{"id":4471,"date":"2025-03-31T10:55:54","date_gmt":"2025-03-31T17:55:54","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/microsoft-copilot\/blog\/?post_type=copilot&p=4471"},"modified":"2025-03-31T10:57:59","modified_gmt":"2025-03-31T17:57:59","slug":"whats-new-in-copilot-studio-march-2025","status":"publish","type":"copilot","link":"https:\/\/www.microsoft.com\/en-us\/microsoft-copilot\/blog\/copilot-studio\/whats-new-in-copilot-studio-march-2025\/","title":{"rendered":"What\u2019s new in Copilot Studio: March 2025"},"content":{"rendered":"\n

In this edition of our monthly roundup, we’re recapping the most notable new Microsoft Copilot Studio<\/a> features released in March 2025: <\/p>\n\n\n\n

    \n
  1. Autonomous agents: now generally available<\/a><\/li>\n\n\n\n
  2. Deep reasoning in agents<\/a><\/li>\n\n\n\n
  3. Agent flows in Copilot Studio<\/a><\/li>\n\n\n\n
  4. Generative orchestration: now generally available<\/a><\/li>\n\n\n\n
  5. Model Context Protocol<\/a><\/li>\n\n\n\n
  6. Tools and prompts inside Copilot Studio<\/a><\/li>\n\n\n\n
  7. Open web search<\/a><\/li>\n\n\n\n
  8. Find and install Microsoft-built agents inside Copilot Studio<\/a><\/li>\n\n\n\n
  9. Private preview opportunity: try GPT-4.5 in Copilot Studio<\/a><\/li>\n<\/ol>\n\n\n\n

    1. Autonomous agents: now generally available<\/h2>\n\n\n\n

    Responding instantly to critical events is more vital than ever, especially for organizations operating on a global scale. Whether it\u2019s a finance team managing budget thresholds, a sales team seizing renewal opportunities early, or a frontline team addressing urgent low-supply alerts, timely action drives efficiency and impact.<\/p>\n\n\n\n

    That\u2019s why we\u2019re thrilled to announce the general availability of autonomous agents, designed to keep you proactive by automating responses to critical events. The need for manual checks, scheduled workflows, or complex custom API solutions is gone. Using triggers, you can configure your agents to wait for specific events and execute a set of actions when that event happens. The instructions you provide\u2014written in natural language, not code\u2014add autonomous capabilities to your agent which can then monitor, detect, and react to pertinent events to automatically carry out the workflow you defined.<\/p>\n\n\n

    \"A<\/figure>\n\n\n\n

    These workflows can handle a wide variety of tasks, from simple actions, like notifying users of updates, to more complex automation, such as automatically ordering new equipment for your department when a new employee joins. While these agents run in the background, you\u2019ll maintain full visibility into every action the agent takes through the Activity tab, ensuring transparency and control.<\/p>\n\n\n\n

    With triggers, agents evolve from working with you, to also working for<\/em> you. Autonomous agents dramatically save time for individuals, teams, and entire organizations by automating business processes and getting tasks done across every department.<\/p>\n\n\n\n

    Learn more about getting started with triggers here<\/a>.<\/p>\n\n\n\n

    2. Deep reasoning in agents<\/h2>\n\n\n\n

    On March 25th<\/sup>, CVP Charles Lamanna announced the preview release of deep reasoning for agents<\/a>, which enables agents to handle complex business processes more effectively. With this new release, agents can leverage advanced reasoning models like OpenAI o1, along with your enterprise data, to process information, analyze data, and help you take action in subjective, complex situations.<\/p>\n\n\n\n

    Deep reasoning can be applied in both declarative and autonomous agents\u2014and, in fact, you can build your own deep reasoning agents to solve complex problems specific to your organization and data. There are many ways to use deep reasoning agents\u2019 critical thinking skills, including analyzing intricate patterns in demand forecasting, qualifying and categorizing sales leads, identifying opportunities and providing smarter recommendations, and more.<\/p>\n\n\n\n

    Check out this video for an example demonstration of how deep reasoning can help a team create RFPs and respond to customers more quickly:<\/p>\n\n\n\n

    \n