azurecurve

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:

Describe the objective of your process in natural language, and let AI develop an automation plan to achieve it.
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.
Validate the flow by reviewing how the AI flow is achieving the business objective prior to moving the flow into production.
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.

Click to show/hide the New Functionality In Microsoft Power Automate 2024 Wave 1 Series Index

New Functionality In Microsoft Power Automate 2024 Wave 1
Use Generative AI to Achieve a Process in AI Flows
Receive Intelligent License Recommendations for Admins
Be More Productive with Power Automate and Excel Desktop
View a Power Automate Visual in a Power BI Report
Monitor Performance for Cloud and Desktop Flow Activities
Connect to Other Environments from the Microsoft Dataverse Connector
Push Cloud Flow Execution Data into Application Insights
Use Your Own Encryption Key for Encrypting Data At-Rest for Existing Environments
Create Power Automate Flows in Excel
View Two Action Properties Panes Simultaneously
Use Undo and Redo While You Build Cloud Flows in the Designer
Use Copy-Paste for Container Actions Like Scope, Condition, and Apply to Each
Use a Simplified OData Editor in Actions like Get Items and Get Files
Manage Unpublished Solution-Aware Cloud Flows Using Admin APIs
Cancel all Flow Runs for a Version of a Flow
Create a Flow on a File in Teams
Cloud Flows are Automatically Defined in Dataverse Solutions
Use Workflows on Calendar Events in Teams and Outlook
Create AI Flows in Power Automate
Use Copilot with French Language
Recommendations to Reassign Orphaned Cloud Flows
Generate Descriptions for Cloud Flows using AI
Use Flows with Connections from Users in Copilot Studio
Use Process Mining Microsoft 365 Personal Recommendations
Create and Edit Expressions with Copilot
Get Quick Insights and Recommendations in Copilot for Process Mining
Troubleshoot with Copilot for Cloud Flows Execution
Automate With Ease Using the AI Recorder
Enter into a Conversation-first Copilot Experience to Build Flows
Transform Scripting Using AI-driven Natural Language
Maximize Your Productivity with Generative Answers
Streamline Workflow Creation with the Next Best Action
Generate Flow Description Using AI
Use Natural Language to Create a Flow in Teams
Leverage Desktop Automation with the Power Automate Plugin for Windows Copilot
Set Up Fallback UI Automation Mechanism
Power Fx Integration with Power Automate for Desktop
Use Power Platform Connectors in Power Automate for Desktop Actions
Use CyberArk Credentials in Desktop Flow Connections
Use Azure Key Vault Credentials in Flow Connections
Connect Your Own Virtual Network with Hosted Machine Group
View Attended Desktop Flow Runs Using Picture-in-Picture Execution Mode
Self-heal UI and Browser Automation Actions at Execution with AI
Use the Run Power Fx Expression
Use Python v3 in Power Automate for Desktop
Use Machine to Credential Mapping in Desktop Flow Connections
Create a Reusable Collection of UI Elements
Use Customer-managed Encryption Key for Hosted RPA
Automation Center to Monitor and Manage All Your Automations and Related Assets
Trigger Attended Desktop Flows in Picture-in-Picture
Use Copilot in Automation Center to Analyze Cloud Flow Runs
Trigger Attended Desktop Flows in Picture-in-Picture Mode Through the Power Automate Console
Use Copilot in Automation Center to Analyze Desktop Flow Runs
Use Copilot in Automation Center to Analyze Work Queue Data
Use Copilot in Automation Center to Ask Power Automate Product Questions
Use New Data Table Actions
Use New Excel Actions in Power Automate for Desktop
Use the New Desktop Flow Running Timeout Property
Ingest Process Data from Customers' Data Lake
Scale Faster with Power Automate Process Mining Thin Client App