Introducing Faraday Public Beta

We are excited to announce that Faraday, our AI scientist for drug design, is now available in public beta. Starting today, researchers and drug developers worldwide can register and begin using Faraday to accelerate their discovery workflows.

Public beta is now open at https://platform.ascentbio.ai/

After testing with early access users and achieving state-of-the-art performance on the Ether0 benchmark, we're ready to bring Faraday's capabilities to the broader scientific community. 

In this post, we cover:

• Faraday Platform's Capabilities

• Getting Started with the Platform

  
  

Faraday Platform's Capabilities

Faraday is an AI scientist agent that autonomously solves multi-step life science research and drug design problems. Given a research objective, Faraday systematically decomposes the task, executes computational workflows, and returns detailed solutions with supporting data visualizations.

Lets go over a few highlights,

Target Biology–Drug Interaction

The agent carries out complex life science research tasks by search across literature and datasets, Integrating and interpreting multi-dimensional(e.g., MOA + chemistry + clinical + commercial) data , running specialized tools and models, and performing multi-step analysis.

See it in action

Molecular Design, SAR Exploration and Property Reasoning

Proposing novel molecules or modifications that satisfy constraints such as molecular formulas, functional groups, or desired properties; Evaluating chemical properties, safety, and ADME characteristics to prioritize candidates for downstream experiments

See it in action

Retrosynthesis planning

Conducts multi-step retrosynthetic planning to identify feasible synthetic routes from commercially available or readily accessible starting materials.

Competitive analysis and unmet needs discovery

Synthesizes insights across publications, patents, clinical pipelines, and commercial disclosures to map the competitive landscape, identify differentiation gaps, and surface unmet scientific and clinical needs, informing target selection and R&D strategy.

Building for the drug developer

A core mission of Ascent Bio is to dramatically shorten the path from idea to experiment in early drug discovery. We believe this has never been more possible with the advent of highly-capable AI agents and the pace of bio foundation model development. A unique aspect of building an agentic platform for life science research is that these agents operate within a landscape of many ML and non-ML models, each specializing in a specific task (e.g. protein structure prediction). This creates both a tremendous opportunity for building in this space as well as a challenge (i.e. avoiding token bloat, inefficient tool use). In this public beta, we're opening up a few open-source that we're excited to see used - Boltz-2 and DiffDock. Based off insights we collect from how these tools are integrated into agentic workflows, we'll be releasing more frontier models in the coming weeks.

Starting today, you can accelerate your drug discovery research with agent-directed frontier model use in the Faraday Platform

Molecular Docking and binding affinity prediction

Uses computational docking methods to predict ligand–target binding poses and interactions, and supports binding affinity prediction through frontier models such as Boltz-2.

Getting Started

Pricing

We're offering Faraday through three tiers designed to meet the needs of individual researchers, teams, and organizations requiring our most advanced reasoning capabilities.

Choose the plan that fits your research needs

Get started today with the Faraday Platform