of professionals.