{"id":10130,"date":"2023-07-31T09:00:00","date_gmt":"2023-07-31T17:00:00","guid":{"rendered":""},"modified":"2025-06-11T07:44:52","modified_gmt":"2025-06-11T14:44:52","slug":"july-2023-updates-for-ai-builder","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/power-automate\/july-2023-updates-for-ai-builder\/","title":{"rendered":"July 2023 updates for AI Builder"},"content":{"rendered":"
We are happy to announce several new updates to AI Builder capabilities that will extend the number of scenarios you can automate with AI.<\/p>\n
The \u2018Create text with GPT action\u2019 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.<\/p>\n
<\/p>\n
You can create custom instructions to GPT or use pre-configured templates to get started. Learn more about how to use GPT from Azure\u2019s OpenAI service with the AI Builder connector: Use your Azure OpenAI Service model in Power Automate (preview) | Microsoft Learn<\/a><\/p>\n 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.<\/p>\n For you to include a human review process within GPT flows, we\u2019ve introduced a new feature in Approvals that allows you to review and edit text. Add the new Power Automate action \u201cStart and wait for an approval of text\u201d after your GPT action to send the AI-generated text to an individual approver or a team of approvers.<\/p>\n This action pauses the flow and creates an \u201cApprove\/Reject \u2013 First to respond\u201d approval with the ability to edit the suggested text generated by GPT.<\/p>\n 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<\/a>.<\/p>\n We\u2019re happy to introduce a new monitoring feature that allows you to keep track of AI Builder model activity and AI credit consumption.<\/p>\n Access it now though the Monitor<\/em> menu in the Power Automate portal<\/a>: 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.<\/p>\n The data is stored in the AI Event<\/em> Dataverse table, giving flexibility to generate custom reports using Power BI so that you can tailor monitoring views for your specific need.<\/p>\n Learn more about this new feature in the Activity monitoring (preview) | Microsoft Learn<\/a> page.<\/p>\n 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<\/a>. Start by creating a custom document processing model, then select \u201cInvoices (preview)\u201d as the type of document to process.<\/p>\n 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.<\/p>\n Learn more about this feature: Create a document processing custom model in AI Builder | Microsoft Learn<\/a>.<\/p>\n 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.<\/p>\n In the model detail page of a model, users now have a new option to share as \u201cCo-owner\u201d. Selecting it when you want to share the model, will grant edit rights to the users that you define:<\/p>\n Learn more about this new feature: Share your AI model – AI Builder | Microsoft Learn<\/a>.<\/p>\n AI Builder prices have also been adjusted, with updated rates and volume discounts available. Download the Power Platform Licensing Guide<\/a> to see the latest updates to AI Builder pricing.<\/p>\nValidate and augment GPT content with editable Approvals<\/h2>\n
<\/p>\n
<\/p>\nAI Builder activity monitoring available in public preview<\/h2>\n
\n
<\/p>\nExtend Invoice Processing with custom fields<\/h2>\n
<\/p>\nCo-ownership of AI models<\/h2>\n
<\/p>\nPricing and more<\/h2>\n