We are announcing a new enterprise agentic platform called Microsoft Discovery to accelerate research and development (R&D) at Microsoft Build 2025.
Our goal is to bring the power of AI to scientists and engineers to transform the entire discovery process—from advanced knowledge reasoning and hypothesis formulation to experimental simulation and iterative learning. Microsoft Discovery enables researchers to collaborate with a team of specialized AI agents combined with a graph-based knowledge engine, to drive scientific outcomes with speed, scale, and accuracy.
We have architected Microsoft Discovery to be highly extensible, enabling researchers to integrate the latest Microsoft innovations with their own models, tools, and datasets as well as a wide range of partner and open-source solutions. Built on top of Microsoft Azure, trust, compliance, transparency, and governance are key design principles of this enterprise-ready platform to enable responsible innovation, keeping the researcher in control.
At Microsoft, our researchers have leveraged the advanced AI models and high-performance computing (HPC) simulation tools in Microsoft Discovery to discover a novel coolant prototype with promising properties for immersion cooling in datacenters in about 200 hours—a process that otherwise would have taken months, if not years. This rapid discovery lays the groundwork for future developments in safer and sustainable solutions across multiple industries and is a demonstration of how Microsoft Discovery can potentially transform R&D in any company.
We are working with a notable set of Microsoft customers who are interested in co-innovating in diverse industries including chemistry and materials, silicon design, energy, manufacturing, and pharma. We are also working with a broad partner base that is building on top of the platform to drive this acceleration, and we couldn’t be more excited. The possibilities are endless as we realize the full potential of AI in R&D and we are just getting started!
The agentic vision for science
At Microsoft, we want to amplify the ingenuity of scientists to usher in a new era of accelerating discovery and expand the horizons of research. Doing so requires empowering R&D teams with transformative technologies that can drive meaningful business impact. However, R&D has very specific challenges compared to other domains:
- Scientific knowledge is vast, nuanced, and distributed.
- The discovery process is diverse and dynamic, involving multiple highly specialized methods and tasks, making it very hard to connect the dots across the different domains involved.
- R&D is iterative. There are rarely simple, clear-cut answers. Instead, scientific knowledge evolves through evidence, discourse, and refinement.
This complexity demands a new paradigm—one that isn’t aimed at doing the same experiments faster, but rather fundamentally changing the paradigm of how we approach R&D.
Imagine if every researcher could collaborate with a tireless team of intelligent, synergistic AI agents with the sole purpose of accelerated innovation. This is our vision for a new agentic R&D paradigm, embedding AI in every stage of the scientific method.
In this new world, people and specialized AI agents will cooperatively refine knowledge and experimentation in real time in a continuous, iterative cycle of discovery—all while maintaining the control, transparency, and trust that enterprises and governmental institutions require. This requires a comprehensive platform where AI can capture both the scientific domain and the cognitive processes involved in managing scientific thought. To realize this vision, scientific AI agents must be able to:
- Reason over a complex and contextual graph connecting all knowledge sources.
- Specialize across distinct domains and tasks.
- Learn from results and adapt entire research plans accordingly.
Introducing Microsoft Discovery
We are taking a big step toward realizing this vision with Microsoft Discovery, bringing agentic R&D to life by leveraging the latest innovations from Microsoft and the broader scientific ecosystem.
Graph-based scientific co-reasoning
The advent of large language models (LLMs) hinted at this new era, offering capabilities to speed up certain scientific tasks, particularly for information retrieval and hypothesis generation. However, LLMs often lack the contextual understanding required to deeply reason over distributed, nuanced, and often contradictory scientific data.
Microsoft Discovery is built on top of a powerful graph-based knowledge engine. Instead of merely retrieving facts, this engine builds graphs of nuanced relationships between proprietary data as well as external scientific research. This allows the platform to have a deep understanding of conflicting theories, diverse experimental results, and even underlying assumptions across disciplines.
This contextual reasoning is also transparent. Rather than outputting monolithic answers, it keeps the expert in the loop with detailed source tracking and reasoning, providing the level of transparency in AI systems that builds trust, ensures accountability, and allows experts to validate and understand every step or make any adjustments as needed.
Specialized discovery agents for conducting research
Instead of siloed and static pipelines, Microsoft Discovery implements a continuous and iterative R&D cycle where researchers can guide and orchestrate a team of specialized AI agents that learn and adapt over time—not just for reasoning, but for conducting research itself. The definition of these specialized agents captures both domain knowledge and process logic, simply through natural language.
R&D teams will be able to build a custom AI team aligned to their specific processes and knowledge, easily encoding these agents with their expertise and methodologies to ensure they can adapt and orchestrate as research progresses. This approach is far more flexible than hard-coding behaviors of today’s digital simulation tools, which often are highly specialized and lack streamlined integration with others, and it means that research teams no longer require computational expertise to drive impact. As an example, users can access and define various agents’ specialties, such as ‘molecular properties simulation specialist’ or ‘literature review specialist.’ They can even suggest which tools or models the agents should use or create, and how they should collaborate with others.
This organic, bidirectional collaboration is a game-changer for managing R&D: agents are not only capable of working for the researchers, but with them in a manner that can truly amplify human ingenuity—seeing both the forest and the trees at once.
At the center of this collaboration is Microsoft Copilot, acting as a scientific AI assistant that orchestrates these specialized agents based on the researcher’s prompts. Copilot is aware of all the tools, models, and knowledge bases in a customer’s catalog on the platform, can identify which agents to leverage, and can set up end-to-end workflows that cover the full discovery process by combining advanced AI and HPC simulations through the joint work of these agents.
Extensible and enterprise-ready
Microsoft Discovery is built on top of Azure infrastructure and services, leveraging by design the trust, compliance, and governance controls at the core of Microsoft’s secure cloud foundation.
We believe in the power of an open ecosystem that leverages the strengths of Microsoft’s latest advancements in combination with other innovative solutions from customers and partners. Microsoft Discovery allows R&D teams to extend the platform’s catalog by bringing their toolkit of choice to cover their specific research needs in a comprehensive scientific bookshelf. This extensibility at the core of Microsoft Discovery simplifies the onboarding of their choice of computational tools, models, and knowledge bases—whether they are custom developments, open-source, or commercial solutions. As we bring to market new capabilities in reliable quantum computing and embodied AI, the platform will remain future-proofed with the best technologies available at Microsoft and across the industry.
Real impact: Discovering a novel, non-PFAS coolant prototype
Over the past months, we have made significant strides aiding computational scientists in their research and incorporating cutting-edge innovations from Microsoft Research. This has led to remarkable breakthroughs, such as discovering a novel solid-state electrolyte candidate that uses 70% less lithium in collaboration with the Department of Energy’s Pacific Northwest National Laboratory (PNNL) and enabling rapid computational simulations that accelerate scientific discoveries at Unilever. Microsoft Discovery is designed to bring these innovations to every scientist—not only those with deep computational expertise.
One of the more exciting early use cases of Microsoft Discovery is unfolding at the Pacific Northwest National Laboratory, where scientists are using Microsoft Discovery’s advanced generative AI and HPC capabilities to further develop machine learning models that predict and optimize complex chemical separations—a critical process in nuclear science. These separations are essential for effectively isolating radioactive elements after the nuclear fission process, a notoriously time-sensitive and incredibly chemically complex task. In the future, the team aims to use these advancements to reduce the time scientists must spend in hazardous radioactive environments, while improving yields and purity, enhancing both safety and efficiency.
—Scott Godwin, Director, Center for Cloud Computing, Pacific Northwest National Laboratory
By leveraging advanced AI models and HPC tools for simulation that will be available on Microsoft Discovery, Microsoft researchers discovered a novel, non-PFAS, immersion datacenter coolant prototype in about 200 hours.1 Current coolants often take many years to develop and can contain harmful PFAS-based chemicals that make them unviable to use, as there’s a global push to ban these “forever chemicals” in favor of more environmentally friendly options in this industry and many others.
After the digital discovery process, we successfully synthesized this coolant prototype in under four months, and it’s currently under further analysis and refinement. We have already tested some of the primary properties of this material and they align to the AI predictions, which is a testament to the accuracy of the predictive models used. While this project is only an experiment, it lays the groundwork for future developments and improvements in coolant technology and demonstrates how the combination of HPC and specialized AI models can accelerate and transform R&D processes.
According to Daniel Pope, founder of Submer, a company whose mission is to build datacenters with a strong focus on sustainability, efficiency, and a smarter usage of resources:
The speed and depth of molecular screening achieved by Microsoft Discovery would’ve been impossible with traditional methods. What once took years of lab work and trial and error, Microsoft Discovery can accomplish in just weeks, and with greater confidence.
A growing ecosystem
We are putting this enterprise-grade platform into the hands of global innovators to demonstrate real-world impact across industries—from chemistry and pharma to manufacturing and silicon design.
It’s only with a strong ecosystem that we’ll be able to realize the full potential of Microsoft Discovery, and it’s why we’re working with customers, partners, and other Microsoft teams to bring first-party advancements together with leading industry tools and domain expertise.
Customers and internal collaborators
GSK is working to revolutionize healthcare, uniting science, technology and talent—including world-class partnerships—to get ahead of disease together. The company uses tech to advance science and accelerate the development and delivery of medicines and vaccines to positively impact the health of people at scale.
GSK’s depth and breadth of data and integrated use of tech across every part of its business—from early scientific exploration through to manufacture and delivery of medicines and vaccines in market—provide a unique offering when working with others. The company looks forward to a possible partnership with Microsoft with the intent of further advancing GSK’s generative platforms for parallel prediction and testing, creating new medicines with greater speed and precision, and potentially transforming medicinal chemistry to new unimaginable levels. The possibilities ahead are exciting, and together, we can strive for the most innovative solutions for patients and for health.
The Estée Lauder Companies has gained a worldwide reputation for high-quality skincare, makeup, haircare and fragrance products that deliver highly effective results demonstrated by extensive research and product evaluation. The company is excited to harness the power of Microsoft Discovery to further accelerate the development of products that uphold the finest standards of excellence.
Our proprietary R&D data, stemming from the minds of our brilliant scientists and nearly 80 years of research, development, and experimentation, is a key competitive advantage. The Microsoft Discovery platform will help us to unleash the power of our data to drive fast, agile, breakthrough innovation and high-quality, personalized products that will delight our consumers.
—Kosmas Kretsos, PhD, MBA, Vice President, R&D and Innovation Technology, The Estée Lauder Companies
Additionally, Microsoft is releasing a medical research agent that uses the same graph-based knowledge engine available in Microsoft Discovery to enhance information retrieval by synthesizing insights from trusted medical journals. As part of a broader set of specialized agents in the healthcare agent orchestrator code sample in Azure AI Foundry, this agent enables researchers and developers to deliver actionable and evidence-based guidance tailored specifically to complex, multi-disciplinary healthcare workflows—such as cancer care.
Domain-specific offerings
Combining Microsoft’s and NVIDIA’s strengths in generative Al and scientific computing, we plan to integrate Microsoft Discovery with NVIDIA ALCHEMI and NVIDIA BioNeMo NIM microservices to accelerate breakthroughs in materials and life sciences. Materials researchers will now have access to state-of-the-art inference capabilities for candidate identification, property mapping, and synthetic data generation. Biomolecular R&D teams will be able to accelerate Al model development for drug discovery, leveraging pre-trained BioNeMo Al workflows, all in Microsoft Discovery’s unified, enterprise-grade platform.
Researchers can also deploy their AI agents on high-performance NVIDIA-accelerated Azure AI Foundry infrastructure, enabling them to efficiently process and synthesize large volumes of scientific data with exceptional speed and responsiveness for accelerated discovery and enhanced research outcomes.
AI is dramatically accelerating the pace of scientific discovery. By integrating NVIDIA ALCHEMI and BioNeMo NIM microservices into Azure Discovery, we’re giving scientists the ability to move from data to discovery with unprecedented speed, scale, and efficiency.
—Dion Harris, Senior Director of Accelerated Data Center Solutions, NVIDIA
Additionally, we plan to integrate Synopsys’ industry solutions in Microsoft Discovery to accelerate semiconductor engineering, helping both hardware designers and software developers deliver superior products.
Semiconductor engineering is among the most complex, consequential, and high-stakes scientific endeavors of our time, which makes it an extremely compelling use case for artificial intelligence. By integrating Synopsys’ pioneering AI-powered design solutions with Microsoft Discovery, we can realize the potential of agentic AI, re-engineer chip design workflows, supercharge engineering productivity, and accelerate the pace of technology innovation.
—Raja Tabet, Senior Vice President, Engineering Excellence Group, Synopsys
Microsoft is also working with PhysicsX, planning to integrate the company’s physics AI foundation models into Microsoft Discovery so customers can unlock new levels of automation, optimization, and performance across engineering and manufacturing.
The Microsoft Discovery platform represents a seismic shift in how AI can accelerate scientific discovery and engineering. This is about transforming how complex physical systems are designed, built, and operated across advanced industries—in aerospace and defense, semiconductors, minerals and materials, energy, and automotive. Together, PhysicsX and Microsoft are building the software infrastructure that will define the next era of engineering.
—Jacomo Corbo, Chief Executive Officer and Cofounder, PhysicsX
Integration support
Lastly, we’re excited to partner with a growing list of software integrators, such as Accenture and Capgemini, to help customers and collaborators scale custom platform deployments.
Together with Microsoft, we are shaping a bold AI vision for organizations who use deep science to bring innovative products to patients and consumers. Our laboratory transformation strategies and Microsoft’s Microsoft Discovery platform create a dynamic ecosystem for scientific advancement. This collaboration will help us realize the laboratory of the future, enabling scientists to push the boundaries of discovery, experimentation, and testing with greater speed and precision.
—Adam Borenstein, Managing Director, Global Laboratory Reinvention Lead, Accenture
We are excited to be bringing the Microsoft Discovery platform and AI agents to R&D-intensive sectors. We believe these technologies have the potential to enable expert scientists to unlock step changes in the pace of innovation, bringing transformative benefits to business and society. This partnership will drive productivity in laboratory-driven R&D by drawing on Capgemini’s industry experience, specialist physical and biological AI capabilities, and science-led ‘lab-in-the-loop’ intellectual property, including that of Cambridge Consultants, the deep tech powerhouse of Capgemini. For our clients this could mean accelerated discovery and predictive modelling or other competitive advantages through using data and AI at scale.
—Roshan Gya, Chief Executive Officer, Capgemini Invent
Ready to take the next steps?
Learn more about how Microsoft Discovery can help scientists and engineers transform research and development:
- Watch the announcement of Microsoft Discovery at the Microsoft Build 2025 Keynote.
- Sign up to receive updates on the Microsoft Discovery preview
¹Based on the definitions of PFAS provided by the Organisation for Economic Co-operation and Development (OECD) (2021), the U.S. Environmental Protection Agency and Buck et. al. (2011)
The post Transforming R&D with agentic AI: Introducing Microsoft Discovery appeared first on Microsoft Azure Blog.