• 6 min read

Unlocking autonomous agent capabilities with Microsoft Copilot Studio

A screenshot of the Agents view in Copilot Studio overlaid on a light blue and orange background, with the Copilot Studio logo overlaid on the top left of the screen shot.
At our AI Tour in London, we’re excited to announce a new set of capabilities that enable you to build autonomous agents, which will be in public preview at Microsoft Ignite 2024. These agents understand the nature of your work and act on your behalf—providing support across business roles, teams, and functions.

At our AI Tour in London, we’re excited to announce a new set of capabilities that enable you to build autonomous agents, which will be in public preview at Microsoft Ignite 2024. These agents understand the nature of your work and act on your behalf—providing support across business roles, teams, and functions.

Since the introduction of generative AI and Microsoft Copilot, our work has rapidly evolved. In our Business Applications, 2.1 million users engage with Copilot monthly, benefiting from AI-driven experiences and workflows with Microsoft’s commitment to privacy, security, and compliance.

Companies like McKinsey & Company, Pets at Home, Thomson Reuters, Clifford Chance, and more around the world, are seeing an incredible impact from the use of Microsoft Copilot Studio and our modern business applications. They’re becoming true AI-first companies. AI-first companies leverage a combination of people, Copilot, and agents to be more efficient, improve customer engagement, and improve employee experience.

Copilot is your personal, private assistant that works solely for you, enhancing your capabilities. And agents are expert systems that operate autonomously on behalf of a process or company. You configure, secure, and test your agent, and then it automates for you and your team across apps and data sources. We expect every employee will have Copilot and will be supported by many agents.

Every organization is unique, and this uniqueness is a competitive advantage. Organizations need a platform that empowers users to create their own agents for specific processes. Copilot Studio plays that crucial role by customizing Copilot and creating agents for your entire company.

Where agents thrive in the AI world

Organizations are always looking for ways to enhance efficiency, improve customer experience, and drive growth, but identifying the starting point is crucial. Copilot Studio can help you modernize existing processes or create new ones, paving the way for innovation and unlocking additional business value.

Organizations like Pets at Home have created autonomous agents for specific business workflows in Copilot Studio. Pets at Home, the UK’s leading pet care business, created an agent for its profit protection team to more efficiently compile cases for skilled human review, which could have the potential to drive a seven-figure annual savings.

We’re using AI to do the time-consuming work so our colleagues can use all resource and expertise to make decisions quickly based on large amounts of data. It’s truly helped empower colleagues through both the level of information at their fingertips, and in time spent on more nuanced and insightful work. The agents solution allows the profit protection team to more effectively assess cases for potential profit loss and dedicate more of their time to skilled analysis, rather than simply information gathering.

—William Hewish, CIO, Pets at Home

In collaboration with Microsoft, and as part of a broader AI transformation playbook for itself and its clients, McKinsey & Company is creating an agent that will speed up the client onboarding process. The pilot showed lead time could be reduced by 90 percent and administrative work reduced by 30 percent. The agent automates complex processes, such as identifying the right expert capabilities and staffing teams, and acts as a single place where colleagues can ask questions and request follow-ups. Streamlining tasks and reducing manual inputs, this agent could potentially save consultants many hours, allowing them to spend more time with clients.

“We are excited about the power of copilot agents in taking AI transformations to the next level. We’ve seen early success of our pilot agent that was built for our own organization, in collaboration with Microsoft. And we see tremendous potential for agents to help our clients rewire the way their businesses operate.

—Rodney Zemmel, senior partner at McKinsey & Company

In continuation of Thomson Reuters’ collaboration with Microsoft, the company built a professional grade agentic solution for legal due diligence. This complex workflow requires significant legal expertise and specialist content, and the ambition was to make this process more efficient. The agentic solution combines the knowledge, skills, and advanced reasoning of Thomson Reuters CoCounsel, and integrates into Microsoft’s productivity tools to take on key tasks in this workflow. By significantly transforming the way work happens, the solution helped lawyers close deals more quickly and efficiently for their clients. Initial tests indicate that several tasks in the due diligence workflow could be cut by at least 50%.

Autonomous agents are positioned to create AI-first business processes across various departments like IT, marketing, sales, customer success, and finance in industries such as travel, retail, and financial services.

On top of being able to build and manage agents from scratch with Copilot Studio, we’re introducing ten new autonomous agents in Microsoft Dynamics 365 to build capacity for sales, service, finance, and supply chain teams.

New capabilities coming to Copilot Studio

Copilot Studio provides an all-in-one platform for building agents, with managed software as a service (SaaS) infrastructure, AI models, a low-code design interface, and thousands of prebuilt connectors. It integrates personal, business, and analytical data, and enables publishing to Copilot, web, and your apps. These new capabilities allow agents to act independently, initiate events, and automate complex business tasks. Let’s explore how this works.

Autonomous triggers

Agents can automatically respond to signals across your business and initiate tasks. They can be configured to react to events or triggers without human input that instead originate from various tools, systems, and databases, or are even scheduled to run hourly, daily, weekly, or monthly.

Animated Gif Image

Dynamic agent plan

Each business process can have different paths since agents create dynamic plans on the fly to handle and complete tasks. Users can view the underlying logic for each of the agents’ paths, which includes key details, steps, and systems involved. This provides insight into why the agent chose a particular method, its decision process, and context, along with detailed steps, including variables and outputs, which are crucial for debugging.

Animated Gif Image

Activity overview

Trust, dependability, and precision are at the core of establishing agent autonomy in organizations. The true strength of these agents is their ability to monitor activities across real-world scenarios, which in turn enhances business outcomes. To further transparency and accountability, we’re launching an “Activity” tab that enables makers to access a complete log of past agent runs, including progress tracking, identification of blocks, trend analysis, and review of earlier decisions.

New models like the OpenAI o1 series

Copilot Studio agents use the latest models, including the OpenAI o1 series, which is being used in the limited private preview for autonomous agents. These models are optimized for advanced reasoning tasks, enhancing the ability to solve complex problems.

Secure and trusted platform

Microsoft is committed to the advancement of AI driven by responsible AI principles that put people first.

Organizations are equipped with enterprise data protection including a comprehensive set of features to secure agents, including encryption, data loss prevention measures, and a responsible AI strategy to mitigate AI-related risks such as prompt injection. The data sources linked to the agent adhere to stringent security measures and controls, managed through the admin center, including robust authentication protocols.

Agent guardrails and controls are established by maker-defined instructions, knowledge, and actions. You can implement access controls for creating, sharing, and using agents. And you can establish policies and information labels to safeguard data and monitor agent usage.

You can also oversee the lifecycle management of agents efficiently with process governance, from creation to retirement. You can establish policies regarding resource utilization, access permissions, and publishing. And you can audit events and obtain insights into application performance to ensure continuous improvement and compliance.

With the comprehensive tooling provided by Copilot Studio, businesses can build, secure, and deploy agents tailored to their organizational needs. Read more about agent security here.

Security&Governance_900

Becoming an AI-first company

Copilot is emerging as the new user experience, acting as your UI for AI, making workflows smarter and more resilient through agents. Powered by your data, converted into knowledge, it’s organized and reasoned over in a secure environment to fuel Copilot and all your agents. This shift empowers organizations to leverage and create sophisticated, intelligent applications.

With Copilot Studio, everyone can become an AI-first company

Join us at Microsoft Ignite 2024 to experience the public preview of these autonomous agents. Discover how they can empower your organization to not only adapt but to lead in this exciting new era of AI innovation, truly embodying the principles of an AI-first approach.