Elena Canorea
Communications Lead
Power Platform is reinventing AI-powered low-code software development. Since 2021 the platform has embarked on a journey to empower all developers with AI-powered experiences and has recently integrated Copilot into Power Apps, Power Automate, and Power Digital Agents.
The marriage of AI and low-code is revolutionizing how solutions are created, fundamentally transforming how people work, collaborate, and create and the way business is done.
With Copilot, Microsoft Power Platform provides AI-powered assistance, helping you create an app, flow, or bot in seconds with simple prompts.
If you want to know how to add value to your Power Platform applications with OpenAI, read on!
Power Automate has become one of the most powerful tools for creating workflow automations thanks to its power and easy integration with the other tools in the Microsoft Power Platform suite.
When discussing its integration with OpenAI, it may seem that we are talking about something completely new; however, we have seen many of these artificial intelligence features integrated into the platform over the last two years until reaching the current functionalities.
With the arrival of Copilot in Power Automate, it will not only be able to describe a workflow when you create it, but it will also enhance and iterate over your workflows with AI-based conversations. This will help each flow every time they are created or modified.
This new functionality makes it easier for humans and machines to work together, empowering people to create transformative automations in a naturally understood language.
We review the main functionalities:
It is a natural language conversion tool that works as follows: you write a sentence to build your flow, and Power Automate will do it in three simple steps.
It is based on an ML model called Codex, and it converts our natural language sentences into an entirely constructed flow. Using it is very simple and efficient in terms of saving time when creating workflows with various connectors such as SharePoint, Excel, Outlook, OneDrive, MS Teams, etc.
It allows you to automate actions such as, for example, sending automatic emails when X task is performed, without having to fill in each field that corresponds to each option, as the tool does it autonomously following our indications.
It also allows data format with examples. Based on PROSE, this technology learns from all the inputs of different programming languages and makes suggestions according to what is needed as an example. Depending on the instructions we give it, we can choose between other options of dynamic content adapted to the needs of each case. It is applicable to text, dates, and numbers, where Power Automate will give output examples to produce the flow and then automatically generate the form of expression to be used.
It can be used, for example, with lists. It allows, for example, to automate the sending of an email every time the list is updated with new items. Also, with economic values applied to surveys, formatting the number with currency value, using the information, and suggesting the expression that performs the transformation. Or even with registration forms in which we want to send a confirmation email greeting with a particular field.
In short, this “Describe it to design it” feature speeds up the creation of better flows. In fact, it takes only 50% of the time to create a flow, and flows are 1.8% more likely to run in the next week compared to creating from scratch.
This option offered by AI Builder is underpinned by a wealth of pre-built AI models that are available for you to choose from and build your applications and flows out of the box.
This new capability allows teams to automate processes and quickly predict outcomes to improve business performance. AI will be added to applications and flows quickly and easily to unlock features such as binary classification, text classification, object detection, image reading, form processing, automating the extraction of key information in formatted documents such as invoices or unformatted documents such as contracts, being able to obtain quantities, dates, names, addresses, etc.
This option opens the door to using the full power of GPT3 in our applications, thanks to the OpenAI API. It is an autoregressive language model that uses Deep Learning to produce human-like text and many other models.
Large language models, or LLMs, help automate complex and repetitive tasks that hinder the creative value of employees. Whether generating code, summarising text, or extracting valuable data, automating these tasks can increase productivity.
ChatGPT integrated with Power Automate helps you learn more about the tool itself, the steps to follow to build a flow, provide suggestions or writes, and explains expressions, among many others.
It is a super scalable scenario as you can run it on a small scale and easily scale it up to a large scale. It will allow you to create content (daily communications to teams or on social networks), collect comments and respond accordingly, extract information from large texts and documents (saving hours of manual scraping), etc.
Copilot in Power Apps makes keeping data at the heart of each application easier. By describing the purpose of our application, a data table is automatically generated for it. With Copilot, developers can take advantage of natural language to refine the application and adapt it to every need.
Power Apps has been a pioneer in AI-centric app development since 2021 when the first features were introduced in GPT to generate Power Fx from natural language. The product has evolved to generate apps based on loaded images, format data based on examples, or suggest modifications.
Imagine your application, describe it, and watch Power Apps generate it instantly. This saves a lot of time, as developers now only have to focus on the more complex code, components, and integrations.
This has initiated a new way of creating and interacting with applications. Thanks to the power of large language models, a further step in the evolution of code abstraction is being taken.
This new era greatly benefits businesses, as they can have customized applications in a few simple steps. In addition, the created applications can have Copilot-powered experiences built in from the first screen, allowing users to discover information in a conversation rather than in clicks.
Examples of instructions that can be given include: creating a time and expense application for employees to submit their reports, automating the manual process of creating and approving customer invoices, tracking new employee onboarding, and so on. With a simple conversation, Copilot will make the adjustments your application needs. It will suggest options (and even help you populate them with sample data) and proactively make recommendations on how to improve your application.
As conversational AI is transforming app development, next-generation AI is revolutionizing how users query and interact with data.
With the introduction of Copilot in Power Apps, users can gain intelligent insights into their app data through a conversational chat experience. Using natural language, they can create queries and refine their analysis with the help of an AI assistant integrated directly into the app.
Whether you need to understand changes in your inventory, estimate the average time to complete a task, or explore which of your campaigns is generating the most revenue, Copilot will analyze and report.
Now you can quickly and easily add a next-generation AI-powered Power Virtual Agents bot to your applications. This gives you access to conversation enhancers and the creation of natural language bots.
On the other hand, by implementing ChatGPT, it is possible to quickly create text for different tool functions such as: generating reports or summaries with the information obtained from the data, producing conversational chatbots, completing forms and questionnaires, etc.
In this way, creating low-code applications with Powers Apps is much faster, more modern, and more intelligent.
The introduction of generative AI within Power Virtual Agents aims to revolutionize how bots are created using simple natural language instructions.
Thanks to Copilot, you simply describe what you want your bot to do, and a complete conversational dialogue will appear (ready in a few seconds) without building and reviewing dialogues step by step painstakingly.
It opens up a new paradigm in which the latest generative AI capabilities are leveraged to make all this possible. The low-code user experience and the Copilot assistant help make bot creation accessible to everyone, as well as make conversation creation easier than ever.
By bringing these two tools together, access to conversational AI has been democratized and accelerated. Previously, creating bots could take months, something that the arrival of Power Virtual Agent changed utterly, reducing the timing to weeks.
Now, with the arrival of Copilot, creating bots is even easier. You can create and iterate on any topic in minutes using natural language. It facilitates the following:
As discussed above, the introduction of generative AI completely changes the traditional model of bot development.
Conversation boosters allow bots to converse about your company’s information with just a URL. In fact, when a user query does not trigger a manually created topic, Power Virtual Agents searches for relevant information in the knowledge source you specify. The results are filtered and passed to Azure OpenAI Service, creating a user response. Bots can then instantly answer hundreds of user questions.
This solves the significant challenges that bots have been facing for a long time, such as the need for a lot of manual creation to get up and running, the limitation to only a few topics to chat about, the need to constantly update content and keep it in sync with the company’s website, and so on. With Copilot, all these problems are immediately eliminated.
We are in the midst of an unprecedented period (and it has only just begun) in which AI is transforming many aspects of our working and personal lives. Whether it’s how we communicate, collaborate or learn, AI is enabling us to improve productivity, save time and achieve better results with much less effort.
At Plain Concepts, we help our clients understand how they can apply different technologies to address their business challenges. GPT models and AI technologies are no exception.
Our Power Platform specialists have a deep understanding of the latest developments that best suit your needs, helping you improve communication and productivity across teams.
We provide you with Plain Concepts’ Azure OpenAI Framework, designed to ensure this service’s correct implementation, improve process efficiency, meet production needs, increase business-critical security, and enhance regional compliance and availability.
If you want to learn how, don’t hesitate to contact us!
Elena Canorea
Communications Lead
Cookie | Duration | Description |
---|---|---|
__cfduid | 1 year | The cookie is used by cdn services like CloudFare to identify individual clients behind a shared IP address and apply security settings on a per-client basis. It does not correspond to any user ID in the web application and does not store any personally identifiable information. |
__cfduid | 29 days 23 hours 59 minutes | The cookie is used by cdn services like CloudFare to identify individual clients behind a shared IP address and apply security settings on a per-client basis. It does not correspond to any user ID in the web application and does not store any personally identifiable information. |
__cfduid | 1 year | The cookie is used by cdn services like CloudFare to identify individual clients behind a shared IP address and apply security settings on a per-client basis. It does not correspond to any user ID in the web application and does not store any personally identifiable information. |
__cfduid | 29 days 23 hours 59 minutes | The cookie is used by cdn services like CloudFare to identify individual clients behind a shared IP address and apply security settings on a per-client basis. It does not correspond to any user ID in the web application and does not store any personally identifiable information. |
_ga | 1 year | This cookie is installed by Google Analytics. The cookie is used to calculate visitor, session, campaign data and keep track of site usage for the site's analytics report. The cookies store information anonymously and assign a randomly generated number to identify unique visitors. |
_ga | 1 year | This cookie is installed by Google Analytics. The cookie is used to calculate visitor, session, campaign data and keep track of site usage for the site's analytics report. The cookies store information anonymously and assign a randomly generated number to identify unique visitors. |
_ga | 1 year | This cookie is installed by Google Analytics. The cookie is used to calculate visitor, session, campaign data and keep track of site usage for the site's analytics report. The cookies store information anonymously and assign a randomly generated number to identify unique visitors. |
_ga | 1 year | This cookie is installed by Google Analytics. The cookie is used to calculate visitor, session, campaign data and keep track of site usage for the site's analytics report. The cookies store information anonymously and assign a randomly generated number to identify unique visitors. |
_gat_UA-326213-2 | 1 year | No description |
_gat_UA-326213-2 | 1 year | No description |
_gat_UA-326213-2 | 1 year | No description |
_gat_UA-326213-2 | 1 year | No description |
_gid | 1 year | This cookie is installed by Google Analytics. The cookie is used to store information of how visitors use a website and helps in creating an analytics report of how the wbsite is doing. The data collected including the number visitors, the source where they have come from, and the pages viisted in an anonymous form. |
_gid | 1 year | This cookie is installed by Google Analytics. The cookie is used to store information of how visitors use a website and helps in creating an analytics report of how the wbsite is doing. The data collected including the number visitors, the source where they have come from, and the pages viisted in an anonymous form. |
_gid | 1 year | This cookie is installed by Google Analytics. The cookie is used to store information of how visitors use a website and helps in creating an analytics report of how the wbsite is doing. The data collected including the number visitors, the source where they have come from, and the pages viisted in an anonymous form. |
_gid | 1 year | This cookie is installed by Google Analytics. The cookie is used to store information of how visitors use a website and helps in creating an analytics report of how the wbsite is doing. The data collected including the number visitors, the source where they have come from, and the pages viisted in an anonymous form. |
attributionCookie | session | No description |
cookielawinfo-checkbox-analytics | 1 year | Set by the GDPR Cookie Consent plugin, this cookie is used to record the user consent for the cookies in the "Analytics" category . |
cookielawinfo-checkbox-necessary | 1 year | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary". |
cookielawinfo-checkbox-necessary | 11 months | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary". |
cookielawinfo-checkbox-necessary | 11 months | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary". |
cookielawinfo-checkbox-necessary | 1 year | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary". |
cookielawinfo-checkbox-non-necessary | 11 months | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Non Necessary". |
cookielawinfo-checkbox-non-necessary | 11 months | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Non Necessary". |
cookielawinfo-checkbox-non-necessary | 11 months | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Non Necessary". |
cookielawinfo-checkbox-non-necessary | 1 year | This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Non Necessary". |
cookielawinfo-checkbox-performance | 1 year | Set by the GDPR Cookie Consent plugin, this cookie is used to store the user consent for cookies in the category "Performance". |
cppro-ft | 1 year | No description |
cppro-ft | 7 years 1 months 12 days 23 hours 59 minutes | No description |
cppro-ft | 7 years 1 months 12 days 23 hours 59 minutes | No description |
cppro-ft | 1 year | No description |
cppro-ft-style | 1 year | No description |
cppro-ft-style | 1 year | No description |
cppro-ft-style | session | No description |
cppro-ft-style | session | No description |
cppro-ft-style-temp | 23 hours 59 minutes | No description |
cppro-ft-style-temp | 23 hours 59 minutes | No description |
cppro-ft-style-temp | 23 hours 59 minutes | No description |
cppro-ft-style-temp | 1 year | No description |
i18n | 10 years | No description available. |
IE-jwt | 62 years 6 months 9 days 9 hours | No description |
IE-LANG_CODE | 62 years 6 months 9 days 9 hours | No description |
IE-set_country | 62 years 6 months 9 days 9 hours | No description |
JSESSIONID | session | The JSESSIONID cookie is used by New Relic to store a session identifier so that New Relic can monitor session counts for an application. |
viewed_cookie_policy | 11 months | The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data. |
viewed_cookie_policy | 1 year | The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data. |
viewed_cookie_policy | 1 year | The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data. |
viewed_cookie_policy | 11 months | The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data. |
VISITOR_INFO1_LIVE | 5 months 27 days | A cookie set by YouTube to measure bandwidth that determines whether the user gets the new or old player interface. |
wmc | 9 years 11 months 30 days 11 hours 59 minutes | No description |
Cookie | Duration | Description |
---|---|---|
__cf_bm | 30 minutes | This cookie, set by Cloudflare, is used to support Cloudflare Bot Management. |
sp_landing | 1 day | The sp_landing is set by Spotify to implement audio content from Spotify on the website and also registers information on user interaction related to the audio content. |
sp_t | 1 year | The sp_t cookie is set by Spotify to implement audio content from Spotify on the website and also registers information on user interaction related to the audio content. |
Cookie | Duration | Description |
---|---|---|
_hjAbsoluteSessionInProgress | 1 year | No description |
_hjAbsoluteSessionInProgress | 1 year | No description |
_hjAbsoluteSessionInProgress | 1 year | No description |
_hjAbsoluteSessionInProgress | 1 year | No description |
_hjFirstSeen | 29 minutes | No description |
_hjFirstSeen | 29 minutes | No description |
_hjFirstSeen | 29 minutes | No description |
_hjFirstSeen | 1 year | No description |
_hjid | 11 months 29 days 23 hours 59 minutes | This cookie is set by Hotjar. This cookie is set when the customer first lands on a page with the Hotjar script. It is used to persist the random user ID, unique to that site on the browser. This ensures that behavior in subsequent visits to the same site will be attributed to the same user ID. |
_hjid | 11 months 29 days 23 hours 59 minutes | This cookie is set by Hotjar. This cookie is set when the customer first lands on a page with the Hotjar script. It is used to persist the random user ID, unique to that site on the browser. This ensures that behavior in subsequent visits to the same site will be attributed to the same user ID. |
_hjid | 1 year | This cookie is set by Hotjar. This cookie is set when the customer first lands on a page with the Hotjar script. It is used to persist the random user ID, unique to that site on the browser. This ensures that behavior in subsequent visits to the same site will be attributed to the same user ID. |
_hjid | 1 year | This cookie is set by Hotjar. This cookie is set when the customer first lands on a page with the Hotjar script. It is used to persist the random user ID, unique to that site on the browser. This ensures that behavior in subsequent visits to the same site will be attributed to the same user ID. |
_hjIncludedInPageviewSample | 1 year | No description |
_hjIncludedInPageviewSample | 1 year | No description |
_hjIncludedInPageviewSample | 1 year | No description |
_hjIncludedInPageviewSample | 1 year | No description |
_hjSession_1776154 | session | No description |
_hjSessionUser_1776154 | session | No description |
_hjTLDTest | 1 year | No description |
_hjTLDTest | 1 year | No description |
_hjTLDTest | session | No description |
_hjTLDTest | session | No description |
_lfa_test_cookie_stored | past | No description |
Cookie | Duration | Description |
---|---|---|
loglevel | never | No description available. |
prism_90878714 | 1 month | No description |
redirectFacebook | 2 minutes | No description |
YSC | session | YSC cookie is set by Youtube and is used to track the views of embedded videos on Youtube pages. |
yt-remote-connected-devices | never | YouTube sets this cookie to store the video preferences of the user using embedded YouTube video. |
yt-remote-device-id | never | YouTube sets this cookie to store the video preferences of the user using embedded YouTube video. |
yt.innertube::nextId | never | This cookie, set by YouTube, registers a unique ID to store data on what videos from YouTube the user has seen. |
yt.innertube::requests | never | This cookie, set by YouTube, registers a unique ID to store data on what videos from YouTube the user has seen. |