AI Copilot in Power Apps

In Senior Consultant Steven Brusse's previous blog, published less than two months ago, he wrote about the impact of Artificial Intelligence (AI) on low-code software development. In it, he asked whether it would ever be possible to have applications developed by an AI model. A few weeks later, Microsoft already answered that question with the introduction of AI Copilot in Power Apps. With AI Copilot, Microsoft shows what is possible when a generative AI model such as ChatGPT is integrated into a low-code development platform. Anyone can now start building an application simply by describing the desired specifications in human language in a conversation with a chatbot. With modern low-code tools, programming experience was already no longer needed to build working applications, but in practice you still did not get very far without specific tool knowledge. That might now change, or is it too early to draw that conclusion? In this blog, you can read what the new AI Copilot currently offers, what its limitations are and how you can request a trial version to test it yourself.

Signing up for a trial version

Before we go into the possibilities of the new AI assistant, it is important to mention that AI Copilot is not yet available to everyone. The new AI Copilot features are not yet intended for production use and are currently only offered as a limited preview. You need to submit a request to Microsoft to use a trial version. A condition for participation is that your environment (Power Platform Environment) is hosted in the US and that AI Builder is enabled on the environment. The request for the trial version can be submitted via an online form.

What can AI Copilot do?

The new AI Copilot is a smart assistant that you can put to work in various ways when developing apps (with Power Apps), flows (with Power Automate) and chatbots (with Power Virtual Agents). In this blog, I will limit myself to the applications of AI Copilot in Power Apps.

• Building apps through conversation
• Adding the Copilot control to apps

Building apps through conversation

Once Copilot has been activated in your environment, the Power Apps home screen asks you to describe what kind of app you want to create. Here, you can describe in human language what kind of information you want to collect, register, process or display. Based on your description, Copilot generates a new table in Dataverse with the back-end logic to automate the requested activities. You are then shown the structure of the new table with some sample data.

You can change the new table, adjust columns or add extra columns by describing the changes you want. To help you along, after each new question you are given suggestions for possible follow-up questions you can ask Copilot. You can ask Copilot not only to change the structure of the table, but also to generate extra sample data.

If the table meets your requirements, you can finally ask Copilot to create an app. The app that is created is a responsive canvas app with a home page and an input page. The new Copilot control (see next section) has been added to the home page, allowing you to ask questions about the data in the app right away. The second page contains a list showing the existing rows from the table. Here, you can edit rows and add new ones.

Adding the Copilot control to apps

The new Copilot control is an AI assistant that developers can add to apps for end users. With this control, end users can gain insights into the data stored in the app through conversations in human language.

The Copilot control is added to your app automatically when you have created the app with Copilot. As a developer, you can also add the Copilot control to existing apps that already use tables in Dataverse. In the control's settings, you can choose which data questions can be asked about.

With this new control, end users can ask very targeted questions about the data in an app, making the app itself more user-friendly. Apps can also be made simpler, because other controls for looking up, displaying and filtering data, for example, are no longer needed.

What are the current limitations?

Although the new AI Copilot features have so far only been released as a trial version, they already give a good picture of the future of low-code software development with Power Apps. Based on the current possibilities and limitations, however, the new features cannot yet be used for production applications. I have listed a number of limitations below:

• Copilot can only create a canvas app, not a model-driven app.
• The apps you can create with Copilot are very simple, because they are linked to just one table in Dataverse.
• If you later want to modify a canvas app and extend it with extra functionality, you cannot use Copilot, so you still need someone with specific tool knowledge.
• The idea behind the new Copilot control is very powerful, but you can only choose one table for the control. This limits the questions users can ask through the control, since data is normally stored in multiple tables.

Conclusion

The AI Copilot preview proves that it is possible to develop apps with the help of a smart chatbot without any prior knowledge of Power Apps. Due to the current limitations, Copilot is not yet really usable in practice. That will undoubtedly change in the near future, as Microsoft has announced that it is fully committed to AI applications in its existing cloud services. For that reason, I expect the capabilities of AI Copilot to be expanded quickly. On the other hand, I do not think experienced app developers with programming experience and/or specialist tool knowledge will be made redundant by an AI-driven chatbot. For complex applications that integrate with external systems, these kinds of specialists are still needed, and that is likely to remain the case.

Want to know more about low-code?

Would you like to know more about the possibilities of low-code tools, or do you have a concrete challenge where a low-code app could provide the solution? We are happy to advise you and think along about the possible applications of low-code for your specific situation. Get in touch with one of our account managers for an introductory meeting.

Schedule an appointment

Want to get started as a low-code developer yourself?

The demand for low-code software keeps growing. That is why E-mergo is looking for new people to strengthen the team that builds solutions for customers with Mendix and Power Apps. Do you see yourself as a future low-code developer? Then don't hesitate and check out the vacancies on our website using the button below.