What if scientific AI agents were guided by expert-built skills?

Most AI agents can call tools. The harder part is knowing how those tools should actually be used.

With SciAgentKit, computational drug-discovery workflows are guided by skills written by domain experts. These skills encode tool selection, parameter choices, validation checks, and scientific decision rules across ligand preparation, PDB selection, pocket detection, docking, molecular dynamics, and trajectory analysis.

The calculations are performed by established scientific software, while the agent follows expert-defined workflow logic.

The aim is to make advanced drug-discovery workflows more reproducible, consistent, and easier to run through natural language.

The goal is not just automation. It is to make computational drug-discovery workflows more consistent, reproducible, and accessible without losing the expert knowledge behind them. We are curious how others think expert knowledge should be built into scientific AI agents.