Copilot  

An Intro to M365 Copilot Agents

Introduction

Nowadays, we hear a lot of terms in the Artificial Intelligence world, like Gen AI, Agents, and Autonomous Agents, especially when it comes to automating tasks from simple to complex. In simple words, an agent can be defined as a specialized assistant that optimizes business processes and enhances the user productivity and experience. Think of a situation where you are required

  • To run a SharePoint site usage report

  • Get all the expired SPNs (Service Principal Names) in the Entra,

  • Get an inventory of all the agents in your tenant

  • Get the frequently used flows in a Power Platform environment

  • Get the documents that are externally shared in SharePoint sites

  • and much more

For any of these tasks, you can work on the ways to get it done, either by using a flow with a premium connector or writing a powershell script with Graph Powershell modules. Imagine you want to get this job once a quarter, then you can

  • Either run these reports manually

  • Or schedule the jobs using Azure Automation

  • or PowerShell with premium connector

  • or use Azure functions in conjunction with Logic Apps

  • or schedule jobs in a dedicated VM to run the batch jobs on a designated schedule

What if you have a chat application that does the job, accepting the user input in plain English (aka simple prompt in AI terminology) and gives you the desired output instantaneously? This is where Agent comes to picture. With the evolution of Copilot, MSFT introduced Copilot Agents, which allow users to design, develop, and deploy agents easily without worrying about the backend infrastructure. Please note that you need to have Copilot licenses assigned to users to develop and deploy the agent.

Anatomy of the Copilot agent:

A copilot agent is an agent that is built on top of Copilot infrastructure. It can also be defined as the agent that is extending the Copilot chat and scoping to specific needs. It comprises the following building blocks

Knowledge

This is where you tell the agent to look for information when the user asks a question. The knowledge component involves integration of MS Graph, which contains information about users, user activities, and organizational data. This allows agents to access user information, Teams chat, emails, etc.

Skills

This component can be used to add capabilities to the agent. For instance, you can add the capability of generating a code, generating an image, sending an email, creating a note in OneNote, or anything that you want the agent to perform on the user’s behalf.

Foundation Models

These are the models coming from the Azure AI Foundry, which are provided by Microsoft. In the Copilot agent, you don’t have an option to choose the AI model. In fact, the Copilot agent will use the same infrastructure as Copilot chat.

Orchestrator

The job of the orchestrator is to make sure the Foundation models are generating the correct / intended responses. As shown in the block diagram, it manages the flow between user experience, knowledge, and Skills and makes sure the response generated is related to the user’s context. You don’t have an option to choose your own orchestrator. This is from MSFT.

AnatomyOfCopilotAgent

What is a declarative agent

Now, let’s try to understand what a declarative agent is. In software terms, declarative means the user provides input and expects the output. The user won’t need to know the details of

  • How the input is sent to the backend,

  • What processes are happening at the backend and

  • How is the output being generated?

All the users care whether the generated output is accurate or not.

Pre-requisites

To design, develop, and deploy the agents, you need a Microsoft 365 Copilot license in addition to E5 licenses.

Building Agents

The picture below from MSFT documentation shows that there are 3 different ways to create agents for M365. You have no-code, low-code and pro-code options

MSFTWaystobuild

Based on the above picture, building agents can be divided into 3 flavors.

WaysToBuildAgents

User Interface for AI (UI for AI)

These are no-code tools, where users just use the UI option to create the agents. The link in the references section from MSFT guides on how to create the agent, and it is very simple to design and deploy. It is just like filling out an application form, defining the knowledge and agent behavior, and you have an agent built in minutes. The tools that can be used in this category are

  • Copilot Studio Lite (formerly Agent Builder), which is available from Copilot Chat (https://m365.cloud.microsoft). You can follow the link below to create an agent using Copilot Studio Lite

https://github.com/MicrosoftDocs/m365copilot-docs/blob/main/docs/copilot-studio-lite-build.md 

  • SharePoint agents that are available in SharePoint sites, which are scoped to a single SharePoint site collection. You can follow the link below to create SP agents.

https://support.microsoft.com/en-us/office/create-a-sharepoint-agent-d16c6ca1-a8e3-4096-af49-67e1cfdddd42 

Visual Interface for AI (VI for AI)

This option contains pre-defined / pre-designed action blocks where users can drag and drop and connect the actions seamlessly using a visual interface. This is like creating flows in Power Automate. You can design a very simple agent or a custom complex agent using all the available connectors and plug-ins. You have the option of designing your own connector.

You can follow the instructions below from MSFT, which guide from a very simple scenario to designing and developing a complex agent.

https://microsoft.github.io/agent-academy/recruit/

Code Interface for AI

This option is for pro-coders wanting to develop the agent using an IDE and SDKs. The recommended approach from MSFT is to use VS Code (lightweight IDE) with the M365 Agents SDK extension. You can follow the link below that guides users on building different agents using the pro-code approach.

https://microsoft.github.io/copilot-camp/ 

Benefits

Below are some of the benefits of Copilot Agents.

Streamline your workflow

  • Agents can automate repetitive tasks to save time and increase efficiency.

Make Informed Decisions

  • Agents leverage data-driven insights to enhance your decision-making process

Boost Productivity

  • Agents empower your team to achieve more with enhanced productivity tools.

Use-cases

  • Site Assistant in SPO site: Summarization of documents and wiki pages

  • Hiring assistant: helps in filtering the profiles based on user's prompt

  • Human Resources Benefits assistant: Explaining the benefits by taking prompts

  • Azure Dev Board Monitoring assistant: To monitor and get the latest content and stats from Azure resources

  • Product Support Assistant: helping the users in troubleshooting and giving specific information about the product from knowledge sources.

Conclusion

Thus, in this article, we have seen

  • What is an agent and a copilot agent and

  • the building blocks of agents

  • Pre-requisite for building agents

  • Ways to build agents with reference links

  • Use-cases

  • Benefits of Copilot agents.

Hope you find this article useful.

References

Membership not found