Automation with Microsoft Copilot y Power Automate has become one of the fastest ways to streamline repetitive processes, connect applications, and reduce manual tasks without getting bogged down in code. If you also work with Copilot Studio and agents, the next logical step is to create flows that these agents can execute in real time to provide much richer and more useful responses to your users.
Throughout this guide we will see how Create workflows with Microsoft Copilot, Copilot Studio, and Power AutomateYou'll learn what technical requirements to consider, how to leverage natural language to design complex automations, and how to manage capacity. You'll see practical examples, such as a flow that returns the weather forecast, prompt ideas for Copilot, and best practices to ensure your flows are fast, reliable, and easy to understand, even for non-technical users.
What are agent flows in Copilot Studio and why do they matter?
The Agent workflows in Copilot Studio These are cloud flows designed to function as tools that an agent (your custom Copilot) runs within a conversation. Instead of simply generating text, the agent can call a flow, ask queries, execute business logic, and return the result to the user in a fully integrated way.
A flow of this type consists of a specific trigger for agents and at least one actionThis typically ends with a response to the agent itself. This allows the bot to orchestrate complex tasks and then use that information as part of the conversation with the user.
The great advantage is that these flows are deterministic and rule-based. With the same input, the result will always be the same, something essential when we talk about automating critical steps in a process or applying sensitive business logic that cannot be left to the improvisation of a generative model.
In addition, Copilot Studio offers a unified environment where you can design, monitor, and analyze your agent flows From a single dashboard. From there you can see name, description, status, performance, and even information to identify bottlenecks and opportunities for improvement.
Requirements for a flow to function correctly with an agent
For a cloud flow to act as an agent tool in Copilot Studio, simply creating it in Power Automate isn't enough. It must meet a series of requirements. very specific technical conditions to integrate properly into the chat experience.
The first step is to use the correct trigger. The flow must begin with the trigger. “When an agent calls the flow”This type of trigger tells the system that the flow can be invoked from an agent, either from a specific topic or through generative orchestration.
Secondly, it is mandatory to include an exit action of the type “Respond to the agent”This action sends the information back to the Copilot so it can use it in the conversation, with parameters and variables that you explicitly define (e.g., text, numbers, summaries, etc.).
Another key point is that the flow must respond in real time and not asynchronouslyIn the "Respond to Agent" action settings, under "Network," the asynchronous response option must be disabled. Otherwise, the user will be left waiting indefinitely for a response that never arrives while the workflow continues in the background.
Finally, time also matters. The flows must respond to the agent. within a maximum of 100 seconds per action. To stay within this limit, it's advisable to optimize internal logic, reduce unnecessary queries, and limit the amount of data returned to Copilot. Tasks that require more time can be placed after the "Respond to agent" action. This way, they will continue to run until the standard Power Automate limit (up to 30 days), but without blocking the conversation.
How to create an agent flow from Copilot Studio step by step
When you create a new agent flow directly from Copilot Studio, the system makes your life much easier: The trigger “When an agent calls the flow” and the action “Respond to the agent” are already preconfigured in a basic template. This reduces errors and ensures compatibility from the very beginning.
The flow is linked to an agent topic in the form of a tool. Thus, when the user reaches a certain point in the dialogue or asks a specific question, the agent can decide to call that flow, pass it parameters, and use the result in its response.
Add a new empty agent flow to a theme
The first part of the process consists of create the skeleton of the flow and associate it with the topic which will trigger its execution. In short, the steps are these:
- Enter the page of Themes of the agent you want to work with.
- Open the topic from which you want to call the flow.
- Anywhere in the dialog tree, click on the icon of “Add node” and choose the option “Add a tool”.
- In the section of Basic tools, select “New agent flow”The agent flows page will open with a template ready to edit, which already includes the agent trigger and response action.
- Publish that flow immediately to save it, even if you haven't added your logic yet. You'll see a successful creation notification.
- Return to the agent using the corresponding button; a new node of type will appear in the topic AGENDA associated with the flow.
- Save the topic to confirm that the tool is linked to the agent.
With this you have what we could call a Agent flow “shell” ready for you to input your business logic that you need: calls to connectors, conditions, loops, data processing, etc.
Configure actions and parameters in the flow (example with weather forecast)
Once the template is created, you can enrich the flow with specific actions. A very instructive example is that of an agent who Returns the current weather forecast for a specific city using MSN Weather.
To do this, you first return to the flow from the topic's action node, using the link “View flow details”On the general information screen, you can take the opportunity to change the name to something recognizable, such as "Get current weather forecast." This may seem like a minor detail, but A good name greatly simplifies maintenance when you have a lot of cash flow.
In the flow designer, you edit the "When an agent calls the flow" trigger and define the input parameters that the agent can pass to it. For example, a text field for the city and another type number for the Postal CodeThese parameters will then be reused in internal actions.
Below the trigger, you add a new action by searching for the connector of “The weather on MSN” and selecting “Get forecast for today”. In the location field, you insert dynamic content from the “City” parameter and do the same with the “Postal Code”. This way, the action will query the forecast based on what the user asked the agent.
Finally, in the "Respond to the agent" action, you define the outputs that the Copilot will use to construct its response. For example, you can add variables such as day_summary (text with the summary of the day), location (text with the location) or chance_of_rain (number with the probability of rain). Again, the goal is for the agent's response to be rich and structured, not just a generic message without context.
Once the inputs and outputs are configured, you publish the flow and it's ready to be called from the theme or from the generative orchestration. The key is to clearly align input parameters, internal actions, and output fields so that the agent can reason about the data in a coherent way.
Management of connections and credentials in workflows linked to Copilot
Another aspect that should not be overlooked is what Connections and credentials use flows when executed as part of an agent. In authenticated environments that allow it, flows can be executed using the credentials of the user interacting with the Copilot, which is especially useful when the information is sensitive or specific to each person.
When using flow in a compatible channel, normally There is no need to configure anything special in the agent itself.Each user can manage their connections when using the bot, just as they would when running a flow independently in Power Automate.
However, in environments that employ customer managed keys (CMK) There are still restrictions: cloud flows cannot be run with client credentials as part of generative orchestration or from themes. In these cases, it's important to verify that the "run-only" setting for flows is configured for specific connections and not the generic "User-provided run-only" option.
In practice, this involves coordinating with the platform administrator to to line up AI agent securitycompliance and user experience before exposing sensitive flows within a corporate Copilot.
Create cloud workflows with Copilot in Power Automate
Beyond agent workflows, Copilot is integrated directly into Power Automate to help you design cloud flows using natural languageInstead of starting from a blank template and searching for connectors one by one, you can describe what you want to achieve and let Copilot generate an initial proposal.
The typical process starts by logging into Power Automate and making sure you are in the section Home From the side menu. There you'll see a field like "Create your automation with Copilot" where you can write, in plain Spanish, how your workflow should work.
The more detailed the description, the better. Copilot uses that information to suggest a trigger and one or more actions that fit the requirements.
When you're satisfied with the proposal, you can keep it as is with the "Keep and Continue" option or request adjustments by adding more details in the text box. Copilot will regenerate the flow structure to adapt it to the new requirements. Thus, the design becomes a iterative conversation process more than in a traditional manual edition.
After accepting the suggested architecture, Power Automate will ask you to review and complete the necessary connections. You'll see which connectors have correct credentials (marked with a green symbol) and which require attention (with a warning icon). Once this is sorted, simply click "Create flow" and fine-tune the final details using the visual designer and the Copilot panel on the right.
How to write good requests for Copilot when creating flows
The quality of the flow generated by Copilot depends largely on how well you phrase your requestIt's not just about asking for something generic, but about clearly explaining what event triggers the flow, what actions you want to be executed, and what connectors should be involved.
The pattern works very well. “When X happens, do Y”For example: “When an email arrives from sales@company.com, save the attachment to a SharePoint library and post a message in the 'Sales' Teams channel with the file name.” This type of structure greatly increases the chances of Copilot getting it right the first time.
It's also a good idea to be as specific as possible. Instead of saying "I want to process an email," you can indicate that you want to send the email subject to a specific Teams channel Or perhaps you want to store certain data in a specific SharePoint list. The more precise the data, the less readjustment work you'll need to do later.
If you know which connectors you want to use, mention them directly in the request: Outlook, Teams, Forms, SharePoint, etc. Copilot is able to interpret those names and configure the appropriate actions for each of them, which saves time and testing.
And if the first attempt isn't perfect, that's okay: the idea is to keep trying. testing variations of the same requestfine-tuning details until you find the flow you need. Copilot is designed precisely for that give and take with the user.
Edit existing flows with Copilot's capabilities
Not only can you create new automations with Copilot; it's also possible Refine existing flows in the new cloud flow designerThis experience is only available in the modern designer, not the classic one, so it's recommended to migrate your workflows if you want to take full advantage of it.
To use Copilot in an existing workflow, go to Power Automate, then... “My flows” Then, for the item you want to modify, select the edit option (either from the three dots or from the details page). The flow opens with the Copilot panel on the right, ready to receive instructions in natural language.
From there you can give it commands like “delete the action“At the end of the flow, I want to send an email with a subject line that matches the SharePoint file name,” or “Instead of an email, I want to post a message to a Teams channel.” Copilot translates these instructions into actual changes to the flow diagram.
It's also possible to set up more advanced scenarios. For example: "Check if each of the returned SharePoint items has a title 'USB' and, if so, send an email." In this way, You can enter conditions and filtering logic without needing to build them piece by piece in the visual interface. Although you can always review and adjust the settings manually afterwards.
This combination of conversation-guided editing and detailed visual control makes maintaining complex workflows much more manageable, even for business teams that don't consider themselves technical.
Hyperautomation, AI and low-code platforms: the context of Copilot
Behind all these capabilities lies a broader trend: the hyperautomationThis involves automating as much as possible within an organization by combining AI, RPA, low-code platforms, and process mining. Microsoft Copilot and Copilot Studio are situated precisely at this intersection.
The artificial intelligence integrated into these tools enables automation Don't just follow a fixed scriptInstead, they learn from data, recognize patterns, adapt to changes, and make decisions in real time. Agents powered by cloud workflows can handle increasingly complex tasks, without requiring constant manual intervention.
Low-code or no-code platforms make it easier for non-technical profiles, such as business analysts or operators, to design and manage their own workflows. Thanks to drag-and-drop interfaces, templates, and AI assistants, The barrier to entry is lowered and the IT team is no longer the bottleneck for every small change in a process.
Furthermore, process and task mining offers an objective view of how processes actually run in practice. With this data, it's easier to see where it's worthwhile to focus efforts. Invest in automation, measure the impact of changes and continue iterating to improve results.
All of this points to the idea that Copilot workflows aren't just small, isolated utilities, but pieces of a larger machine that helps organizations become more agile and scalable. Perfectly prepared for whatever comes next.
Agent flow capacity usage and licensing in Copilot Studio
When designing agent flows, it is important to keep in mind that Each action performed consumes Copilot Studio's capacityThis is not a minor detail, because as your automations grow, so will the associated consumption, and it's important to plan for that.
From the Power Platform admin center, in the section of Licenses > Copilot StudioYou can review how many agent flow actions each flow has consumed. This gives you a clear view of which processes are the most "expensive" in terms of capacity and where you could optimize them.
Interestingly, the tests you run from the designer don't consume Copilot Studio's capacity. However, they can consume resources from other billable services, such as specific generative models. Therefore, you can iterate on your design with some peace of mind before putting the flow into production.
The cost also depends on how the flow is invoked. If it's run from an agent theme, it consumes a standard agent response plus the agent flow actions. If it's called using generative orchestration, it counts as a standalone action plus the flow actions. And if you test it from the test chat embedded in the agent, only the agent flow actions are counted, not the direct chat messages.
Having these rules clear allows Properly assess the necessary capacity and avoid surprisesEspecially in projects where workflows are executed very frequently or are exposed to a large number of users.
Convert Power Automate flows into agent flows
If you already have automations in Power Automate that work well, you might not want to recreate them from scratch. The good news is that you can convert an existing cloud flow into an agent flowso that it is managed in Copilot Studio and consumes its capacity instead of that of Power Automate.
To do this, you must ensure that the flow is part of a solution. On the flow details page in Power Automate, if the tile appears... “Solutions”This means it's already included. If not, you'll need to add it to a solution before continuing.
Another requirement is that the workflow must be in the Power Platform environment where you want to use Copilot Studio capabilities. If this capability is not yet assigned, you will need to coordinate with your administrator to configure it correctly.
Once those conditions are met, you edit the flow and change its plan to “Copilot Studio”After saving, the system will ask you to confirm that you want to convert it; this is an important step because it is a one-way operation. can't be undoneprecisely because of the associated change in the billing model.
After the conversion, you can use that flow as part of your agents, take advantage of Copilot Studio's tracking and capabilities, and continue to access it from Power Automate as well, offering considerable flexibility for hybrid scenarios.
Activate or deactivate Copilot in Power Automate depending on the region
Copilot availability in Power Automate may vary depending on the region where your tenant is staying and the presence of GPUs in that region. In locations where GPU resources are available (such as the UK, Australia, the US, or India), Copilot is usually enabled by default at the tenant level. To disable it, an administrator must... contact support and use a PowerShell script to disable Copilot globally for the tenant, since there is currently no fine-grained control per environment.
In regions without GPUs (except in sovereign clouds), Copilot is also enabled by default, but through the mechanism of data exchange between geographical areasIf you need to disable it, you can do so by disabling that data exchange from the Power Platform admin center, also at the tenant level.
Whatever your situation, it's advisable to align this configuration with the policies of compliance, privacy and governance and the principles of Zero Trust in the Age of AI of your organization before massively deploying cloud flows with Copilot and agents in production.
The combination of agent flows, Copilot in Power Automate, Process Mining, and integration with low-code platforms makes Microsoft Copilot a very powerful tool for transforming processes: It allows you to move from isolated automations to a coherent ecosystem of agents, flows, and analytics. that anyone in the company can understand, adjust, and scale with relative ease, provided that technical requirements, capacity management, and good application design and security practices are taken into account.
