\u201cPower Automate allows you to optimize your business processes across your organization and automate repetitive tasks. This service helps you create automated workflows between your favorite apps and services to synchronize files, get notifications, collect data, and more.\u201d<\/p>\n
Some key points can be derived from above definition:<\/p>\n
- \n
- Power Automate is a tool to create automated workflows.<\/li>\n
- Power Automate acts as a process orchestrator and connects multiple steps.<\/li>\n
- Power Automate can connect to systems and apps that can reside inside the Microsoft 365 and Azure ecosystem <\/strong>(SharePoint, Outlook, Teams, Blob Storage) or completely exist outside of it<\/strong> (Hubspot, Gmail or SAP).<\/li>\n<\/ul>\n
We have a complete blog on Power Automate<\/a> if you\u2019re interesting in learning more on Power Automate\u2019s capabilities and features.<\/p>\n
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-1.webp\")
<\/p>\t\t\n\t\t\t\n\t\t\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tVon der Vision zur Umsetzung<\/p>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\n\t\t\t\t\tOb Sie gerade erst mit der Automatisierung beginnen oder diese ausbauen, wir helfen Ihnen, Ihre Ideen in wirkungsvolle L\u00f6sungen zu verwandeln.<\/p>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\t\t\t\n\t\t\t\n\t\t\t<\/i>\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\t\t\t\n\t\t\t\n\t\t\t<\/i>\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<\/div>\nFlows: Logic and Structure<\/h3>\n
A flow<\/strong> is an automated process that performs steps or actions, it\u2019s based on a trigger (i.e., something needs to happen for the process to start) and it can include conditions, loops, variables and all the \u201ctraditional\u201d concepts of programming. It is usually designed to handle repeatable, rule-based tasks<\/strong> with little or no human intervention.<\/p>\n
Flows usually:<\/p>\n
- \n
- Run based on structured logic (inputs,\u00a0pre-defined\u00a0conditionals, set of steps)<\/li>\n<\/ul>\n
- \n
- Uses rules<\/li>\n<\/ul>\n
- \n
- Deterministic outcome (e.g. fill out a template, create a new client, notify someone)<\/li>\n<\/ul>\n
As a summary, flows are a series of steps that follow logic and structure and usually have deterministic inputs and outputs.<\/p>\n
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-2.webp\")
<\/p>\nTypical use cases<\/h3>\n
Based on above, Power Automate is ideal for automating structured, repeatable processes that follow clear rules. Some examples are:<\/p>\n
- \n
- Sequential approvals<\/a>. Power Automate is the perfect tool to handle approval requests when new projects are created. The approval assignment can be based on rules such as: Company, Cost Center and Project Amount.<\/li>\n
- Customer Onboarding automation. Customer onboarding is usually a process with\u00a0many steps and requirements and it\u2019s usually rule-based: creating new customers in 3 different systems, creating a contract template based on conditions.<\/li>\n
- Data entry automation<\/a>. Tax forms are standard every month and there are specific rules to follow to fill out, so Power Automate comes in really handy as the perfect tool for this process.<\/li>\n<\/ul>\n
It\u2019s key to mention that Power Automate can also integrate Artificial Intelligence (AI) features inside workflows. For example, we can create a workflow that starts every time a new client signs a contract in DocuSign and use an AI service to read the PDF content and based on the results of this action, send an approval request (rule-based) or fill out an Excel template (deterministic outcome). This doesn\u2019t mean the workflow is an agent, it just means it\u2019s using AI features to perform some parts of the automation.<\/p>\n
Copilot Studio and Agents<\/h2>\n
Now that we know what Power Automate is, let\u2019s talk about the other side of the equation: Copilot Studio and Agents, but before getting into deep waters, let\u2019s clarify that Copilot Studio and Copilot are different products.<\/p>\n
Copilot<\/strong> (without \u201cStudio\u201d in the name) is the ready-to-use AI assistant built by Microsoft, that can be used in all the apps we already know: Outlook, Excel or PowerPoint. The little icon bugging us everywhere, offering help. Copilot Studio is the tool to build our own AI agents. In this blog, we\u2019re referring to Copilot Studio<\/strong>.<\/p>\n
What is Copilot Studio?<\/h3>\n
Microsoft\u2019s official definition<\/a>\u00a0for Copilot Studio is as follows:<\/p>\n
\u201cCopilot Studio is the AI agent platform for Copilot, where you can build agents that help do work. Effortlessly connect agents to your organization\u2019s data, tools, and systems to multiply capacity and accelerate outcomes. Build agents for any scenario\u2014from simple to sophisticated\u2014using natural language and publishing to where you need them.\u201d<\/p>\n
A lot to process from the official definition! But here is a list of key points:<\/p>\n
- \n
- Copilot Studio is the tool to build our own \u201cCopilots\u201d or our own \u201cChatGPTs\u201d<\/li>\n
- With Copilot Studio we can build agents that can do work for us<\/li>\n
- We can connect agents to data and multiple systems<\/li>\n<\/ul>\n
Copilot Studio (and any other tool for building agents) leverage large language models (LLMs) to receive an input or a question and derive an answer or plan actions based on the input.<\/p>\n
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-3.webp\")
<\/p>\nYou can also read our full blog on Copilot Studio fundamentals<\/a>.<\/p>\n
Agents: Context and decision-making<\/h3>\n
Since agents leverage LLMs, an agent can interpret natural language <\/strong>and choose an appropriate (or better said, what the model thinks is appropriate) next step based on the information available.<\/p>\n
When we build agents in Copilot Studio, we usually provide knowledge sources (e.g. an HR Policy document or a SharePoint site with standard procedures for expense reports), tools (e.g. Send emails) and data (e.g. access to a Database). All this information provided helps the agent understand context, make decisions, and act on behalf of a user.<\/p>\n
Based on above, agents usually:<\/p>\n
- \n
- Work based on unstructured logic\u00a0(natural language,\u00a0prompts, instructions)<\/li>\n<\/ul>\n
- \n
- Use context\u00a0to decide, plan or answer<\/li>\n
- Acts based on Intent-based and may have dynamic\u00a0outcome\u00a0
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-4.webp\")
<\/li>\n<\/ul>\nTypical use cases<\/h3>\n
Copilot Studio is ideal for scenarios that require context and decision-making. Some examples are:<\/p>\n
- \n
- Employee self-service for HR processes.<\/strong> Answering questions about maternity leave or vacation policies or guiding through the process of submission and approval of days off.<\/li>\n
- Expense reports.<\/strong> Agents can guide employees through submitting expense reports, validate required information, answer policy questions, and trigger approvals or reimbursements automatically.<\/li>\n
- Categorize support requests and route accordingly<\/strong>. An agent can have a conversation with a user that is having a technical issue and provide quick fixes based on general guidelines but based on the type, urgency, or content of the request, the agent can direct and escalate it to the appropriate team and create support tickets.<\/li>\n<\/ul>\n
AI Models vs Agents<\/h3>\n
It\u2019s very important to also learn the difference between AI Models and Agents. An AI Model can perform a wide range of tasks, but these are usually isolated tasks. For example, an AI model can read a PDF document, summarize text or classify a text as positive or negative.<\/p>\n
AI Models do not have memory and do not take any action. Agents, on the other hand, as we have discussed, use AI as part of a broader system that includes context and memory. AI Models can be used as part of a Power Automate workflow or as part of Agents.<\/p>\n
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-5.webp\")
<\/p>\nCopilot Studio + Power Automate<\/h2>\n
The features and capabilities of Copilot Studio agents and Power Automate flows can be combined and Microsoft has been releasing a lot of new features that leverage the two tools at the same time. And in fact, many of the Power Automate options we see from the portal can be used from Copilot Studio.<\/p>\n
Autonomous agents<\/h3>\n
We think of agents as a conversational tool: someone has a question or needs to submit a support request, so they open Teams, SharePoint or whatever channel has been selected for the agent and start a new chat. But did you know agents can also \u201cstart\u201d actions on their own?<\/p>\n
Using Copilot Studio triggers, we can set up different events that will automatically activate an agent when the event happens.<\/p>\n
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-6.webp\")
<\/p>\nFor example, let\u2019s say
\nwe have an agent that receives IT support tickets from users in a chat, the
\nagent has been trained with guidelines and policies and works just fine. But
\nlet\u2019s assume that we also have an email address (servicedesk@yourcompany.com<\/a>) where users can send emails asking for help.<\/p>\t\t\n\t\t\t\n\t\t\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tAutomatisieren Sie Aufgaben, die Sie verlangsamen<\/p>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\n\t\t\t\t\tGeben Sie Ihrem Team mehr Zeit und erm\u00f6glichen Sie ihm, sich auf strategische Aufgaben zu konzentrieren, dank digitaler und robotergest\u00fctzter Automatisierung.<\/p>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\t\t\t\n\t\t\t\n\t\t\t<\/i>\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\t\t\t\n\t\t\t\n\t\t\t<\/i>\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<\/div>\nWe can connect the
\nservice desk mailbox to the very same agent that was trained for the chat, and
\nit will use the very same instructions, tools, data and knowledge and simply
\nact whenever a new request arrives through email.<\/p>\nThis feature converts an agent that is only
\nconversational to an agent that is also autonomous, and behind the scenes is
\nusing Power Automate workflows and triggers but we don\u2019t need to create
\nseparate automations, it\u2019s all done automatically inside Copilot Studio.<\/p>\nAgent flows<\/h3>\n
Agent flows are just flows that are created from Copilot Studio and they are used to connect agents with automated actions. Agent flows are just the Power Automate interface used inside Copilot Studio.<\/p>\n
Agent flows can receive input data from, perform one or many actions and return a response to the agent.<\/p>\n
Below is an example of a workflow built for a Copilot Studio agent that receives an Order ID from the customer, then queries this order ID in a Dataverse database and updates its status.<\/p>\n
![\"\"](\"https:\/\/powergi.net\/wp-content\/uploads\/an-agent-or-a-flow-img-7.webp\")
<\/p>\nHow our Power Automate and Agenting automation services can help<\/h2>\n
- Expense reports.<\/strong> Agents can guide employees through submitting expense reports, validate required information, answer policy questions, and trigger approvals or reimbursements automatically.<\/li>\n
- Employee self-service for HR processes.<\/strong> Answering questions about maternity leave or vacation policies or guiding through the process of submission and approval of days off.<\/li>\n
- Work based on unstructured logic\u00a0(natural language,\u00a0prompts, instructions)<\/li>\n<\/ul>\n
- Sequential approvals<\/a>. Power Automate is the perfect tool to handle approval requests when new projects are created. The approval assignment can be based on rules such as: Company, Cost Center and Project Amount.<\/li>\n
- Deterministic outcome (e.g. fill out a template, create a new client, notify someone)<\/li>\n<\/ul>\n
- Uses rules<\/li>\n<\/ul>\n
- Run based on structured logic (inputs,\u00a0pre-defined\u00a0conditionals, set of steps)<\/li>\n<\/ul>\n