Wire flash
XtalPi upgrades XtalPi Science platform, launches 80+ proprietary scientific skills for AI agents
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
On September 21, XtalPi Technology announced a major product upgrade to its scientific AI agent platform, XtalPi Science. The upgrade introduces over 80 proprietary scientific skills and tools, encapsulating real R&D project expertise, proprietary datasets, algorithms, and computational tools. These capabilities cover key stages of drug discovery, including target research, patent analysis, molecular generation, property prediction, protein preparation, molecular docking, retrosynthesis route prediction, structure-activity relationship analysis, LC-MS spectrum analysis, and data processing automation. The skills are presented as Tools, Skills, and Reusable Recipes, accessible via a simple dialog command without programming. The platform now extends from digital to experimental execution, connecting to a robot laboratory to schedule experiments, collect data, and adjust tasks based on feedback. XtalPi stated that as more researchers join, it will continue to drive AI, research agents, and robotic experiments to form a tighter closed loop from scientific question to analysis and experimental verification.
Source report
September 21 — XtalPi Science, the scientific agent platform developed by XtalPi, today announced a significant product upgrade, officially launching over 80 proprietary scientific skills and tools, while expanding its invitation-based testing scope.
Key Features of the Upgrade
The newly released 80+ scientific skills and tools encapsulate real-world R&D expertise, proprietary datasets, algorithms, and computational tools. This enables mature research methodologies to be invoked, combined, and traced on demand by intelligent agents.
Capabilities Covering Key Stages of Drug Discovery
The platform's capabilities span major stages of drug discovery, including:
- Target research and patent analysis
- Molecular generation and property prediction
- Protein preparation and molecular docking
- Retrosynthetic route prediction
- Structure-activity relationship (SAR) analysis
- Liquid chromatography-mass spectrometry (LC-MS) spectrum interpretation
- Data processing and workflow automation
Three Forms of Capability Delivery
These capabilities are presented in three formats:
- Tools – supporting specific operations
- Scientific Skills – enabling specialized research tasks
- Reusable Workflows (Recipes) – facilitating multi-step continuous execution
Users can simply type "/" in the dialogue box to bring up the skill list, select the desired capability, and let the agent execute the task and output results — all without the need for programming or installing specialized software.
From Digital to Experimental Execution
XtalPi Science has extended its capabilities from the digital realm to experimental execution. By connecting to scientific data systems and autonomous laboratories, the platform can:
- Schedule lab robots to conduct experiments
- Collect experimental data
- Adjust subsequent tasks based on feedback from results
This integration allows research plans developed in the digital workspace to enter real experimental workflows.
Future Outlook
According to XtalPi, as more researchers and partners join the platform, the company will continue to drive the coordinated operation of AI, scientific agents, and robotic experiments. The goal is to form a tighter闭环 (closed loop) — from scientific question formulation and analysis through to experimental validation.
Source
环球网Eastern
Part of this Story
XtalPi Science AI agent outperforms Claude in drug discovery, integrates robotic lab automation