What's New in Copilot Studio

In March, Copilot Studio continued to evolve, bringing new features and improvements designed to streamline AI-driven business processes. At Digital Bricks, we stay ahead by integrating the latest innovations to deliver enhanced solutions for our clients. Discover how these new capabilities can power your AI strategy and explore our AI Adoption Services for tailored implementations.

Autonomous Agents: Now Generally Available

In today’s fast-paced world, responding instantly to critical events is crucial, especially for organizations operating globally. Whether it’s a finance team managing budget thresholds, a sales team seizing early renewal opportunities, or a frontline team addressing urgent low-supply alerts, timely action drives efficiency and impact.

That’s why we’re excited about the general availability of autonomous agents in Copilot Studio, designed to keep you proactive by automating responses to critical events. These agents eliminate the need for manual checks, scheduled workflows, or complex custom API solutions.

Using triggers, you can configure your agents to wait for specific events and execute a set of actions when that event happens. The instructions—written in natural language, not code—add autonomous capabilities to your agent, enabling them to monitor, detect, and react to pertinent events, thereby automating your defined workflows.

These autonomous agents can handle a wide range of tasks, from sending notifications to executing complex workflows like automating supply chain responses. They run seamlessly in the background while maintaining full visibility through the Activity tab. At Digital Bricks, we specialize in implementing AI-driven automation solutions, helping organizations increase productivity and stay ahead.

Deep Reasoning in Agents

A standout advancement in Copilot Studio is the integration of deep reasoning for agents. This new capability allows agents to make more nuanced decisions by leveraging advanced reasoning models like OpenAI o1. By combining your enterprise data with sophisticated algorithms, these agents analyze information, identify patterns, and solve complex problems.

For industries like finance and supply chain management, where data-driven insights are paramount, deep reasoning enhances the ability to predict trends, qualify sales leads, and make smarter recommendations. Copilot Studio enables users to build agents with critical thinking skills, useful for creating RFPs, analyzing market shifts, or processing complex datasets.

Agent Flows in Copilot Studio

Agent flows offer structured, rules-based automation for tasks requiring consistency and precision. These flows follow a predefined sequence of actions, making them ideal for routine processes like data validation or compliance monitoring. Unlike autonomous agents, which respond to dynamic inputs, agent flows are designed for repetitive, predictable tasks.

For example, a finance team might use agent flows to automate end-of-month reporting, while an HR team could automate onboarding workflows. Digital Bricks helps businesses implement these workflows through our Business Process Automation Services, ensuring consistent and efficient operations.

Generative Orchestration

Anticipating every possible question an end-user might ask agents is nearly impossible. With generative orchestration now available in general availability, you no longer have to try. This powerful feature eliminates the need to manually define countless trigger phrases or delineate every conversation flow through topics.

Unlike classic orchestration, which relies on predefined, manually authored topics, generative orchestration enables agents to generate contextual intelligent responses on the fly based on your organizational knowledge sources, actions, and topics. Agents can even generate their own questions to collect information they need to solve the end-user’s problem, or ask for confirmation when needed before executing an action. This creates more natural conversations, decreases escalations and abandonment rates, and broadens the range of scenarios agents can successfully support.

Generative orchestration further enables your agents to handle multiple requests that come in a single query, such as an end-user asking to find their nearest store and get that store’s opening hours. By being able to comprehensively answer the end-user’s questions, the agents create a better experience and higher satisfaction during agent interactions.

Model Context Protocol

MCP is a transformative way to seamlessly connect AI apps, APIs, and data sources into your agents, streamlining the creation of intelligent systems.

MCP enables faster integration by automatically bringing actions and knowledge from your server into your agent, including names, inputs, outputs, and descriptions. It keeps these elements in sync as updates happen on the backend, eliminating the need for manual adjustments and ensuring your agents stay up to date. Plus, MCP’s growing library of pre-built, MCP-enabled connectors in the marketplace makes it effortless to connect existing systems while maintaining enterprise-grade security and governance.

Whether you’re working with internal APIs or third-party services, MCP empowers you to create more responsive, intelligent agents with less effort. At Digital Bricks, we integrate MCP into our Copilot Studio Development projects to build robust and flexible AI solutions.

Tools and Prompts Inside Copilot Studio

Copilot Studio has a new centralized place where makers can create, manage, and assign reusable functionality across agents: Tools. At the Copilot Studio application level, you’ll find Tools in the left-hand navigation. Click into it to try out the first tool available, Prompts.

In Copilot Studio, prompts instruct the GPT model to behave in a certain way or perform a specific task. A custom prompt can guide the model to answer a question, complete text, translate languages, summarize a document, and identify tasks, to-dos, and action items in text. The complexity of a custom prompt can range from a single sentence to something more intricate, depending on the task. When this prompt is assigned to an agent, the agent follows the prompt before responding, giving the maker more control over the responses the agent will generate and resulting in higher-quality answers or actions from the agent.

The Prompts tool allows makers to easily create custom prompts inside Copilot Studio, either at the app level—then assigning the prompts to agents—or within an agent or topic. Inside the tool, you’ll find out-of-the-box templates to help you instruct the model effectively, or you can write the prompt from scratch. Then you can test the prompt with sample data or inputs before assigning it to an agent.

The Tools menu and in-app prompt builder are powerful new additions for two reasons. First, they streamline the experience so that it’s easier to get started on prompts, easier to test, and easier to work on prompts at the level you need them (app, agent, or topic), all inside one tool. These prompts also use the same consumption-based meter as those created in the external tool, no extra license or cost involved.

Second, they make these functions endlessly reusable. Makers can build a prompt once and assign it to multiple agents, and any maker can use prompts created by other makers in the same Copilot Studio environment. More consistent, more collaborative, and more scalable. All this results in more effective agents and more efficient business processes.

Open Web Search

Open web search has arrived in Copilot Studio, empowering your agents to access high-quality, real-time information from the web when pre-configured knowledge sources are insufficient. This powerful new feature enhances your agents' ability to provide relevant responses in diverse, open-ended scenarios, such as research, content creation, and competitive analysis—without requiring developers to anticipate every possible data source in advance.

By connecting agents to publicly available information through open web search, you significantly enhance their ability to deliver accurate and current answers. This capability is particularly valuable for enriching internal knowledge with the latest technological insights or delivering more dynamic and flexible responses to end users. The result? Increased usage, higher satisfaction rates, and a more substantial impact.

With open web search now available in public preview, you can build smarter, more adaptable agents that seamlessly address a wider range of business needs. Integrate this feature to ensure your agents remain relevant and valuable in an ever-changing information landscape.

That's a Wrap!

The latest updates to Copilot Studio empower makers and organizations to build smarter, more adaptable agents that seamlessly integrate with dynamic business environments. With features like autonomous agents, deep reasoning capabilities, agent flows, generative orchestration, Model Context Protocol (MCP), enhanced tools and prompts, open web search, and the preview of GPT-4.5, Copilot Studio significantly reduces complexity while enhancing functionality. These innovations enable users to automate complex tasks, generate contextual responses, and access real-time information effortlessly, driving productivity and innovation across industries. At Digital Bricks, we leverage these advancements to deliver tailored AI solutions that help organizations stay ahead in a rapidly evolving landscape.

‍