Book Image

Power Platform and the AI Revolution

By : Aaron Guilmette
Book Image

Power Platform and the AI Revolution

By: Aaron Guilmette

Overview of this book

In this AI era, employing leading machine learning and AI models such as ChatGPT for responding to customer feedback and prototyping applications is crucial to drive business success in the competitive market. This book is an indispensable guide to integrating cutting-edge technology into business operations and leveraging AI to analyze sentiment at scale, helping free up valuable time to enhance customer relationships. Immerse yourself in the future of AI-enabled application development by working with Power Automate, Power Apps, and the new Copilot Studio. With this book, you’ll learn foundational AI concepts as you explore the extensive capabilities of the low-code Power Platform. You’ll see how Microsoft's advanced machine learning technologies can streamline common business tasks such as extracting key data elements from customer documents, reviewing customer emails, and validating passports and drivers’ licenses. The book also guides you in harnessing the power of generative AI to expedite tasks like creating executive summaries, building presentations, and analyzing resumes. You’ll build apps using natural language prompting and see how ChatGPT can be used to power chatbots in your organization. By the end of this book, you’ll have charted your path to developing your own reusable AI automation patterns to propel your business operations into the future.
Table of Contents (16 chapters)

Sending prompts to ChatGPT

Working with ChatGPT as an end user is pretty simple. So, how hard is it to do the same thing with Power Automate? The answer, it turns out, is that it isn’t that bad.

You have two main options for passing data to the OpenAI ChatGPT service itself: the built-in HTTP (Premium) connector or a third-party OpenAI connector. We’ll go through both options quickly, and you can adapt whichever you like to suit your purposes.

Both of the examples will be built as instant cloud flows with a simple text prompt. For both examples, you’ll need the OpenAI API key that you created in Chapter 2, Configuring an Environment to Support AI Services.

HTTP

The HTTP method is the more complex method of the two but also gives you the most flexibility.

Updated parameter information

Like all cloud services, OpenAI may change endpoints and other parameters without notice. You can get the most updated endpoints and parameters at https://platform...