Build solutions faster with Microsoft Power Platform and next-generation AI
Low-code technology is radically changing the traditional development landscape. And with Microsoft Power Platform and next-generation AI, Microsoft is providing both a new way for developers to solve business problems and a new way for end users to use AI in the flow of their work to be more productive.
We recognize the significance of both AI and low-code for organizations, and the benefits these technologies in union can have for all developers: a more intuitive, iterative experience for citizen developers and accelerated development for professional developers.
Today, we’re taking another big step forward in this journey with the launch of next-generation AI features for Power Virtual Agents and AI Builder, enabled by Azure OpenAI Service.
Next-generation AI features for Power Virtual Agents and AI Builder
New! Conversation booster in Microsoft Power Virtual Agents: Simply point your bot to your company-specific resources, like your website or an internal knowledge base, and watch it start to answer questions in minutes, right out-of-box, with no additional authoring. Learn more here.
New! Create text with GPT model in AI Builder: AI Builder now brings Azure OpenAI Service to its user-friendly interface, enabling makers to use a new low-code generative AI model and templates with Microsoft Power Automate and Microsoft Power Apps. Learn more here.
We announced AI Builder four years ago as the first AI capability in Microsoft Power Platform, followed by Power Apps Ideas 18 months ago, which was the first infusion of generative AI in a commercially available product. And we have continued to invest with the addition of express design in Power Apps and description to flow in Power Automate late last year. And we have much more to come.
Conversation boosters in Power Virtual Agents
Power Virtual Agents is the low-code approach to building chatbots with an intuitive visual drag-and-drop approach that vastly simplifies bot creation, all backed with a code experience, if needed (preview). And like most industry bot tools, it has relied on the maker to create conversation topics and configure dialog flows.
But that’s about to change with the new conversation booster capability in Power Virtual Agents.
Normally, when a bot encounters a question or response that it hasn’t been trained on, it can only respond in one of two ways: ask the user to rephrase, or offer to connect to a human agent, something we are all very likely familiar with.
Now, using the power of next-generation AI, you can connect your bot to your most current and useful data sources, like internal and external company websites, and the bot can immediately start to use that data to construct a response.
This means that out of the box, the bot is ready to answer user questions based on the information on your site—all without authoring a single topic or spending additional development cycles. This gives developers more time to focus on building complex conversation flows and delivering increased resolution rates and improved customer outcomes.
With the conversation booster feature, you can use the data source that holds your single source of truth across many channels through the chat experience, and the bot responses are filtered and moderated to adhere to Microsoft’s responsible AI principles.
This also unlocks new use cases for bots which may have been difficult to justify due to the expected build time and cost. With the bot now able to search, summarize, and moderate answers at speed, with just a URL and no additional development, you can quickly create bots to help resolve repetitive queries for your customers and internal functions like human resources, IT, operations, and more.
Here are some examples of how organizations can put the conversation booster to work. And check out the videos to see it in action.
- A retail company builds a bot to answer questions for seasonal job postings, pulling from existing content on the recruitment process and company values.
- A technology company can quickly connect a bot to disparate product support knowledge bases and FAQs and provide support to customers without writing any code.
- A media company can build an employee bot to resolve common HR queries about performance reviews, bonuses, and policies based on existing policy documentation.
Watch how to build customer-facing bots:
Watch how to build departmental bots:
Create text with GPT model in AI Builder
AI Builder has democratized access to complex AI models for use in Power Apps and Power Automate and includes models for category classification, object detection, prediction, sentiment analysis, and many more.
And today we’re excited to announce the addition of a new Azure OpenAI Service model that unlocks new ways for organizations to embed intelligent text generation features into their Power Automate and Power Apps solutions with a few clicks.
Makers can use the prebuilt templates to interact with the model and build the right prompts for their workflow, reducing development time for both citizen and pro developers.
It’s easy to get started and use the new model in your app or flow, some examples could include:
- A researcher can use the model to summarize text from weekly released reports and send it to their email inbox, all with Power Automate. This helps inform their analysis and identify themes/trends at speed.
- A marketing manager can create targeted generated content ideas by entering specific keywords or topics and use the generated text for emails or social media posts, all within their marketing team’s app.
- A customer service agent can build a flow within Power Automate to summarize, classify, and route customer queries for quick responses to complaints or feedback.
The sky really is the limit, and that’s why AI Builder is an invaluable tool and key ingredient within Microsoft Power Platform. It’s helping everyone—regardless of their background or level of AI expertise—to quickly and easily use next-generation AI in the solutions they build.
Take a look at it in action in the video below.
You can find all the information regarding Microsoft’s recent announcements on the AI Hub.
Responsible AI at Microsoft
Microsoft is committed to creating responsible AI by design. Our work is guided by a core set of principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. We are helping our customers use our AI products responsibly, sharing our learnings, and building trust-based partnerships. For these new services, we provide our customers with information about the intended uses, capabilities, and limitations of our AI platform service, so they have the knowledge necessary to make responsible deployment choices.
Availability
The conversation booster feature in Power Virtual Agents is experimental, and its accuracy and relevance cannot be guaranteed. It is not currently possible to publish your bot while this feature is enabled, but you can easily disable it in the settings at any time.
Create text with GPT model in AI Builder will be available via a limited preview, which you can learn more about here.
Both features will be available in the United States and in the English language only.
