Microsoft Discovery is an AI-powered platform for scientific research and engineering, designed to accelerate discovery across pharmaceuticals, materials science, chemicals, semiconductors, energy, and advanced manufacturing. The platform supports the full research lifecycle—from understanding existing knowledge to designing, testing, and refining new ideas. Below are the core scenarios ...
Microsoft Discovery is an extensible platform that brings together agentic orchestration, advanced reasoning, a graph-based knowledge foundation, and high-performance computing for scientific research and R&D workflows.
Discovery is an online platform with human oversight. Researchers can change, edit, and kick off runs as needed. We're thinking about extending Microsoft Discovery to digital twins and lab automation using natural language, giving researchers more access to lab processes.
The Discovery Engine is the cognitive backbone of Microsoft Discovery. It operates as an autonomous research partner that plans work, delegates to specialized agents, monitors progress, and adapts when results come back differently than expected. Instead of responding to individual prompts in a chat window, the engine runs continuously in the background while you focus on the scientific ...
Set up Microsoft Discovery infrastructure by creating a supercomputer, workspace, project, agents, investigations, and then run your first AI-powered scientific investigation.
In this tutorial, you create an investigation, set up a small set of tasks, enable Discovery Mode, and observe how the Discovery Engine executes your work autonomously. By the end, you have a completed investigation with results that were planned, executed, and validated using cognition.
Learn about Microsoft Discovery Studio, a web-based research environment built on Visual Studio Code for the web that enables scientists and engineers to work with AI agents, investigations, and scientific tools in a customizable interface.