SandboxAQ integrates physics-based drug discovery models into Claude via natural language interface

SandboxAQ has partnered with Anthropic to integrate its large quantitative models (LQMs) directly into Claude, according to an announcement from the company. The integration allows researchers to access quantum chemistry calculations and molecular dynamics simulations through a conversational interface without requiring specialized computing infrastructure.

What are large quantitative models

SandboxAQ's LQMs are proprietary models trained on laboratory data and scientific equations rather than text patterns. According to the company, these "physics-grounded" models can run quantum chemistry calculations, simulate molecular dynamics, and model microkinetics — the study of how chemical reactions unfold at the molecular level.

The models are designed for what SandboxAQ calls "the quantitative economy," which the company claims represents a $50+ trillion sector spanning biopharma, financial services, energy, and advanced materials.

Technical requirements eliminated

Previously, users of SandboxAQ's LQMs needed to provide their own digital infrastructure to run the models. The company's customers — typically computational scientists, research scientists, or experimentalists at large pharmaceutical or industrial companies — were required to have technical expertise to operate the tools.

"For the first time, we have a frontier [quantitative] model on a frontier LLM that someone can access in natural language," Nadia Harhen, SandboxAQ's general manager of AI simulation, told TechCrunch.

Company background

SandboxAQ was spun out from Alphabet roughly five years ago and is chaired by former Google CEO Eric Schmidt. The company has raised more than $950 million from investors and operates multiple business lines including cybersecurity.

According to Harhen, SandboxAQ's 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."

What this means

This integration represents a distribution strategy rather than a model breakthrough. While companies like Chai Discovery and Isomorphic Labs focus on improving the underlying science of drug discovery models, SandboxAQ is betting that accessibility — not model quality — is the primary adoption barrier. By packaging physics-based simulations behind a chat interface, the company is testing whether conversational AI can democratize tools that previously required computational expertise. The approach could expand the user base for scientific AI beyond specialists, though the quality of results through natural language prompts versus direct technical control remains to be demonstrated.