The role of agentic AI has grown rapidly over the past several months as organizational leaders seek ways to accelerate AI Transformation. We firmly believe that Agents + Copilot + Human Ambition can deliver real AI differentiation for our customers. By putting the autonomous capabilities of an agent to work for their businesses, our customers are unlocking AI opportunity to realize greater value. The recent introduction of Microsoft 365 Copilot Chat is delivering on our promise of “Copilot for all” by providing frontline workers with a free, secure and enterprise-ready AI chat interface. Our customers are building their own custom agents with the no-code, low-code features of Microsoft Copilot Studio, allowing citizen and professional developers to extend the capabilities of Copilot and deliver on the unique needs of their industry. We also offer the best prebuilt agent framework right out-of-the-box, such as Sales Agent that works autonomously to help sellers build pipeline and close more deals with greater speed. Similarly, we recently announced general purpose reasoning agents — such as Researcher and Analyst — and invite all of our Microsoft 365 Copilot users to try these in their environments.

It is exciting to see how agents are driving pragmatic AI innovation for our customers by increasing productivity, creating capacity across every role and function and improving business processes. Below are a few highlights from the past quarter that underscore the impact of an agentic AI approach — from improving employee experiences to streamlined workflows and significant cost savings.

Agentic service management software provider Atomicwork leveraged Azure AI Foundry to create Atom — an AI agent that transforms the digital workplace experience for employees and automates service delivery. Adopters of this agentic management platform recognize significant benefits, such as reduced operational costs and increased employee satisfaction, with one customer achieving a 65% deflection rate within six months of implementation and projections of 80% by the end of the year. Integration within Microsoft Teams and other enterprise tools have further streamlined service delivery, allowing employees easier access to information and support. The company’s AI-driven approach has resulted in a 20% increase in accuracy and 75% reduction in response latency when compared to competing solutions.

To support employees as they manage the high demand of internal requests and to create a more satisfying work environment, BDO Colombia used Copilot Studio and Power Platform to develop BeTic 2.0 — an agent that centralizes and automates key payroll and finance processes. The agent reduced operational workload by 50%, optimized 78% of internal processes and showed 99.9% accuracy in managed requests. It also helped reduce duplicative work, optimized workflows, improved the employee-client experience and continues to serve as a competitive differentiator for the company in the market.

Dow is using agents to automate the shipping invoice analysis process and streamline its global supply chain to unlock new efficiencies and value. Receiving more than 100,000 shipping invoices via PDF each year, Dow built an autonomous agent in Copilot Studio to scan for billing inaccuracies and surface them in a dashboard for employee review. Using Freight Agent — a second agent built in Copilot Studio — employees can investigate further by “dialoguing with the data” in natural language. The agents are helping employees solve the challenge of hidden losses autonomously within minutes rather than weeks or months. Dow expects to save millions of dollars on shipping costs through increased accuracy in logistic rates and billing within the first year.

As a leading provider of sustainable energy in Belgium, Eneco serves over 1.5 million customers. Facing performance issues with their existing chatbot, Eneco developed a new AI-driven agent using the no-code, graphical interface in Copilot Studio. This multilingual agent was deployed on the company website in just three months, integrating seamlessly with its live chat platform. The new agent manages 24,000 chats per month — an increase of 140% over the previous solution — and resolves 70% more customer conversations without a handoff to a live representative. For requests that do require escalation, the agent provides an AI-generated summary of the conversation for a more optimized call center experience.

To reimagine trend forecasting and consumer marketing, The Estée Lauder Companies Inc. leveraged Copilot Studio to develop ConsumerIQ — an agent that centralizes and streamlines consumer data to enable instant access to actionable insights. Using natural language prompts, the agent reduced the time required for marketers to gather data from hours to seconds, while accelerating decision-making and helping prevent duplicated research. Together with Azure OpenAI Service and Azure AI Search, teams can gather data, identify trends, build marketing assets, inform research and move products to market faster.

To create proposals and streamline knowledge retrieval and organization, Fujitsu leveraged Azure AI Agent Service within Azure AI Foundry to develop an intelligent, scalable AI agent for sales automation. The agent boosted productivity of sales teams by 67% while addressing knowledge gaps and allowing them to build stronger customer relationships. This transformation allowed teams to shift from time-intensive tasks to strategic planning and customer relationship building, while also supporting new hires with product information and strategic guidance.

To reduce manual tasks and help employees deliver exceptional experiences, global baker Grupo Bimbo established its first ever technology Center of Excellence. Using Power Platform solutions and Copilot Studio, teams created 7,000 power apps, 18,000 processes and 650 agents to reduce busy work and enhance consumer service. By automating low-value tasks, the company saved tens of millions of dollars annually in development efforts and operational efficiencies. Grupo Bimbo also migrated to Azure for its AI capabilities, scalability, security and rapid time to market for apps.

KPMG developed Comply AI — an agent that helps identify environment, social and governance compliance. Using Microsoft AI technologies, the agent helps identify relevant obligations, generate statements in natural language, assess control effectiveness and redraft control descriptions. This has already helped one of its customers achieve 70% improvement in Controls and Risks descriptions, an 18-month reduction in compliance program timelines and a 50% cut in ongoing compliance efforts. KPMG is also using an agent to support new hires by providing templates and historical references to speed up the onboarding process and reduce follow-up calls by 20%.

To significantly enhance its customer service operations, T-Mobile used Power Apps to develop PromoGenius — an app that combines promotional data from multiple systems and documents to keep frontline retail employees equipped with the latest promotional information for customers. Using Copilot Studio, the company embedded an agent in the app so customer service representatives can instantly search for technical details from device manufacturers and create a customer-facing view of product information in a fraction of the time a manual search would require. PromoGenius is the second most-used app in the company, with 83,000 unique users and 500,000 launches a month.

Using Copilot Studio, Virgin Money developed Redi — an agent serving as a digital host within a mobile app for credit card customers. The agent, trained to understand colloquialisms and even known to tell jokes, serves as a secure way for customers to get answers quickly while understanding appropriate context for when a live representative is required. The company views this agent as a tool for its employees to better serve customers, handling over one million interactions, boosting customer satisfaction and becoming one of the bank’s top-rated service channels. Redi now supports customers across Virgin Money’s digital platforms and has been recognized with an industry award for AI in financial services.

To help employees navigate countless procedures, evolving regulations and complex banking systems, Wells Fargo built an agent through Teams to ensure fast and accurate customer support. Using large language models, the agent provides instant access to guidance on 1,700 internal procedures across 4,000 bank branches. Employees can now locate needed information faster without support from a colleague, with 75% of searches happening through the agent and response times reduced from 10 minutes to 30 seconds.

There is immense potential for agents to drive AI-first differentiation for organizations everywhere, especially when combined with Copilot and human ambition. At Microsoft, we believe AI is about empowering human achievement, unlocking potential and democratizing intelligence for as many people as possible with our cloud and AI solutions — as evidenced by these AI Transformation stories of more than 700 customers and partners. I look forward to partnering with you to unlock continued AI opportunity, drive pragmatic innovation and realize meaningful business impact for your organization.

The post How agentic AI is driving AI-first business transformation for customers to achieve more appeared first on Microsoft AI Blogs.

That’s enough text to describe an image generation model for now—check out the video below and see GPT-image-1 in action:

Key features and improvements

GPT-image-1 builds upon the strengths of its predecessor, DALL-E, with significant enhancements:

• Granular instruction response: GPT-image-1 excels at understanding and executing detailed instructions, ensuring precise and accurate image generation.
• Text rendering: The model reliably renders text within images, enhancing its utility in creating educational materials and storybooks.
• Image input acceptance: Users can upload images and provide text prompts to generate new images or edit existing ones, offering a versatile tool for creative projects.

GPT-image-1 capabilities

GPT-image-1 supports multiple modalities and features:

• Text-to-image: Generate images from text prompts, similar to text2im in ChatGPT DALL-E.
• Image-to-image: Create new images from user-uploaded images and text prompts, a feature not available in ChatGPT DALL-E.
• Text transformation: Edit images using text prompts, akin to the transform feature in ChatGPT DALL-E.
• Inpainting: Edit images with text prompts and user-drawn bounding boxes, similar to inpainting with DALL-E.

Use cases

GPT-image-1 is designed to power a wide range of applications, including:

• Educational material generation: Create visual aids and interactive content for learning.
• Storybook creation: Generate consistent and engaging illustrations for children’s books.
• Game production: Develop game assets with consistent style and character design.
• UI designs: Design user interfaces with photorealistic elements and coherent layouts.

Technical specifications

• Resolution: Supports images with a minimum width and height of 1024 pixels, including 1024×1024, 1024×1536, and 1536×1024 resolutions.
• API integration: Gpt-image-1 is available via API. 

Safety and moderation

GPT-image-1 is built with a robust safety stack from OpenAI, including c2pa and input/output moderation. Azure AI specific items include: Content safety and abuse monitoring.

Get started today

Unleash your creative potential with GPT-image-1, the cutting-edge technology designed to elevate your artistic projects. With capabilities that support high-resolution images and seamless API integration, you can effortlessly bring your visions to life. Experience the stunning photorealistic elements and coherent layouts that will set your projects apart. Use ethical and safe image generation with GPT-image-1’s robust moderation systems, making it the clear choice for all your creative needs.

Discover the transformative power of GPT-image-1 today.

The post Unveiling GPT-image-1: Rising to new heights with image generation in Azure AI Foundry appeared first on Microsoft AI Blogs.

To maximize AI’s potential, it’s important to first develop cohesive strategies that align AI adoption with the core mission of your institution, ensuring long-term impact and responsible evolution. Microsoft is committed to helping you define your institutional strategy and innovate with confidence. The Cloud AI Adoption for Higher Education e-book contains structured guidance that prepares organizations to adopt AI at scale, beginning with key operational processes for creation of a wholistic AI strategy. This includes establishing institutional AI leadership, aligning your plan to institutional goals, prioritizing the most valuable AI use cases, and finally identifying the right AI technology strategy for the institution.

Let’s take a closer look at how institutions can develop an AI strategy that aligns with their specific needs and capabilities, reviewing key considerations to help strike the right balance between speed, simplicity, and customization in achieving their desired outcomes.

Key considerations for AI strategy in higher education

When defining an AI technology strategy, you’ll likely need to weigh trade-offs between ease of implementation and the flexibility to build fully customized solutions. Low-code tools provide speed and accessibility, ideal for fast deployment and integration with existing systems but offer limited customization.

Pro-code solutions, on the other hand, enable deep innovation through advanced orchestration, data governance, and full code access but take more time and technical expertise to configure. Comprehensive AI solutions from Microsoft span this spectrum, offering tools that support both rapid deployment as well as deeply customizable development paths.

Deploy AI quickly with out-of-the-box tools

You can empower faculty and staff with AI tools that require minimal technical expertise or setup. Out-of-the-box solutions like Microsoft 365 Copilot and Copilot Chat can make it easy to boost individual productivity with AI-powered support for writing, analyzing, and collaborating across apps in Microsoft 365. These tools can also streamline workflows in areas like security and operations, embedding intelligence directly into the applications faculty and staff already use. For more tailored experiences, you can extend and customize capabilities using the graphical development environment in Microsoft Copilot Studio—building role-specific agents that address unique campus needs with ease.

Check out how the University of South Florida (USF) drives innovation and acceleration with Copilot.

Customize AI solutions to fit your institution’s goals

You can tailor AI adoption to your specific goals using Microsoft Platform as a service (PaaS) solutions, choosing between fully managed services for ease of deployment or infrastructure-level control for advanced research. With tools like Copilot Studio and Azure AI Foundry, you can build and deploy custom AI agents or applications—without the burden of managing infrastructure.

For example, retrieval-augmented generation (RAG) can power AI agents that support tutoring and research by synthesizing timely information into clear, accurate explanations. You can also fine-tune generative AI models to personalize learning and streamline workflows, while maintaining privacy, security, and responsible use through Microsoft Azure AI Content Safety. These flexible options empower universities to innovate at scale and align AI capabilities with academic, operational, and research priorities.

Discover how Babson College meets the demands of its evolving strategic goals through Azure AI.

Accelerate research and scale AI workloads with full control

Microsoft infrastructure as a service (IaaS) AI solutions empower you to take on compute-intensive workloads using scalable, cost-effective cloud resources—enabling reproducible research while helping to manage AI computing costs. Tools like Microsoft Azure CycleCloud, Batch, and Kubernetes support model training and orchestrate complex workloads for advanced simulations, including climate modeling and biomedical research.

These platforms also improve collaboration and data sharing across institutions, enabling analytics and AI-powered insights in fields such as genomics, materials science, and social research. Built on trusted and secure cloud infrastructure, these solutions support compliance with regulatory standards—allowing researchers to innovate efficiently and responsibly.

Learn how the University of Nottingham optimizes AI computing costs while ensuring research reproducibility through accessing AI infrastructure.

Combine solutions to match your goals and resources

It’s important to acknowledge that the right AI technology strategy isn’t necessarily one path, but potentially the right combination of paths. In many cases, the most effective strategy combines multiple approaches—software as a service (SaaS), PaaS, or IaaS solutions. A hybrid strategy allows you to balance speed and scalability with customization and control—selecting ready-to-use tools for common tasks while developing tailored solutions for high-impact use cases. Trade-offs may need to be made between out-of-the-box value and deep customization, depending on the paths you select. Microsoft AI solutions give you the freedom to mix and match capabilities in ways that best support the mission, resources, and technical readiness of your institution.

Begin your AI journey today in higher education

As AI becomes an integral part of the educational landscape, the question for leaders in higher education is no longer if to adopt AI—but how to do so in a way that aligns with your institution’s values and long-term goals. By taking a thoughtful and responsible approach, you can harness AI not only to enhance learning and operations but also to create a lasting competitive advantage. Now is the time to chart a strategic course forward. Get started with the Cloud AI Adoption for Higher Education e-book to develop an AI strategy and implementation plan.

Explore these additional resources to learn more:

• Microsoft Cloud Adoption Framework for Azure
• Establish an AI Center of Excellence
• Comprehensive guidance for AI adoption and architecture

The post Best practices for optimizing AI strategy in higher education appeared first on Microsoft AI Blogs.

As AI becomes more deeply embedded in workflows, having a secure foundation from the start is essential for adapting to new innovations with confidence and ease. New regulations like the European Union AI Act demand greater transparency and accountability, while threats like shadow AI and adversarial attacks highlight the urgent need for robust governance. 

Getting Started with AI Applications

Microsoft Guide for Securing the AI-Powered Enterprise

Read today

To help organizations navigate these challenges, Microsoft has released the Microsoft Guide for Securing the AI-Powered Enterprise Issue 1: Getting Started with AI Applications—the first in a series of deep dives into AI security, compliance, and governance. This guide lays the groundwork for securing the AI tools teams are already exploring and provides guidance on how to manage the risks associated with AI. It also dives into some unique risks with AI agents and how to manage these. Here’s a look at the key themes and takeaways. 

Securing AI applications: Understanding the risks and how to address them 

AI adoption is accelerating, bringing remarkable opportunities but also a growing set of security risks. As AI becomes more embedded in business decision-making, challenges such as data leakage, emerging cyber threats, and evolving and new regulations demand immediate attention. Let’s explore the top risks and how organizations can address them. 

Data leakage and oversharing: Keeping AI from becoming a liability 

AI thrives on data. But without guardrails, that dependence can introduce security challenges. One major concern is shadow AI—when employees use unapproved AI tools without oversight. It’s easy to see why this happens: teams eager to boost efficiency turn to freely available AI-powered chatbots or automation tools, often unaware of the security risks. In fact, 80% of business leaders worry that sensitive data could slip through the cracks due to unchecked AI use.² 

Take a marketing team using an AI-powered content generator. If they connect it to unsecured sources, they might inadvertently expose proprietary strategies or customer data. Similarly, AI models often inherit the same permissions as their users, meaning an over-permissioned employee could unknowingly expose critical company data to an AI system. Without proper data lifecycle management, outdated or unnecessary data can linger in AI models, creating long-term security exposure. 

Addressing the risk

• Implement clear AI usage policies so employees stick to vetted, secure tools.
• Allow AI’s to access data only based on the user’s credentials and use role-based access controls (RBAC) to manage that data access.
• If an AI does need to use its own credentials to access resources, only grant AI access to people who should have access to those resources.
• Automate data retention policies to prevent sensitive information from persisting beyond its intended use.

Emerging threats: The expanding landscape of AI vulnerabilities 

As AI evolves, so do the threats against it. According to Gartner® Peer Community, among 332 participants, a staggering 88% of organizations are concerned about the rising risk of indirect prompt injection attacks,³ with attackers developing new ways to exploit vulnerabilities. One of the most pressing concerns is prompt injection attacks—where malicious actors embed hidden instructions in input data to manipulate AI behavior. A cleverly worded query, for example, could trick an AI-powered chatbot into revealing confidential information. 

Beyond direct attacks, AI systems themselves can introduce security risks. AI models are prone to hallucinations (generating false or misleading information), unexpected preferences (amplifying unfair decision-making patterns), omissions (leaving out critical details), misinterpretation of data, and poor-quality or malicious input leading to flawed results. A hiring tool, for example, might favor certain candidates based on biased historical data rather than making fair, informed decisions. 

Addressing the risk

• Validate and sanitize input data before AI processes it to prevent manipulation.
• Limit AI’s access to sensitive information and implement identity verification.
• Design (and secure) the end-to-end (E2E) business process, not the AI component.
• Secure the AI component by imagining replacing it with a new hire fresh out of school. What would you do to make your process robust against it making mistakes?
• Use robust monitoring, validation, and oversight to ensure AI operates securely and responsibly.
• Leverage commercial AI tools with built-in safeguards like bias detection, input sanitization, and access controls to reduce risks while supporting business goals.

Compliance challenges: Navigating the complex AI regulatory landscape

Beyond security, compliance is another major hurdle in AI adoption. Over half of business leaders (52%) admit they’re unsure how to navigate today’s rapidly evolving AI regulations.² Frameworks like the European Union AI Act, General Data Protection Regulation (GDPR), and Digital Operational Resilience Act (DORA) are rapidly evolving, making compliance a moving target. Organizations must establish clear governance and documentation to track AI usage, decision-making, and data handling, reducing the risk of non-compliance. Digital resilience laws like DORA require ongoing risk assessments to ensure operational continuity, while GDPR mandates transparency in AI-powered decisions like credit scoring and job screening. Misclassifying AI risk levels—such as underestimating the impact of a diagnostic AI tool—can lead to regulatory violations. Staying ahead requires structured risk assessments, automated compliance monitoring, and continuous policy adaptation to align with changing regulations. 

Addressing the risk

• Align AI governance with evolving regulations like DORA through risk assessment, testing, and monitoring.
• Keep detailed AI records to ensure compliance and responsible use.
• Use AI-powered tools to monitor compliance with GDPR and HIPAA, reducing risks like data drift and unauthorized access.
• Audit AI decisions to ensure fairness, transparency, and regulatory compliance.
• Classify AI risks clearly and stay updated on evolving regulations to maintain compliance. 

The next frontier: Unique challenges in securing agentic AI 

The pace of AI growth is staggering, with AI capabilities doubling every six months. Organizations are rapidly adopting more autonomous, adaptable, and deeply integrated systems to tackle complex challenges. 

One of the most significant developments in this shift is agentic AI—a new class of AI systems designed to act independently, make real-time decisions, and collaborate with other AI agents to achieve complex objectives. These advancements have the potential to revolutionize industries, from optimizing energy grids to managing fleets of autonomous vehicles.  

But with greater autonomy comes greater risk. Overreliance on AI outputs, cyber vulnerabilities, and reliability concerns all need to be addressed. As these systems integrate deeper into operations, strong security, oversight, and accountability will be essential. 

Building a secure AI future: A responsible AI adoption playbook 

AI’s transformative power comes with inherent risks, requiring a proactive, strategic approach to security. A Zero Trust framework ensures that every AI interaction is authenticated, authorized, and continuously monitored. But security isn’t something that happens overnight—it requires a phased approach. 

Microsoft’s AI adoption guidance, part of the Cloud Adoption Framework for Azure, provides a structured path for organizations to follow and is clearly outlined in the Microsoft Guide for Securing the AI Powered Enterprise Issue 1: Getting Started with AI Applications. This guide offers a starting point for embracing the cultural shift needed to secure AI with clarity and confidence.  

Cross-team collaboration, employee training, and transparent governance are just as essential as firewalls and encryption. By embedding security at every stage, breaking down silos, and fostering trust, organizations can confidently navigate the AI landscape, ensuring both innovation and resilience in a rapidly evolving world. 

Learn more 

• Guide for Securing the AI Powered Enterprise Issue 1: Getting Started with AI Applications.
• Get the playbook: AI Adoption Guidance.
• Read the e-book: Grow Your Business with AI You Can Trust.

¹Microsoft internal research, February 2025 

² ISMG, First Annual Generative AI Study: Business Rewards vs. Security Risks.

³ Gartner Peer Community Poll: If your org’s using any virtual assistants with AI capabilities, are you concerned about indirect prompt injection attacks?

GARTNER is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally and is used herein with permission. All rights reserved. 

The post Securing AI: Navigating risks and compliance for the future appeared first on Microsoft AI Blogs.

The post AI updates: 2025 Work Trend Index reveals a new kind of organization — plus the latest on Microsoft 365 Copilot appeared first on Microsoft AI Blogs.

The 2025 Work Trend Index Annual Report is designed to prepare leaders and employees for this shift. As in previous years, it draws on a large global survey, Microsoft 365 telemetry and LinkedIn hiring and labor trends. New this year are insights from AI-native startups, economists, scientists and academics — all pointing to a seismic shift already underway. In fact, 82% of leaders say this is a pivotal year to rethink core aspects of strategy and operations.

The data reveals the emergence of a new kind of organization: the Frontier Firm — built around intelligence on tap, human-agent teams and a new role for everyone: agent boss. While the shift ahead is profound, human ambition, creativity and ingenuity will continue to create new economic value and opportunity. In fact, 71% of workers at these firms say their company is thriving, compared to just 37% globally.

You can buy intelligence on tap

Imagine if you knew, before the internet took off, just how much it would reshape business. That’s where we are with AI. Intelligence is no longer bound by headcount or expertise. It’s an essential durable good: abundant, affordable and scalable on-demand. As economic and shareholder pressures grow, this on-demand intelligence offers a new lever for growth — one that can close the growing gap between business demands and human capacity. While 53% of leaders say productivity must increase, 80% of the global workforce reports lacking the time or energy to do their job. And on average, employees are interrupted by a meeting, email or ping every 2 minutes. To bridge this Capacity Gap, 82% of leaders expect to use digital labor to expand their workforce in the next 12 to 18 months.

Digital labor will spur the reinvention of even the most established firms — and the birth of new companies we haven’t even thought of yet. On LinkedIn, top AI startups are hiring at 2X the rate of Big Tech. Much of that talent is flowing out of Big Tech and staying in the startup world, pointing to a deeper shift where innovation — and opportunity — are rising. As incumbents adapt and challengers scale, like we saw in the .com boom, the rules of talent and competition are being rewritten in real time.

Human-agent teams will upend the org chart

As AI continues to democratize expertise, we’re seeing a move from rigid org charts to more fluid, outcome-driven Work Charts. These structures flex with the needs of the business, drawing on the right mix of humans and agents to get the job done. While every function will evolve at a different pace and scale, 46% of leaders say their organization is using agents to fully automate workstreams or business processes — with customer service, marketing and product development as the top AI investment priorities.

To maximize the impact of these human-agent teams, organizations need a new metric: the human-agent ratio. Leaders must ask two critical questions: How many agents are needed for which roles and tasks? And how many humans are needed to guide them? Getting that ratio right will be critical — and task-specific. Organizations will need to consider if there are times when human and digital labor outperform AI alone, when customers prefer a human touch or when society expects people to be responsible for the consequences — like a high-stakes product or finance decision. Whether it’s a customer conversation, a strategic decision or a product launch, knowing how to staff the right mix of humans and agents will define how work gets done — and how success is measured.

Every employee becomes an agent boss

As agents increasingly join the workforce, we’ll see the rise of the agent boss: someone who builds, delegates to and manages agents to amplify their impact and take control of their career in the age of AI. From the boardroom to the frontline, every worker will need to think like the CEO of an agent-powered startup. In fact, leaders expect their teams will be training (41%) and managing (36%) agents within five years.

For those ready to lean in, AI will be a career accelerator — but leaders are ahead. We measured the agent boss mindset across seven indicators — from regular use and trust to career impact. Leaders outpace employees on every measure: 67% are familiar with agents (vs. 40% of employees) and 79% believe AI will accelerate their careers (vs. 67%). But this shift won’t stop at the top. As agents become embedded into daily work, roles across every level and function will evolve — along with the broader workforce. While 33% of leaders are considering headcount reductions, 78% are considering hiring for new AI roles. And 83% say AI will enable employees to take on more complex and strategic work earlier in their careers.

This shift is multifaceted — every industry and role will evolve differently as the technology diffuses across business and society. Just as the internet era created billions of new knowledge jobs — from social media managers to UX designers — the AI era is already giving rise to new roles, with many more to come. Preparing for what’s next is no longer optional. Employees must build AI skills and companies must support them with the right tools and training. This moment calls for honest conversations, intentional communication and real investment in reskilling. The companies that invest now won’t just keep up — they’ll shape what comes next.

Copilot is the new UI for AI

Today we’re announcing the Microsoft 365 Copilot Wave 2 Spring release — designed to power the next era of human–agent collaboration. The Microsoft 365 Copilot app is now your window into the world of agents, with new capabilities for this next phase — driven by more advanced models, adaptive memory and reasoning agents that work alongside you. Updates include:

• Researcher and Analyst agents powered by OpenAI’s deep reasoning models rolling out to customers through the Frontier program — and with our new Agent Store, you can easily find, pin and use agents — from partners like Jira, Monday.com and Miro — or your own custom agents.

• Create brings OpenAI’s GPT-4o AI image generator to work, unlocking design and content creation skills for everyone. Easily modify or customize brand images or generate AI images aligned to your company’s approved brand guidelines and create everything from marketing copy and social assets to newsletter banners, videos and more.

• Copilot Notebooks transforms your notes, documents and data into immediate insights and actions. By grounding Copilot in a notebook containing specific chats, files, meeting recordings and more, it can focus on the most relevant information — all while constantly scanning your source material to update in real time as your data evolves. Notebooks can even create an audio overview of your content with two hosts that walk you through the key points — a fun, flexible way to stay informed.
• Copilot Search is a new AI-powered enterprise search that helps you find what you need instantly with rich, context-aware answers from across your organization’s apps and data. It connects to first- and third-party apps — from ServiceNow to Google Drive, Slack, Confluence, Jira and more — so you get fast, relevant results at work no matter where your data lives.
• New capabilities in the Copilot Control System empower IT pros to enable, disable or block agents for specific users or groups — to help ensure the right agents are being used by the right people.

2025 will be remembered as the year the Frontier Firm was born — the moment companies moved beyond experimenting with AI and began rebuilding around it. Like the digital native companies of a generation ago, they understand the power of pairing irreplaceable human insight with AI and agents to unlock outsized value. We’re giving customers the insight to anticipate what’s next — and the technology to help shape it.

Read the Annual Work Trend Index on WorkLab and visit the Microsoft 365 Blog to learn more about our product announcements. Learn what this year’s Work Trend Index findings mean for small and medium-sized businesses.

For all the blogs, videos and assets related to today’s announcement, please visit our microsite.

The post The 2025 Annual Work Trend Index: The Frontier Firm is born appeared first on Microsoft AI Blogs.

Agentic AI as the hero 

At MWC 2025, Microsoft spotlighted how agentic AI is driving real industry transformation—turning innovation into impact for telecoms. Throughout the event, telecom leaders cited agentic AI as a game-changer, exploring new revenue streams, and automating complex tasks. From hyper-personalized marketing campaigns to proactive network management, these applications are already delivering measurable business value. AI is no longer a pilot or proof of concept; it’s a proven technology, a necessity, for operators to deliver transformative customer experiences at-scale. 

Attendees witnessed demos and theater sessions that showed how AI can assist in the automation of complex tasks, anticipate network bottlenecks, and enhance customer experiences at-scale. Industry leaders consistently emphasized that building trust in AI is paramount, especially as AI becomes more important in supporting decisions previously handled by humans. Microsoft’s approach—rooted in transparency, security, responsible AI and governance—stood out. Microsoft highlighted how integrating Azure’s robust compliance features offers operators and their customers peace of mind, showing that trust and AI innovation are complementary. 

Booming booth and demo showcase 

The Microsoft booth welcomed more than 11,500 unique visitors—interested in learning how Microsoft’s AI portfolio helps drive innovation. The energy was high around our experiential demos, bringing to life real-world applications. Attendees learned how Microsoft Fabric and Azure analytics unifies data to optimize network operations, and powers immersive applications. These showcases highlighted the practical benefits of modern AI-powered technologies. 

Packed theater sessions 

The energy in Microsoft’s theater sessions was electric—overflow crowds packed the aisles to hear how telecom operators are igniting innovation and growth with AI sessions like “Korea Telecom Accelerates AI Adoption” and “AI Ignites Innovation and Growth in Telecom,” where speakers spotlighted how agile customers and partners, such as Accenture, Nokia, and Amdocs, are taking decisive leaps forward in their AI journeys. Each of these sessions echoed a consistent message: whether it’s network modernization or harnessing data, customer and partner momentum is accelerating digital transformation with real business results.

Announcements and customer success stories 

In addition to the success stories shared onstage, Microsoft unveiled news and announcements at MWC 2025 (see my LinkedIn post for details) that reinforce our commitment to accelerating telecom innovation. Microsoft introduced extended agentic AI capabilities for proactively detecting and self-healing network anomalies, demonstrating how operators can achieve near-zero downtime while reducing operational expenses. Another focus was low-code expansion across Microsoft Dynamics 365 and Microsoft Power Platform, empowering telecoms to rapidly build and deploy AI-powered workflows—everything from personalized marketing funnels to simplified customer onboarding experiences. Microsoft also introduced two AI-powered sales agents—Sales Agent and Sales Chat—within Microsoft 365 Copilot to help sales teams close deals more efficiently by automating lead management, customer engagement, and sales tasks. ​ 

Microsoft showcased deepened partnerships with industry leaders like Amdocs and Nokia, geared toward modernizing network infrastructure and elevating customer touchpoints. These collaborations highlight Microsoft’s efforts with partners to tackle the sector’s biggest challenges, such as automating network rollouts, augmenting cybersecurity with AI defenses, and simplifying data monetization. Together, these new announcements reinforce how AI—and especially agentic AI—will continue to transform telecom, enabling telecoms to deliver faster, smarter, and more secure connectivity.

Attendee excitement also came in the form of customer success stories. Telecoms spoke about how agentic AI and other Microsoft AI solutions have already begun reshaping their business: 

• Vodafone described how adopting AI-powered network maintenance cut outages and boosted satisfaction scores.
• KT provided a real-time case study on scaling AI from niche pilot projects to a core tenet of corporate strategy. 

Each story illustrated tangible business value, resonating with attendees seeking proven outcomes.

Partner ecosystem and shared success 

One of the most energizing aspects of MWC 2025 was connecting with Microsoft’s dynamic ecosystem of partners. At this year’s customer and partner reception, conversations buzzed with ideas on how to unlock greater value by combining Microsoft’s cloud and AI capabilities with solutions from trusted partners like Amdocs, Accenture, Nokia, and more. 

The partner spotlight was on innovation—from co-developed analytics dashboards that simplify 5G rollouts to integrated AI modules that accelerate service provisioning. These collaborations underscore how Microsoft’s partnerships with leading telecom Software Development Companies (SDCs) and System Integrators (SIs) are delivering tangible business outcomes. Startups were also a key part of the story. Microsoft for Startups highlighted a new wave of innovative startup SDCs that are helping telecom customers improve customer experience, data insights, and operational efficiency. 

By bringing together Microsoft’s technological depth with the domain expertise of partners, the company is addressing some of the telecom industry’s most pressing concerns—reducing operational overhead, maximizing customer lifetime value, and accelerating innovation. This spirit of community sets the tone for continued innovation.  

What is next 

The momentum behind AI adoption in telecom is accelerating. According to a recent McKinsey report, the focus on scaling AI from one-off pilots to enterprise-wide initiatives will only intensify as data volumes grow and networks become more complex. Microsoft stands ready to help telecoms navigate the next phase through delivery of telecom-specific AI innovations that drive business results: 

• Telco data model in Microsoft Fabric 
  Provides a unified data framework enabling telecoms to run advanced agentic AI workflows across service assurance, customer care, and revenue management.
• Autonomous networks and self-healing operations 
  Leveraging Azure OpenAI Service and the Microsoft generative AI and agentic AI platform, Microsoft envisions proactive, self-healing networks that detect, diagnose, and remediate issues in real time—reducing truck rolls, lowering OPEX, and raising customer satisfaction.
• Open and intelligent Radio Access Network (RAN) optimization 
  Now open source, Project Janus enables dynamic service models and real-time telemetry in Open Radio Access Network (O-RAN) environments—empowering telecoms to build intelligent, AI-optimized RAN architectures using Microsoft’s agentic AI framework to enhance performance, flexibility, and innovation.
• Hyper-personalized customer experiences 
  AI agents within Dynamics 365 Customer Insights, Microsoft 365 Copilot and Amdocs Customer Engagement Platform can unify behavioral and usage data to deliver precise, timely engagements. Telecoms can reduce churn and boost average revenue per user (ARPU) by offering the right products and solutions.
• Expanding revenue beyond connectivity 
  With the embedding of AI-powered interactions directly into customer and developer ecosystems, telecoms can open new business models—such as vertical-specific APIs and AI marketplaces that monetize network APIs, network analytics and agentic automation. 

Microsoft is deeply committed to partnering with telecom operators to co-create the future of connectivity. By aligning agentic AI capabilities with the industry’s most urgent challenges, Microsoft helps telecoms unlock new value—securely, ethically, and at scale. Through strategic collaborations with partners like Nokia, Amdocs, and leading SDCs and SIs, Microsoft delivers scalable, trusted solutions that position telecoms as pioneers in the AI-powered era. 

Until next time, Barcelona 

The transformation of the telecom industry is accelerating—driven by bold investments in AI, deepened partnerships, and a shared commitment to innovation. As the industry moves beyond MWC 2025, one thing is clear: telecom operators are poised to lead in an era defined by intelligent networks, data-driven agility, and customer-centric growth. 

With Microsoft’s agentic AI capabilities, trusted cloud infrastructure, and collaborative partner ecosystem, telecoms can unlock new efficiencies, monetize new services, and deliver seamless experiences that generate lasting business value.

Learn more about how Microsoft is powering the next wave of telecom transformation with AI and agentic automation by visiting our Microsoft for telecommunications Industry Page.

Microsoft for telecommunications

Accelerate telecom transformation in the era of AI

Explore solutions

The post Microsoft’s AI vision shines at MWC 2025 in Barcelona appeared first on Microsoft AI Blogs.

Microsoft and our network of partners can support your journey forward with AI. Unlike many publicly available AI tools, a solution built by a Microsoft partner with Microsoft Azure OpenAI Service keeps your AI interactions private, allowing you to stay in control of your institution’s information. It’s also easier to maintain compliance with data privacy laws like Family Educational Rights and Privacy Act (FERPA), General Data Protection Regulation (GDPR), and Health Insurance Portability and Accountability Act (HIPAA).

Microsoft’s commitment to Trustworthy AI means that AI is secure, safe, and private. Students, faculty, and researchers can also select from a wide array of leading models, with popular options from creators such as OpenAI, Meta, DeepSeek, and more, to find the best fit for their use cases.

In a datasheet on accelerating AI innovation, we highlight how our partner Cloudforce has developed the nebulaONE® solution, powered by Azure OpenAI Service, to simplify access to Microsoft’s most advanced generative AI capabilities. Let’s explore how it empowers institutions to achieve more.

How nebulaONE by Cloudforce aims to bring secure AI to all

Many students and faculty are already using generative AI. But as they adopt their own unsecured AI tools, it creates concerns with IT governance, security, privacy, and data protection, and it limits the ability to scale AI throughout the institution. Cloudforce, a Microsoft Supplier of the Year in 2024, has expertise in building AI solutions to address those concerns, as well as over a decade of experience designing and deploying complex infrastructure and cloud-native apps exclusively on Azure. Cloudforce built nebulaONE on Azure to use its built-in security and privacy features, and the company is engaged with dozens of higher education institutions to fulfill its mission of providing secure AI access for all.

A conversational generative AI gateway, nebulaONE allows students, faculty, researchers, and staff to harness cutting-edge AI models to reimagine learning experiences, accelerate research, protect intellectual property, and drive institutional efficiencies in every department. It includes an intuitive, multimodal chat interface for the AI interactions that are familiar to many, and it provides the ability to develop low-code, task-specific AI agents to drive innovation and efficiency across campus. The nebulaONE platform deploys to your Azure environment, so your data remains private, and you gain the compliance and security protections built into Azure AI services.

“We know leaders in higher education are facing pressure to prepare the workforce of tomorrow to succeed with AI, or risk being left behind,” says Cloudforce CEO Husein Sharaf. “We created nebulaONE to address the most pressing needs of educators and students, with a rapid implementation process that securely enables generative AI use at scale. Our campus-wide management layer keeps institutions in the driver’s seat from a cost and governance perspective, while a simple, custom-branded user interface drives user adoption. Our platform provides the foundation for a flexible AI strategy that evolves as new models and capabilities emerge.”

Cloudforce supports institutional leaders wherever you are in your journey, whether that’s exploring AI for the first time or connecting an AI platform to their full data estate. The Cloudforce team can host workshops to help identify early use cases or provide trainings and prompt-a-thons to reinforce best practices and teach you and your colleagues how to develop your own agents. They also offer assistance with change management and strategic communications to drive campus-wide adoption of nebulaONE and the uses that provide the most value for your institution.

The real-world impact of generative AI in higher education

One success story comes from the University of California, Los Angeles, John E. Anderson Graduate School of Management (UCLA Anderson). Leaders at UCLA Anderson had concerns with using public AI platforms, so they looked for a partner who could deliver a secure, private experience that enabled their priority use cases. They chose to adopt nebulaONE because it’s a fully managed platform that deploys in their Azure environment, and within about two months, they launched a generative AI chatbot to support MBA students with their capstone project.

UCLA Anderson leaders sought to develop and deploy a host of AI-powered chatbots for a variety of specific purposes, and Cloudforce validated use cases and provided hands-on training to empower UCLA staff to independently build them with nebulaONE. The school has now deployed bots to help students register for classes and provide feedback on essays, as well as a forthcoming AI-powered agent that will reduce administrative tasks for career coaches so they can spend more time with the school’s 40,000 alumni. Several months after UCLA deployed the platform, monthly active user rates continued to increase rapidly, growing by 485% from December 2024 to January 2025.

UCLA is hardly alone. A growing number of colleges and universities are deploying nebulaONE to harness the power of AI:

• California State University, Fullerton (Cal State Fullerton) now provides secure, university-managed AI for all students through TitanGPT, as the custom-branded platform is known. They have also started exploring use cases for support solutions, like an agent to streamline HelpDesk support and their IT ticketing system.
• London Business School sought to find a cost-effective, scalable AI solution, with access to a variety of AI foundation models. After a brief demo, they quickly began a full deployment to all 6,000 students, faculty, and researchers—the first in the United Kingdom to do so.
• TerpAI, the chatbot built on the nebulaONE platform at the University of Maryland, acts as a digital assistant and educational resource to help faculty and students brainstorm ideas, analyze data, create study guides, develop lesson plans, and more.
• The platform is nicknamed CWRU AI at Case Western Reserve University (CWRU), where the CRWU community can select between AI models like OpenAI’s ChatGPT 4o or 3.5 Turbo, Meta’s Llama 3.2, and DeepSeek R1. CWRU AI uses AI reasoning to analyze images, PDFs, Word, and Excel files, and the community can deploy chatbots connected to specific data sources for departments or groups.

Learn more about what’s possible with AI

These examples highlight how leaders in higher education can quickly and securely implement generative AI to enhance student services, academic offerings, and operational efficiency. Ready to deploy AI at your school? Discover how nebulaONE can make AI accessible by downloading the datasheet from Microsoft and Cloudforce.

Learn more about how to get started with these resources:

• Explore the features and benefits of nebulaONE.
• Find out how institutions are reimagining student experiences with Azure OpenAI Service.
• Explore the benefits of powering your institution with Azure.
• Discover the AI learning hub, which includes documentation for adopting AI and trainings to improve AI skills for a variety of roles.

¹ Jenay Robert. 2024 EDUCAUSE AI Landscape Study​. Research report. Boulder, CO, US: EDUCAUSE, February 2024.

The post How Microsoft and Cloudforce help institutions innovate with Azure AI appeared first on Microsoft AI Blogs.

Key features and enhancements

Both o3 and o4-mini offer significant improvements on quality and safety while supporting the existing features of o1 and o3-mini and delivering comparable or better performance through its integration and support of the newest APIs and reasoning features.

In addition, they introduce:

• Multiple APIs support: Both models are available in Responses API and Chat Completions API with Responses API supporting seamless integration with multiple tools and enhanced transparency with the reasoning summary as part of the model output.
• Reasoning summary: In the Responses API, both models now support reasoning summary in their output providing more insights into their thinking process. This enhances the explainability and the effectiveness of the resulting actions and tools that leverage the insights for even better outcomes.
• Multimodality: With enhanced vision analysis capabilities in o3, and new vision support in o4-mini, both models expand their reasoning capabilities to process and analyze visual data, extracting valuable insights and generating comprehensive text outputs. This is supported in both Responses API and Chat Completions API.
• Full tools support includes parallel tool calling: Both models are first reasoning models with full tools support like the mainline models including parallel tool calling. Customers can use these to build the next generation of agentic solutions. This capability is supported in both Responses API and Chat Completions API.

New innovations in safety

The o-series reasoning models use deliberative alignment, a training strategy that teaches reasoning models safety specifications and trains them to reason explicitly about these specifications before answering. Both o3 and o4-mini feature the next level of safety improvements within the o-series of models so you can use the power of these models knowing these models are pushing the frontiers on safety as well.

New audio models available 

Azure OpenAI Service has also introduced three powerful new audio models available for deployment today in East US2 on Azure AI Foundry: GPT-4o-Transcribe and GPT-4o-Mini-Transcribe, which are speech-to-text models outperforming previous benchmarks, and GPT-4o-Mini-TTS, a customizable text-to-speech model enabling detailed instructions on speech characteristics. Check out more on the Tech Community blog. 

A new era in AI reasoning

Imagine a world where AI reasoning is not just a tool but a partner in innovation. With the launch of o3 and o4-mini models, we are stepping into that world. These models are not just upgrades; they are gateways to new possibilities, enabling you to push the boundaries of what AI can achieve. Whether you’re solving complex problems, creating seamless workflows, or exploring new frontiers in AI, o3 and o4-mini are here to elevate your journey. Embrace the future of AI reasoning with Azure OpenAI Service and let your imagination soar. Sign up to use o3 and o4-mini in Azure AI Foundry today.

The post o3 and o4-mini: Unlock enterprise agent workflows with next-level reasoning AI with Azure AI Foundry and GitHub appeared first on Microsoft AI Blogs.

Subtle and complex in nature, social inflation impacts profitability by driving up claims payments. Outpacing economic inflation by 1.7% in the United States from 2017 to 2022,¹ social inflation drove a 57% surge in liability claims over the past 10 years,² and led to a USD20 billion increase in commercial auto liability payouts from 2010 to 2019.³ 

In response, insurers are increasingly turning to technology, particularly AI, to help predict trends, enhance underwriting processes, and automate workflows. And now, with the potential application of a cloud-based solution that lets companies explore insights collaboratively, insurers can have more options.  

Helping insurers forge effective long-term technology strategies is core to our vision for intelligent insurance and our work with Microsoft Cloud for Financial Services. In the case of social inflation, cloud and AI can help insurers mitigate the incidence and impact of unpredictable outcomes. 

How cloud and AI can help solve the social inflation challenge 

To improve competitiveness amid a volatile landscape, most insurers have invested in cloud modernization over the past decade. This provides an essential foundation for many critical benefits. For example, solutions built on Microsoft Power BI can track and analyze key performance indicators (KPIs), perform predictive analytics, and generate real-time insights.  

Generative AI is now expanding upon these core benefits to deliver dramatic improvements in productivity, operations, and enhanced workflows. For many firms, the first step in realizing value from generative AI is to adapt Microsoft 365 Copilot, which is integrated seamlessly in Microsoft productivity applications. Drawing on the full scope of Microsoft 365 data within the firm (such as emails, Word and Excel documents, Teams communications, and more) Microsoft 365 Copilot can, for instance, help a claims analyst generate a report that draws on the best available information from research reports, emails, calls, and external data sources.  

Many firms are also building custom agents to address specific use cases on challenges such as streamlining processes, enhancing claims processing workflows, and improving overall productivity. Additional value is also being unlocked as firms transform their unstructured data into structured formats, which enables even more robust predictive models and other advanced data analytics.  

To help address social inflation, generative AI and agent functionality can be used to gain important new insights, such as the following:  

• News monitoring: AI-powered tools can continuously scan and analyze news articles from myriad sources. Thanks to natural language processing (NLP), these tools can identify relevant news items, summarize key points, and highlight trends or significant events. This helps businesses stay updated on industry developments, competitor activities, and market shifts.
• Market insights: AI can process vast amounts of market data, such as economic indicators, consumer behavior patterns, and stock prices. With the power of machine learning algorithms, AI can detect patterns, predict market trends, and offer actionable insights. An AI agent can then present these insights seamlessly in daily workflows, helping decision-makers to make informed choices. 
• Marketing campaigns: AI can track the performance of marketing campaigns by analyzing data from multiple channels such as social media, email, and web analytics. It can measure engagement, conversion rates, and return on investment (ROI), providing real-time feedback on campaign effectiveness. AI agents can also assist in generating reports and suggesting optimizations based on the data. 

Looking forward, these capabilities will be further enhanced with agentic AI—autonomous systems that can plan, adapt, and act to achieve goals, requiring minimal human input as they interact with other tools and environments. For insurers, agentic AI can help in ways such as the following: 

• Automating data collection: Agents can autonomously gather data from multiple sources, helping ensure that information is always up to date.
• Providing real-time alerts: Agents can monitor and respond to specific events or changes in data and send real-time alerts to stakeholders to help ensure prompt responses.
• Generating insights: By continuously analyzing data, agents can identify patterns, correlations, and trends, helping businesses to stay ahead of the curve. 

Confidential computing: Opening new opportunities while protecting sensitive data 

To gain new benefits from more sensitive data, such as claims or confidential information, an additional layer of security and confidence is now offered by Azure confidential computing.

Azure confidential computing creates a protected environment called Azure Confidential Clean Rooms that lets different teams within a company or across multiple companies perform joint data analysis and develop risk models, fraud detection models, and more, using advanced encryption techniques to anonymize data.

Across the financial services industry, confidential computing is increasingly being enlisted to help unlock new opportunities. For example, financial messaging provider Swift is using it in an innovative anomaly detection model, enabling the model to be trained on distributed datasets without copying or moving data from secure locations. Beyond regulated industries like financial services and healthcare, confidential computing is also being used for solutions in retail, manufacturing, and energy sectors. 

In addressing social inflation, confidential computing can help insurers understand the hidden drivers that contribute to rising costs, distort risk assessments, and influence claim outcomes. This involves identifying patterns and connections between contributing factors, such as litigation trends or the influence of social media and viral campaigns that can amplify public sentiment.  

With the power of AI combined with confidential computing, actuaries, underwriters, and claims professionals can use natural language prompts to ask questions of data, semantic search can recognize their meaning and intent, and the system can write coherent responses and deliver appropriate resources. This offers an entirely new and transformative way where, by analyzing interconnected factors, insurers can identify high-risk cases and insights that suggest propensity towards social inflation claims, enabling insurance to develop proactive strategies such as early settlements or policy adjustments in high-risk areas. 

Of course, bringing teams or organizations together to consider the adoption of a broad solution approach like confidential computing involves more than just technology. It also requires structure, guidance, cooperation, and leadership. Microsoft is here to help for the long run and enable such collaboration starting with the industry leading Microsoft Azure cloud platform, and our ongoing commitment to security and responsible AI, and our long-term leadership in insurance and financial services.  

We are excited to partner with insurers and the industry at large to help innovate new solutions and business opportunities through cloud and AI. To get started with your business, reach out to your Microsoft representative and we’ll be happy to explore the possibilities. 

Learn more 

• To learn more about our solutions for insurers, visit our Microsoft Cloud for Financial Services website.
• For a deeper look at confidential computing, read the Azure Confidential Computing Blog.  

Microsoft Cloud for Financial Services

Discover cloud and AI-powered solutions

Learn more

¹ Swiss Re Institute, Social inflation: litigation costs drive claims inflation, September 2024.

² Risk and Insurance, Social Inflation Drives 57% Surge in US Liability Claims Over a Decade, September 2024.

³ Boston Consulting Group, P&C Insurance topics for 2024.

The post Social inflation is costing insurers—here’s how cloud and AI can help appeared first on Microsoft AI Blogs.