In today’s business environment, streamlined workflows and reduced manual tasks are essential. Microsoft AI Builder brings the power of advanced automation to routine processes like email handling, document processing, and image management, helping businesses run smarter and more efficiently. With new capabilities, including multi-modal content processing, structured JSON outputs, flexible model selection, Dataverse grounding, and an extensive prompt library, AI Builder elevates agents, apps and automation to the next level of business impact.
Next generation document and image processing with GPT
One of the most game-changing updates in AI Builder is the new multi-modal content processing capability, which allows businesses to handle various data types —including text, document, and images—within a single natural language instruction. This integration greatly simplifies the process of crafting AI actions for intelligent document processing. Unlike traditional machine learning models that require extensive training and expertise, AI Builder’s multi-modal processing can be set up using natural language, and without training data.
Structured JSON outputs now generally available
With AI Builder’s new structured JSON output feature, businesses gain a more deterministic and reliable way to handle generated content. Unlike traditional outputs that might vary in format and structure, JSON outputs are now generated with a consistent predefined schema that you define at design time, ensuring that every result aligns precisely with expected data formats. This determinism in content generation means your automated workflows will produce predictable, structured data every time, and those results will be readily integrated as variables in your Power Automate workflow for downstream processing. This feature is especially beneficial when integrating AI Builder outputs into other systems, as it reduces the need for additional data cleaning or transformation. Whether feeding data into a CRM, database, or custom application, you can ensure that data is generated in a structured and predictable way.
Dataverse grounding is now generally available
The new Dataverse grounding capability empowers Generative AI models with up-to-date, contextually relevant information from your organization’s own data. By employing Retrieval-Augmented Generation (RAG), AI Builder integrates directly with Dataverse to pull in real-time, business-specific knowledge, giving models a deeper understanding of your unique context.
This RAG-enhanced approach allows AI models to dynamically retrieve and incorporate relevant data from Dataverse during processing, enabling Q&A scenarios with accurate responses that are also highly contextualized to your organization. For instance, models can instantly access customer histories, product information, and up-to-the-minute operational data, enriching outputs with knowledge directly grounded in your business reality.
As part of this feature becoming generally available, the capability has been enhanced to support multiple tables, including tables with large amounts of data records.
Model selection: GPT-4o and GPT-4o Mini
AI Builder offers flexibility in model selection, allowing users to choose between the powerful GPT-4o and the cost-effective GPT-4o Mini. This adaptability enables customization based on specific project requirements and resource considerations.
Prompt library
The prompt library feature provides a collection of pre-designed prompts, serving as templates to expedite the creation of AI models. This resource accelerates development and ensures best practices are followed in prompt engineering. Users can modify templates to suit specific needs, adjusting language, tone, and detail to match organizational standards and requirements. The templates cover key areas like document extraction, data transformation, and content generation, making it easy for users to find the right starting point for their intelligent automation goals.
Use cases to get started
With AI Builder, you don’t need to be a coding expert to leverage the power of AI in your daily operations. By creating prompts that can extract information from documents, classify emails, and even analyze images, you can empower your team to work smarter, not harder. AI Builder works hand-in-hand with other Power Platform tools like Power Automate, Copilot Studio and Power Apps, enabling users to create intelligent workflows and applications that are customized to meet the needs of any business.
For example, let’s say your team frequently processes customer inquiries. Using AI Builder and Power Automate, you can design a workflow that analyzes the content of incoming emails, categorizes them by urgency or topic, and even suggests responses. This not only saves time but also keeps communication consistent and efficient. By setting up this automated flow, businesses can stay on top of customer interactions and ensure timely responses.
Are you ready to bring AI to your organization?
The AI Builder Documentation provides a comprehensive guide on setting up AI Builder, configuring models, and integrating it with tools like Power Automate and Power Apps. For step-by-step tutorials, the Microsoft Learn AI Builder Learning Path is an excellent place to start. It covers everything from foundational concepts to advanced use cases, helping users of all levels become proficient in leveraging AI Builder to automate and optimize workflows.
The latest AI experiences in Power Automate are redefining the boundaries of what is possible in enterprise automation—transforming how we optimize and manage business processes to achieve more. Developers can now create advanced automation faster, business analysts can quickly extract, analyze, and optimize critical processes, and IT administrators can seamlessly manage and govern automation at scale. Copilot in Power Automate makes it faster to build solutions that save valuable time and reduce costs, thereby achieving business outcomes. Step into the future with the Power Automate advanced, enterprise-grade intelligent automation solutions.
Build advanced, reliable automations faster with AI
Developers are key to business process innovation. In Power Automate, it is now possible to build automations that utilize AI within cloud flows using generative actions, easily use natural language to create expressions for flows with Copilot for expressions, and incorporate document processing into workflows with next-generation document processing. These features enhance developers’ ability to deliver solutions efficiently and effectively.
Introducing next-generation document processing with GPT
Efficient document management is vital for smooth operations and timely decisions, but traditional AI models require lengthy training and frequent updates. With GPT-4-powered document processing, now available in public preview, you can use natural language to extract and process unstructured data from documents like invoices, medical results, or emails. This next-gen tool handles multi-modal content, automating email, document, and image processing for improved productivity. For makers who want to blend in pro-code or gain greater control, we’ve added the ability to structure outputs using JavaScript Object Notation (JSON) directly inline. Makers can combine multi-modal content with enterprise knowledge from Microsoft Dataverse in their prompts. This feature enables makers to quickly deploy document and image processing directly into existing workflows using natural language instructions.
Transform your automation processes with generative actions
Generative actions allow you to add AI-powered steps to your cloud flows, letting AI reason over enterprise guardrails provided in unstructured content format such as documents and PDFs, and decide the best course of action for complex tasks. For example, with generative actions you can automate conditional approvals based on the content of incoming emails and company policies. This feature, currently in the Early Access Program, is coming soon to public preview, when you will be able to create, edit, test, and run generative actions all from within the cloud flow designer.
Create and edit expressions faster with Copilot
Copilot for expressions, now in public preview, is designed to assist developers and makers in creating or editing complex expressions using natural language. By simply describing what you want to build and referencing the dynamic data in the flow, Copilot translates your prompts into specific expressions in your Power Automate flow, speeding up development and reducing manual coding time.
Monitor and manage at scale with new automation center
Automation center, now generally available, is a central hub for efficient monitoring and troubleshooting experiences for automation processes across Power Automate at scale. The automation center provides comprehensive visualizations that enable you to monitor the health of your automations, quickly detect issues or trends, and troubleshoot problems more efficiently.
Whether you’re a developer, operator, Center of Excellence team member, or business analyst, the automation center provides a centralized view of all automation activities. Now generally available, it features a user-friendly interface with dashboards that show recommendations, the health status of work queues, and desktop flow activity. Additionally, new views for execution logs, performance metrics, and integrated agents are now available in public preview.
To learn more and to get started, read our Automation center documentation.
Improve robotic process automation (RPA) reliability using repair with Copilot
Repair with Copilot, now in public preview, simplifies resolving user interface (UI) control issues in both attended and unattended RPA with Power Automate for desktop. By proactively providing solutions to common automation issues, such as notifying the right person in the automation center, repair with Copilot reduces downtime for RPA scenarios.
Example of using repair with Copilot for unattended RPA:
Example of using repair with Copilot for attended RPA:
Start your journey into a new era of automation and AI
Are you ready to bring your organization into the future with the latest AI capabilities in Power Automate? Get started with a free trial or compare plans, join our sessions below at Microsoft Ignite 2024, and read about other exciting announcements for Microsoft Power Platform.
Power Automate
Find the right low-code automation plan for your business.
Traditionally, attended automation takes over users’ mouse, keyboard, and screen, halting their current activity. Picture-in-Picture in Power Automate for desktop lets you run attended desktop flows within a virtual window that mirrors your desktop. It allows multitasking, improves user experience, and increases productivity.
You no longer need to wait for the flow to finish before continuing your work!
To execute in picture-in-picture mode from the Power Automate console, select your flow, open the command bar, and click on Run in picture-in-picture.
Alternatively, enable the Run in picture-in-picture flow property to ensure your flow always operates in this mode when initiated locally via the console or its Run URL.
Initiate a desktop flow from a cloud flow using picture-in-picture mode. Use the Run a flow built with Power Automate for desktop cloud action, set Run Mode to Attended, and in the Advanced parameters, choose Attended Mode as Picture-in-picture.
To troubleshoot a desktop flow with picture-in-picture, enable this option in the designer and run your tests. This helps confirm the flow will work seamlessly in production.
To supervise the flow executions in picture-in-picture mode, navigate to desktop flow runs in the portal and apply a filter by run mode.
In an earlier blog, we showed you how the Microsoft Customer and Partner Solutions (MCAPS) organization is optimizing internal processes using Copilot for automation and process mining in Microsoft Power Automate. In this blog, we explore how another Microsoft division is using the same tools to get similar results.
Streamlining security access requests
Microsoft Customer Experience & Success (CE&S) is one of the largest customer support teams in the world. With over 17,000 employees worldwide, CE&S is responsible for shaping the strategy, design, and implementation of Microsoft’s end-to-end customer experience.
For one of their projects, CE&S focused on their Just in Time (JIT) security process used to grant access to resources. “Leveraging the process mining capabilities in Power Automate, we wanted to explore ways to improve our responsiveness – without compromising on security,” says Kirk McNesby, Senior Business Process Manager at Microsoft.
In just one week, CE&S successfully deployed process mining and began gathering insights. “With process mining in Power Automate, we were able to easily input data and immediately jump behind the wheel to do meaningful exploration,” says Kirk. “We had no prior knowledge or training. We were ingesting data and learning how to use the tool – all at the same time.”
To begin using process mining, over 14GB of event log data (consisting of SR events and JIT security logs) was loaded into the tool. The team was particularly impressed with the easy-to-use interface. “We liked the out of the box presentations. Variances were presented in a clear, visual format and filtering worked really well with our data,” says Kirk.
The team used the filtering capabilities within process mining to quickly segment access requests by type and looked for patterns that would contribute to optimization. This strategy revealed bottlenecks in a specific access request for users acting as backup support on cases when the main support engineer was unavailable.
By automating approvals for this scenario, the team estimated that they could automate up to 54,000 approval requests per year, saving users 13,200 hours of wait time. As Kirk adds, “The process mining capabilities in Power Automate were critical to achieving insights this quickly.”
Continue reading to learn about new ways to automate, from outcome-based AI flows that simplify complex processes, to multi-modal AI recording that makes UI automation more natural, accessible, and resilient.
Power Automate for desktop comes with new great additions in 2024 April’s release, including UI elements collections, Copilot for flow descriptions, multiple new actions in several modules, and more!
In the fast-paced world of marketing and sales, efficiency and agility are key. That’s why the Microsoft Customer and Partner Solutions (MCAPS) organization has embarked on an exciting journey to better understand internal processes by monitoring them, uncovering inefficiencies, and optimizing them to excellence. The threefold approach using combined capabilities of Power Automate, Process Mining and Copilot have become a staple, internally.
The Power Automate Process Mining solution helps the organization get the full lifecycle visibility into their processes, understand the inefficiencies and targeted improvements to drive via process alignments and automation. Microsoft’s Process Mining offering is easy to use with powerful features including rework detectors, root cause analysis, custom reporting, and seamless integration and automation. The power of Copilot and general ease of use of the platform allow the team to not only scale across all of its processes quickly, but also augments the products owner toolkit to drive process optimization as a critical lever for accelerating digital transformation.
Given the large coverage of the customer base, Marketing execution is inherently complex, involving multiple roles and activities. By focusing on the demand generation process step, the MCAPS team was able to delve into the nested processes and uncover areas for improvement.
By utilizing Power Automate Process Mining, the team gathered event log data, transformed it using Power Query, and completed data attribution. The resulting process map was then analyzed with the help of Copilot, which provided insights and identified bottlenecks that could be addressed through automation.
The analysis revealed that the average duration of this process component was ~60 days, with five different variants spanning across 33 activities. Notably, 20% of the cases required rework activities, indicating a significant area for potential optimization. Roles such as event lead marketing Operations and Integrated Marketing Manager were found to be the most involved in the process, contributing to 80% of the executional activities. By zooming in on individual activities, the team discovered that the intake for content creation averaged 8 days to complete, accounting for about 10% of the total time spent in the process.
With the insights provided by Copilot, the team identified the review loop as the longest-running activity and a major bottleneck. But Copilot didn’t stop there; it went a step further by leveraging Power Automate to automate the process steps, providing improvement suggestions along the way.
The team chose to create digital process flows, and Copilot seamlessly handed it off to Power Automate with a prompt to build the automation. As the flows were built out, Power Automate Copilot continued to refine then until they were ready to be published.
Through iterative process mining and the acceleration provided by Copilot’s automation recommendations, the team projects an outcome of reducing the timeline from 12 weeks to 8 weeks.
“With the recommendations using Power Automate with Process Mining, we project accelerated time in our demand generation process from twelve to eight weeks. Copilot has given us a lot of confidence as it allows us to scale process simplification as the tip of the spear for our digital transformation!”, says Sandeep Bhanot, Corporate Vice President within Microsoft Customer & Partner Solutions.
This case study is just one example that showcases the power of AI in transforming organizational processes. Within Microsoft Customer and Partner Solutions organization, process mining is being scaled to all business-critical sales processes to realize accelerated efficiencies through process simplification, improved seller productivity, increased compliance and accelerated time to value for Microsoft and our Customers. The team is projecting at least $20 million+ labor productivity improvement across these process areas.
By embracing Process Mining with AI-powered Copilots, businesses can achieve greater efficiency and agility, paving the way for innovation and success.
How can businesses streamline their processes and optimize their performance with process mining? Microsoft Customer and Partner Solutions organization has been using Power Automate Process Mining with Copilot to analyze, improve, and monitor their sales processes. The results have been impressive for their marketing demand generation process. Read on to learn how they did it, and how you can benefit from Power Automate Process Mining too.
The enterprise journey toward operational excellence is ongoing, and the adoption of hyperautomation has become a pivotal milestone. Microsoft Power Platform stands at the forefront of this movement, offering a suite of tools that transform the way businesses approach digital transformation at scale – and Microsoft Power Automate is a key accelerator.
Imagine a world where every repetitive task, every mundane process, and every time-consuming operation is transformed into a symphony of automated actions, working in perfect harmony to deliver results at lightning speed. This isn’t just a fantasy; it’s a reality that Power Automate can bring, and it’s revolutionizing the way enterprises operate on a global scale.
Watch the following overview video or continue reading for more details!
Optimizing with precision
Take, for example, a large insurance company bogged down by the weight of its claims process. With the magic of Copilot and process mining in Power Automate, data is ingested from Microsoft Azure Data Lake. The data is analyzed, insights are provided, bottlenecks are identified, and recommendations from Copilot to create an app or automation moves you to action.
Watch the video below to go deeper or continue reading!
Leveraging the power of AI
But why stop there? Power Automate doesn’t just automate; it hyperautomates. It takes the data from process mining and help crafts a late payment prediction AI model that can foresee issues before they arise. This predictive prowess is akin to having foresight, enabling better decision-making and resource allocation that can save time and money.
Watch the video below to go deeper or continue reading!
The approval symphony
And let’s not forget the settlement approval process, often a maze of documentation, is now simplified with task mining. Power Automate, with its task mining capabilities, records each step and transforms them into a process map that’s as clear as day. It then guides the creation of an automation that uses AI, RPA, and API-based automation together to connect data to SAP.
Watch the video below to go deeper or continue reading!
Deploying solutions at scale
Now we move from proof of concept (POC) to enterprise-wide deployment, where IT is empowered with robust Application Lifecycle Management (ALM) that extends across Power Platform. With custom dashboards, automation, apps, and more you can visually track and act on the transformative impact of hyperautomation.
Watch the video below to go deeper or continue reading!
Embrace the future of productivity
Hyperautomation with Power Automate is not just about adopting new technology; it’s about embracing a future where efficiency and productivity are paramount. Let’s embark on this journey together, leveraging the power of hyperautomation to achieve a new standard of excellence.
The enterprise journey toward operational excellence is ongoing, and the adoption of hyperautomation has become a pivotal milestone. Microsoft Power Platform stands at the forefront of this movement, offering a suite of tools that transform the way businesses approach digital transformation at scale – and Microsoft Power Automate is a key accelerator.
Introducing a new data governance feature for desktop flows that allows administrators to control when desktop flow run action logs are captured or disable them completely
Power Automate for desktop comes with new additions in 2024 March’s release, including new functionalities for Power Fx enabled desktop flows, a new Excel action, and more.
General availability of auto-claim for Power Automate licenses, a feature that simplifies license management for admins and enhances the user experience.
Power Automate for desktop’s March release includes major updates for Power Fx enabled desktop flows (preview). IntelliSense capabilities, a revamped variable picker and a dedicated function picker assist makers in creating complex functions with minimal effort.
Microsoft Loop is a powerful productivity tool that enables collaborative work and flexible information organization. It provides teams with a shared workspace where they can create and collaborate on content such as notes, tasks, and files. Loop integrates seamlessly with Microsoft Power Automate, allowing users to automate repetitive tasks. By creating rules, you can trigger specific actions based on conditions, saving time and effort. For instance, you can set up a rule to send an email notification to your team whenever a new task is added to a project table in Loop. Overall, Loop enhances teamwork and streamlines communication by combining a shared workspace with automated workflows.
