As a result, mastering how to instruct AI models effectively is now crucial to unlocking tangible results and boosting productivity in the AI age. New tools are emerging that empower users to fully leverage AI’s potential. One such tool is the AI Prompt Builder, an advanced capability included in Power Automate. This feature allows users to craft precise instructions and choose the most suitable model for each task, whether automating information extraction from e-mails using GPT-4o mini or enabling agents to analyze customer feedback with o1 to identify pain points. Through this prompt engineering interface, organizations can customize AI to behave exactly as needed for their unique business scenarios. 

AI Prompts provide structured instructions to improve AI results 

AI Prompts provide structured instructions that guide large language models (LLMs) to perform specific tasks. This technique, known as instruction tuning, allows businesses to optimize AI-generated responses for more precise, relevant, and useful outputs. By clarifying directives, instruction tuning reduces ambiguity and enhances consistency across automated and agentic workflows. With AI Prompts, organizations can also ground models in their enterprise data—respecting runtime user permissions and data policies—so they can securely draw insights from internal resources. By carefully crafting prompts, businesses can extract higher-value insights, automate complex processes, and improve AI alignment with organizational goals.

We are excited to announce that AI Prompts can now leverage the o1 model, unlocking reasoning capabilities for your AI-driven workflows. For instance, imagine a customer support scenario in which agents need to analyze complex troubleshooting data—like error logs or past support tickets—to pinpoint the root cause of an issue. By tapping into o1’s powerful logic and chain-of-thought (CoT) reasoning, agents can rapidly identify patterns, suggest tailored solutions, and offer clear next steps for resolution. This enhanced approach not only streamlines support operations but also elevates the overall customer experience. The o1 reasoning model in AI Prompt Builder, currently in private preview, will be available to all customers in March.

How to configure AI Prompts 

AI prompts leverage several key features to create specialized AI-powered functions. They include: 

• Customizable Instructions: Users can tailor prompts to address unique business needs, ensuring AI-generated content aligns with specific workflows and objectives. 

• Dynamic Input Handling: AI Prompts can integrate input variables and contextual data, making responses more relevant and adaptable based on real-time information. 

• Model Selection for Tasks: Users have the flexibility to choose the right AI model for specific tasks, optimizing performance and accuracy based on the desired outcome. 

• Knowledge and RAG with Dataverse Data: AI Prompts can leverage knowledge retrieval and retrieval-augmented generation (RAG) to contextualize prompts with relevant data from Dataverse, ensuring more informed and accurate AI responses. 

• Document and Image Processing: AI Prompts can handle document and image inputs, enabling AI-driven workflows to extract insights, summarize content, and interpret visual data. 

• Configurable Output Formatting: Responses can be structured in JSON format, allowing seamless integration into applications that require standardized data outputs like Power Automate. 

For more details on leveraging these features to craft effective prompts, download our Prompt Guide. 

Real world applications of AI Prompts 

AI Prompts enable an endless number of scenarios and can apply to a multitude of industries and processes. Some of the most common use cases our customers are implementing include: 

• Document Processing – AI Prompts can automate document extraction, categorization, and summarization, making handling large volumes of text-based content more efficient. 

• Email Classification and Auto-Reply – AI Prompts can analyze incoming emails, categorize them based on intent, and generate automated responses to streamline communication. 

• Automated Content Summarization – AI Prompts can be configured to extract key insights from lengthy documents or emails, making it easier to digest critical information efficiently. 

• Data Transformation – AI Prompts can be used to convert raw data into structured formats, improving data consistency and usability. 

Building on the sample scenarios above, The AI Builder Prompt Library offers a curated set of ready-made prompts designed to help you rapidly create AI-driven results. With practical examples and step-by-step guidance, these resources streamline prompt engineering—enabling you to craft precise instructions, simplify workflows, and optimize AI-driven initiatives. 

Getting Started with AI Prompts 

Ready to transform your business processes with advanced AI tools? 

With AI Prompts, you have access to the latest AI models, enterprise-grade security, and a powerful instruction building playground. Start supercharging your flows and agents with these AI tools today! 

The post Supercharge your Agents and Flows with AI Prompts appeared first on Microsoft Power Platform Blog.

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.

For guidance and samples on using the multi-modal content processing and other prompts with Power Apps, you can use the Creative AI Kit in App Source or GitHub. The new samples that use multi-modal prompts include AI Image Diff, AI Describe Image, AI Fields from Image and AI Generate QnA.

Join our Ignite sessions and read about other exciting announcements for Microsoft Power Platform:

• Automate e-mail, doc, and image processing with GPT in Power Automate with Gwenael Bego and Maria Gutierrez
• Revolutionize the way you work with Power Automate and AI with Joe Fernandez and Heather Orta-Olmo
• Unlock innovation with practical strategies in Power Automate with Jonathan Kendall
• See our Dataverse Ignite session (virtual and in person): Explore Ignite 2024: Unlock enterprise knowledge with Dataverse – Microsoft Power Platform Blog

The post Boost productivity: Automate emails, documents, and images with Microsoft AI Builder appeared first on Microsoft Power Platform Blog.

Keep reading to find out more about how to craft Power Automate actions that will transform your business processes with the power of GPT-4, including the ability to automate GPT Prompts with enterprise knowledge stored in Dataverse, generate structured outputs with JSON formatting and adjust GPT model temperature settings.

Use the power of GPT to process content using your enterprise knowledge

Prompts are the natural language instructions that users provide to Large Language Models (LLMs) to produce a specific response. With AI Builder’s “Create text with GPT using a prompt” action, you can use prompts to make AI powered functions that can process and generate text content dynamically with GPT. Prompts for example can include instructions in natural language that will guide your cloud flow or desktop flow to accurately process an incoming e-mail, analyze the content of a document or automate insights extraction from your data. Today, we are adding more features to Prompts to enable users to connect their enterprise knowledge and generate trusted outputs.

Enterprise knowledge is crucial for building effective prompts because it ensures contextual relevance, accuracy, and precision. Understanding the specific domain language and business context allows for crafting prompts that are aligned with the company’s goals and processes. This leads to streamlined workflows, consistent outputs, and enhanced user experiences by providing tailored and intuitive interactions.

In the Prompt Builder interface, a new option to add data sources is now available, allowing you to select a Dataverse table and its related entities as knowledge associated with your prompt. The fields selected will be used by the Generative AI model to expand its knowledge base with current enterprise specific data that will help provide the most contextual response to the prompt.

The new interface allows you to filter the data to add to your knowledge source, and to reference the associated knowledge inline within your natural language instruction. This will unlock many new enterprise specific actions, like for example generating summaries of account interactions based on Dataverse data, classifying content based on custom categories stored in Dataverse, or suggesting the most appropriate actions to respond to a customer query based on historical data stored in Dataverse. Learn more about prompt data grounding in our documentation.

GPT-4 Model selection and temperature settings

Another new feature in Prompts is the ability to select which model to use to process a given action, and to control the Temperature associated with the given model. Using the model selector, users can select to opt-in to use GPT-4o (rolling out in the coming weeks), GPT-4 (gpt-4-32k-0613 available today) or GPT 3.5 (gpt-3.5-turbo-0613 default model) for individual prompts. This allows for greater flexibility to optimize costs and performance associated to Prompts based on what tasks will be performed by the prompt and the context window required to perform the task.

Alongside the model selector, a slider has also been added to control the temperature of the Generative AI model, allowing you to adjust the model to be more deterministic or more creative to perform a given task. Learn more about model selection and parameters in our documentation.

JSON output formatting for reliable end-to-end automation

By default, prompts generate a text output allowing you to automate the process of creating text-based data that can be used across an end-to-end workflow. To optimize how to parse and re-use text data created by GPT, we’re introducing a new feature that allows you to generate a structured text output formatted in JSON. This new capability will allow you to ensure that the generated data always follows the same structured schema, so that you can reliably use it in downstream actions in your flow. This will be particularly useful when you want GPT to generate structured content like a project schedule, or extract data from a document like the different fields associated to an invoice or purchase order.

To trigger structured output formatting, you can select JSON as an output format in the Prompt Builder. The target JSON structure will be auto-detected based on the prompt instructions provided, but you can also edit the schema to force a given output structure.

Once you have defined your desired schema and saved your prompt, the output format will be locked, ensuring that your prompt will always generate the same structured format and that the output fields will automatically be available for use in downstream actions in Power Automate:

Get started

Find the most recent documentation for our new features and learn how to create more effective automation with Generative AI Prompts:

• Create a prompt | Microsoft Learn
• Use your own data in a prompt | Microsoft Learn
• Model selection and temperature settings | Microsoft Learn
• Change the output of your prompt | Microsoft Learn
• Distribute your prompt using a solution | Microsoft Learn
• Human Review for automation with a prompt | Microsoft Learn

The post Generative AI Prompts to automate content processing appeared first on Microsoft Power Platform Blog.

What are the benefits of Invoice Customization?

AI Builder is already equipped with a pre-configured AI model capable of extracting standard fields from invoices. This model is finely tuned to identify typical invoice components such as invoice ID, invoice date, amount due, and various other standard field types. If your invoices include custom fields beyond the standard ones, you’ll need to create a specialized Document Processing AI model and label a training dataset with sample documents. This process trains the AI model to identify and extract these extra fields.

Instead of starting from scratch and labeling every field for extraction, you can now opt to use an existing invoice model as your starting point:

This method allows you to efficiently extract standard invoice fields and simplifies the training phase, concentrating only on adding the extra fields required to develop your custom invoice processing model. Customers like Ashley Francis, a Certified Public Accountant (CPA) with The Francis Group practice in Seattle, are already benefiting from this new solution to transform traditional processes, increase efficiency, and save time.

“Finding out about all the things in the Power Platform has been amazing. Like this is technology that I didn’t even know existed. I want so much more time to learn everything on the Power Platform and AI because it can do so much for my profession.”

– Ashley Francis, Certified Public Accountant, The Francis Group

Read the full story: Certified Public Accountant transforms accounting processes using Power Automate 

What are the benefits of Document field types?

In an end-to-end workflow for document processing, it’s crucial to extract not just the field’s name and value but also its type and format (such as a number, date, checkbox, table, or text field). The newly introduced typed fields feature enables the extraction of fields identified as numbers and dates, allowing you to specify their anticipated format while training a custom document processing model. This enhancement aids in standardizing the output of document processing and boosts the precision of document extraction performance.

Get started with invoice customization and field types

Leverage these additional resources to learn more about these new document processing features:

• Create a document processing custom model in AI Builder | Microsoft Learn
• Extract dates and numbers from documents | Microsoft Learn
• Start using AI Builder

The post Custom processing for invoice and document field types generally available appeared first on Microsoft Power Platform Blog.

What are Prompts? 

Prompts are the instructions that we can give to large language models (LLMs) like GPT to perform specific tasks. The more precise the instructions we give, the better GPT performs at executing the tasks. To allow companies to create effective prompts we’ve created a new tool, Prompt Builder, a low-code prompt engineering interface that is seamlessly integrated in Power Automate. 
Customers are already excited about the perspectives that Generative AI can bring to Power Automate. Epiq, a global leader in technology-enabled services, has set a new standard with its innovative use of Generative AI by applying it to transform their HR operations. “With AI Builder in Power Automate, we added a model that cleans up formatting of new employee submission forms. This allows us to process more efficiently at scale – and it works flawlessly.” says Colt Coan, Senior Manager of Rapid Development, Epiq. Want le learn more? Read Epiq’s customer story article.

How to build a Prompt 

To access Prompt Builder, start by adding the “Create text with GPT using a prompt” action from the AI Builder connector:  

You’ll then be able to use Prompt Builder, AI Builder’s new low-code prompt engineering interface, to create your instructions to GPT that will be executed during the workflow. 
We’ve added examples of Prompts to help you get started. Common scenarios include: 

• Classify Text: E-mail classification and case routing. 
• Summarize Text: Summarization of e-mails, contracts or meeting notes. 
• Extract action points from text: Identify upsell/cross-sell opportunities and next best actions. 
• Extract information from text: Understand customer requests to automate sales quotes and proposals. 
• Respond to a complaint: Draft e-mail responses to fast-track support case management. 

When creating a prompt, you’ll be able to add dynamic values in the instructions so that the Prompt can automatically be executed over new data, for example an incoming e-mail. 


In the body of the prompt, you’ll be able to craft your GPT instructions, add multiple dynamic values, define the output format you want, and test your prompt with sample data:

Once you’re happy with the way your prompt performs, you can save your prompt for future use. You’ll be able to access all your saved Prompts along with a library of pre-built Prompts from the new AI Prompts page. Prompts can be shared with other users, added to solutions for cross-environment deployment, and invoked across other products like Power Apps or Copilot Studio. To learn more about how to create effective Prompts, refer to our new Prompt engineering guide.

Human in the loop validation 

Content generated by AI can include mistakes and surprises, so it’s important to make sure it is accurate and appropriate before using it. To facilitate this process, you can include GPT-generated text in an approval flow that allows you to validate and edit the content before using it: 

Approval workflows to validate GPT content are highly recommended but no longer mandatory now that the feature is generally available. 

Available in the United States, Australia, UK, and Europe  

GPT Prompts and Prompt Builder will be generally available this week across the United States, Australia, the United Kingdom, and Europe. 
GPT Prompts currently leverage the GPT-3.5-Turbo model from Azure’s OpenAI Service, meaning your prompts and outputs: 

• are NOT available to other customers. 
• are NOT available to OpenAI. 
• are NOT used to improve OpenAI models. 
• are NOT used to improve any Microsoft or 3rd party products or services. 
• are NOT used for automatically improving Azure OpenAI models for your use in your resource
   

Please reference the Azure OpenAI Service data, privacy and security documentation for details on how your data will be processed, used and stored with GPT Prompts. 

Get Started

• Try Prompt Builder: https://aka.ms/tryprompts  
• Prompt Engineering Guide: https://aka.ms/promptguide 
• Documentation: Prompts Overview | Microsoft Learn
• Learning Videos: Overview Video | GPT Prompts with Excel Video 
• Customer Story: Epiq – Revolutionizing HR operations with Power Platform + Generative AI 
• Pricing for GPT Prompts can be found in the Microsoft Power Platform Licensing Guide 
• Governance: Learn about administrating Generative AI features and cross region availability  

The post AI Builder GPT Prompts are generally available appeared first on Microsoft Power Platform Blog.

GPT action broadly available to US customers

The ‘Create text with GPT action’ is now broadly available to customers based in the United States. This exciting new capability allows makers to use GPT models in the context of automation to perform a wide range of enterprise scenarios centered around text processing and content generation. Available through the AI Builder connector, this capability allows you to send dynamic content to GPT and perform numerous tasks like summarizing content, extracting content, classifying e-mails or pre-generating e-mail responses.

You can create custom instructions to GPT or use pre-configured templates to get started. Learn more about how to use GPT from Azure’s OpenAI service with the AI Builder connector: Use your Azure OpenAI Service model in Power Automate (preview) | Microsoft Learn

Validate and augment GPT content with editable Approvals

An essential part of using AI-generated content in automated workflows is the ability for human review. AI-generated content can be imperfect, and it is important to be able to review it, especially if it is used for customer-facing communication.

For you to include a human review process within GPT flows, we’ve introduced a new feature in Approvals that allows you to review and edit text. Add the new Power Automate action “Start and wait for an approval of text” after your GPT action to send the AI-generated text to an individual approver or a team of approvers.

This action pauses the flow and creates an “Approve/Reject – First to respond” approval with the ability to edit the suggested text generated by GPT.

It has never been easier to review and edit text with the power of Approvals! Learn more about this feature: Use your Azure OpenAI Service model in Power Automate (preview) | Microsoft Learn.

AI Builder activity monitoring available in public preview

We’re happy to introduce a new monitoring feature that allows you to keep track of AI Builder model activity and AI credit consumption.

Access it now though the Monitor menu in the Power Automate portal:

This new monitoring interface allows makers and admins to track the data processed by AI Builder models, as well as the processing time and number of credits consumed by flow or app runs. Administrators of the environment can access data for all users and models in the environment, while makers will be able to access monitoring activity generated by their own usage.

The data is stored in the AI Event Dataverse table, giving flexibility to generate custom reports using Power BI so that you can tailor monitoring views for your specific need.

Learn more about this new feature in the Activity monitoring (preview) | Microsoft Learn page.

Extend Invoice Processing with custom fields

You can now extend the behavior of the prebuilt invoice processing model by adding new fields to be extracted in addition to the default ones. Start by creating a custom document processing model, then select “Invoices (preview)” as the type of document to process.

Instead of having to build an invoice processing model from scratch, you can re-use all the default fields of the invoice processing pre-built model and add only the additional ones you need. This feature will simplify the model creation process for custom invoices, making it much easier to train a custom model.

Learn more about this feature: Create a document processing custom model in AI Builder | Microsoft Learn.

Co-ownership of AI models

AI Builder now supports multiple users co-owning an AI model, empowering multiple individuals to contribute to the AI model training lifecycle process. By enabling multiple owners, model improvements can be performed by multiple individuals within a company, allowing teams of makers to update and improve model performance over time.

In the model detail page of a model, users now have a new option to share as “Co-owner”. Selecting it when you want to share the model, will grant edit rights to the users that you define:

Learn more about this new feature: Share your AI model – AI Builder | Microsoft Learn.

Pricing and more

AI Builder prices have also been adjusted, with updated rates and volume discounts available. Download the Power Platform Licensing Guide to see the latest updates to AI Builder pricing.

Please feel free to provide your AI Builder questions and feedback in the Power Automate Community. Happy Automation!

The post July 2023 updates for AI Builder appeared first on Microsoft Power Platform Blog.

New model capabilities

Unstructured Document Processing

Most documents used in the enterprise are based off free-form layouts that don’t have a specific content structure. This is true for documents like contracts, statements of work, letters or resumes. Visualizing and extracting content from these documents is even more difficult than with a structured form, as the fields aren’t properly labeled and can be anywhere in the document. AI Builder helps to solve this problem with the Unstructured Document Processing capability based off Azure Form Recognizer’s Custom Document Neural Model.

With Unstructured Document Processing generally available, you can train a custom AI model to identify and extract specific fields that will help you automate how to process information from all types of documents.

Improved accuracy and language support with Azure Form Recognizer 3.0

AI Builder’s document processing models now leverage Azure Form Recognizer v3.0, improving detection accuracy and extending language support. Highlights of improvements include:

• Custom Document Processing adds support for 42 new languages including Arabic, Hindi, and other languages using Arabic and Devanagari scripts to expand the coverage to 164 languages. Handwritten language support expands to Japanese and Korean.
• Pre-built invoice processing model now supports Spanish, French, Dutch, German, Italian and Portuguese.
• Pre-built receipt processing model now supports Spanish, French, German, Italian and Portuguese.
• Pre-built Identity Reader now supports US state ID, social security and green cards, as well as passport visa information.
  

  Multi-page Tables

  Documents across the enterprise like invoices often include large tables of data that can span across multiple pages, making it difficult to accurately extract information. AI Builder has re-built its multi-page table capability, allowing makers to tag tables across pages ensuring that the table data is extracted reliably.

  

  The multi-page table functionality is currently being rolled out and will be available in all regions by the end of October.

  Multi-Line Tagging

  When fields to extract span across two lines in a document, AI models struggle to extract data correctly. With AI Builder’s new continue tagging capability, we make it easy to train a model to identify and extract fields like an address that can be split across multiple lines in a document.

  

  Managing Model Performance

  Feedback Loop

  What happens when you try to process documents that are too different from the original samples you used to train AI Builder? When new documents are processed with specific layouts that differ too much from what you trained for, a low accuracy score can be returned. To help users manage this use case and improve model performance, we’ve created the Feedback Loop capability. Using the AI Builder feedback loop action in Power Automate, makers can automate the process of monitoring documents that weren’t processed correctly and send them back into a queue for re-training. Makers can now easily track new documents with low quality processing and improve their model’s performance.

  

  The Feedback loop functionality is currently being rolled out and it will be available in all regions by the end of October.

  Governing and sharing models

  With increased adoption of AI models to automate content processing, teams of makers want to collaborate on models to speed up the training cycle and transfer ownership rights. This is now possible with Model co-ownership. From the Model Details Page, users can share model ownership rights with other users, granting them the ability to re-train and re-publish models.

  Model co-ownership will be available in all regions by the end of 2022.

  To improve model governance, AI Builder models are now also visible in the Power Platform Center of Excellence (CoE) Starter Kit. Admins can monitor which AI models were created across environments and how they are being used in their tenant, giving the ability to better govern and foster AI innovation within their organization.

  Getting Started

  Head over to https://aka.ms/tryaibuilder to access all the latest capabilities, video tutorials and learning material and get started deploying AI models to make your organization more productive!

The post Automate Document Processing end-to-end with AI Builder appeared first on Microsoft Power Platform Blog.

On top of providing our community with a brand-new interface to share ideas, the migration will enable our product teams to be much more responsive to user feedback and better integrate your ideas into our product roadmap.

Fig 1. New Power Automate Ideas portal, available for desktop and mobile browsers

The Power Automate team is listening!

A new process for voting and managing ideas will be implemented as part of this change. Every month, our community team will review and triage all incoming ideas. Duplicate ideas will be grouped for easier search, and clarification may be requested from the author. Top ideas (ideas that get upvoted at least 50 times) will be sent to the Power Automate product team for review. During every planning cycle, the product team will review Top ideas and determine if and when they can be added to the roadmap.

Statuses for ideas will be updated as follows:

• NEW: New ideas recently submitted that haven’t been triaged yet
• NEEDS VOTES: Triaged ideas that need at least 50 votes before they are reviewed by the product team.
• TOP IDEA: Ideas that have gathered at least 50 votes, and are currently being reviewed by the product team for inclusion in the next release wave.
• IN BACKLOG: The product team has approved the idea for inclusion in the product backlog, without a committed date yet.
• PLANNED: The team has committed to building the idea which has been added in the official release plans.
• COMPLETED: The idea has made it into the product and has shipped!
• DECLINED: The product team has declined to build the idea at this time

With this new process, the Power Automate product team will be able to respond to your community ideas and incorporate more of them into the product.

Fig 2: Posting a new idea on the portal 

How will the migration happen?

On July 18, Power Automate Ideas will go into “read-only” mode. The possibility to post a new idea will be temporarily disabled while we transfer all existing ideas to the new site: https://ideas.powerautomate.com

Starting July 20, we will launch the new site and you will be able to resume posting and sharing ideas. All ideas posted prior to July 18 will be made available on the new site with their new corresponding statuses.

We thank you for your continued engagement in our community and look forward to your new ideas for Power Automate!

The post New ways to share Power Automate Ideas appeared first on Microsoft Power Platform Blog.

Unstructured document processing

We are expanding Intelligent Document Processing (IDP) capabilities for Power Automate by adding support for unstructured document processing. AI Builder and Power Automate already enable everyone to build end-to-end workflows that automatically extract and process content from structured (for example, surveys and questionnaires) and semi-structured documents (for example, invoices and purchase orders). AI Builder now supports the ability to train a custom Document Processing AI model that can extract content from unstructured documents like contracts or letters.

Figure 1. Extracting key-value pairs from a contractual agreement

The new document processing capability leverages Azure Form Recognizer’s custom neural model and comes complete with a no code UI training wizard and model governance capabilities.

Model performance metrics for structured documents

To enable admins and makers to better measure the performance of their models, we’ve re-designed the structured document model page to include a global accuracy score. The page also features a breakdown of the training set as well as recommendations on how to improve the model. More information: Improve the performance of your processing model

Figure 2. Model accuracy score and evaluation for structured document processing models
General availability of Image Classification

Image Classification with Lobe is becoming generally available.  Lobe is a free, easy-to-use app from Microsoft that helps you build image classification models on your own computer. All you need to do is add and label images, and Lobe will automatically train a custom machine learning model for you. The Lobe model can be exported to AI Builder and used in Power Apps and Power Automate. More information: Image classification model by Lobe

Figure 3. Lobe app for AI-powered image recognition which can be used with AI Builder
Additions and enhancements to existing capabilities

• To improve transparency of AI Builder credits and facilitate capacity management, the Power Platform Licensing guide has been updated to include individual credit consumption rates for each AI Builder scenario.
• AI Builder learning and training materials have been updated in the AI Builder in a day Lab. New training courses come complete with sample code and data sets to get you started building your first AI models easily.
• Text Recognition has been updated to support 164 languages. The pre-trained model allows you to extract printed or handwritten text from images, such as photos or street signs and products, as well as from documents. The model supports extracting printed text for English, French, German, Italian, Portuguese, Spanish, Chinese, Japanese, Korean, Russian, Arabic, Hindi, and other international languages that use Latin, Cyrillic, Arabic, and Devanagari scripts. The model now also supports extracting handwritten text in 9 languages: English, Chinese (Simplified), French, German, Italian, Japanese, Korean, Portuguese and Spanish.
• AI Builder is now available in South Korea.

Getting started

Get hands on with all the latest updates, discover which model best fits your scenario, and get inspiration from customer stories. Try AI Builder https://aka.ms/tryaibuilder

We are always working to improve AI Builder to meet your needs. Feel free to share your feedback with us in the AI Builder forum, raise an idea in the Power Automate Ideas, or email us directly at aihelpen@microsoft.com.

The post Exciting new capabilities for AI Builder appeared first on Microsoft Power Platform Blog.