This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 22nd of the new functionality in the Cloud Flows section is use flows with connections from users in Copilot Studio.

Customize copilots with flows as AI plugins with connections provided by users, instead of needing to be shared and managed by the flow owner. This feature makes it possible to use flows as actions in copilots with other users without needing to use your own connections when others run the flow.

Enabled for: Users, automatically
Public Preview: –
Early Access: –
General Availability:  May 21, 2024

Feature Details

Use flows with connections provided by users in Microsoft Copilot Studio, instead of only the connections embedded in the flow. Users of the copilot are prompted to enter their connections when running the flow is run as an action from a copilot. Makers can choose whether a flow uses connections provided by users and their connections embedded in the flow when it’s run from the run-only setting on the flow’s detail page.

This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 21st of the new functionality in the Cloud Flows section is generate descriptions for cloud flows using AI.

Save time and effort managing your cloud flows with descriptions automatically generated using AI. With this addition, a description is generated for you automatically when editing the details of your cloud flow. This description helps you manage complex flows, create new ones, and use flows as actions in copilots.

Enabled for: Users, automatically
Public Preview: –
Early Access: –
General Availability: Aug 2024

Feature Details

When editing the details of a cloud flow, a description is generated automatically by using Copilot in Power Automate to summarize triggers and actions of the flow. You can adjust or change the generated description with your own or choose to keep the description up to date each time the flow changes. This capability helps with managing complex flows that might have been managed by others. It also quickly creates new flows with a useful description and ensures that it’s available for flows with the ‘Run a flow from Copilot’ trigger that is used to run actions from copilots and other AI surfaces in Power Platform.

When editing a cloud flow with the ‘Run a flow from Copilot’ trigger, a prompt displays to confirm or adjust the generated description if a description isn’t already set. For other cloud flows, the generated description is available when editing the description from the flow’s detail page.

This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 20th of the new functionality in the Cloud Flows section is recommendations to reassign orphaned cloud flows.

Today, admins have difficulty finding and reassigning orphaned flows, and changing flows is done individually. This feature gives admins more visibility and lower risk through active management of their automation estate.

Enabled for: Admins, makers, marketers, or analysts, automatically
Public Preview: Jun 2024
Early Access: –
General Availability: –

Feature Details

With this feature, admins can more easily manage their automation estate with recommendations to show a list of orphaned flows that are owned by a user who is no longer with the company. Admins can view information like the name of the last owner and number of days since the flow last ran within the recommendation list in Power Platform admin center. They can then quickly perform simple actions like reassignment to another owner or turning off the flow.

This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 19th of the new functionality in the Cloud Flows section is use Copilot with French language.

Makers in French speaking countries like France and Canada can use their own native language to interact with copilot tools.

Enabled for: Admins, makers, marketers, or analysts, automatically
Public Preview: –
Early Access: –
General Availability: Jun 2024

Feature Details

Makers in France and Canada can create and edit a flow based on a foreign language prompt, or content can be returned in the subject language. This can help our customer base to interact with copilot tools in the language they are most comfortable in.

This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 18th of the new functionality in the Cloud Flows section is create AI flows in Power Automate.

Copilot workflows enable much more sophisticated automation of business processes. AI flows can simplify and accelerate the automation process by reducing the need for specifying the exact trigger and action sets to execute. This automation can adapt to changing scenarios and data sources by leveraging the AI runtime’s intelligence and reasoning capabilities. It can handle complex and dynamic tasks that involve multiple steps, conditions, loops, branches, and integrations.

Enabled for: Admins, makers, marketers, or analysts, automatically
Public Preview: Jul 2024
Early Access: –
General Availability: –

Feature Details

AI flows are a new type of automation that is authored, tested, and executed through an AI runtime. You specify just the intent of the automation and the AI chooses the correct set of actions in the correct order based on the input, context, and your intent.

You can author AI flows from the Create page or from the My flows page in Power Automate. When you give the system an intent, the AI generates suggested inputs/outputs and static flow values to use in the flow. These are items that the AI suggests. You can choose to accept or reject them and add your own inputs/outputs and flow values. In addition to inputs/outputs and flow values, the system also provides connectors and action that it can use to achieve its intended automation goal. You can again choose to accept, reject, or add your own.

This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 17th of the new functionality in the Cloud Flows section is use workflows on calendar events in Teams and Outlook.

You can boost productivity with calendar-related templates to get ideas for scenarios you might be interested in.

Enabled for: Users, automatically
Public Preview: –
Early Access: –
General Availability: Aug 2024

Feature Details

This feature allows you to create flows on existing and new calendar events. For example, you can configure a flow that is triggered to run at the start or end of a meeting.

This post is part of the New Functionality In Microsoft Power Automate 2024 Wave 1 series in which I am taking a look at the new functionality introduced in Microsoft Power Automate 2024 Wave 1.

The 1st of the new functionality in the AI Flows section is use generative AI to achieve a process in AI flows.

AI flows use generative AI reason over unstructured content and determine what steps and sequence are needed to achieve a process outcome based on instructions and parameters provided by you in natural language.

Enabled for: Admins, makers, marketers, or analysts, automatically
Public Preview: Aug 2024
General Availability: Feb 2025

Feature Details

Instead of building out complex rules-based processes from beginning to end, you work with AI to create an automation plan. When you execute the plan, the LLM considers all the resources available to it and dynamically selects the most appropriate actions to achieve the desired outcome.

Building an AI flow is a fundamentally different user experience than building a rules-based cloud flow or desktop flow. It involves the following steps:

1. Describe the objective of your process in natural language, and let AI develop an automation plan to achieve it.
2. Refine the automation plan generated by the LLM and adjust inputs, outputs, and variables as needed. Add reference sources and guidelines in natural language that influence the LLM as it executes the flow.
3. Validate the flow by reviewing how the AI flow is achieving the business objective prior to moving the flow into production.
4. Review production run history, analytics, and individual flow run details to ensure your process is performing to expectations.

The ability of AI flows to easily incorporate both structured and unstructured data makes it flexible as information resources are updated. Its reasoning abilities make AI flows uniquely beneficial in the building and maintenance of complex process flows to handle conditions, exception management, and process loops.