Copilot - The 5 Lanes of Development

Copilot - The 5 Lanes of Development

I've just begun my journey with Copilot Studio, and it feels like reconnecting with an old friend. It shares the familiar look and feel of Power Virtual Agents, along with many features that one would anticipate from Power Automate.

Copilot Studio can be described as a tool with a structured 5-lane development approach. This breakdown into distinct lanes facilitates newcomers in exploring the capabilities of Copilot Studio, providing a comprehensive overview of what can be accomplished within a project.


Click here for a larger version
The 5 lanes of development in Copilot Studio (click the image for a larger version)


1) Self-contained or scripted lane: In this foundational lane of development within Copilot Studio, envision creating simple interactions like greetings for user inputs such as "hi" or "hello." This lane allows you to generate basic, scripted responses or extend the complexity to provide straightforward informational replies. It serves as the fundamental layer of development in Copilot Studio.

2) Plugins and connectors enabled lane: Moving to the second lane, the focus shifts to leveraging plugins and connectors. Here, conversations can become more intricate as you integrate plugins and connectors to collect user input and communicate with various services such as Azure and M365. Whether utilizing Power Automate flows or plugins for specific services like Azure Entra ID or SQL Server, this lane enhances the depth of interaction.

3) Generative answers enabled lane: Advancing further, the third lane introduces a significant enhancement. User input is directed to Azure OpenAI, enabling the retrieval of generative answers from diverse sources in tandem with Azure AI Search. The extensibility of plugins and connectors persists, providing flexibility in handling data obtained from Azure OpenAI's generative responses.

4) Automation lane: The fourth lane showcases the potential when integrating other bots through the Azure AI Bot Service - https://azure.microsoft.com/en-us/products/ai-services/ai-bot-service. By reusing existing bots within your bot, such as those interacting with SQL Server for booking updates, you can streamline processes. This lane emphasizes efficiency by avoiding the recreation of specific functionalities within your bot.

5) System lane: Concluding the development lanes is the "System Lane." Essential in every bot, this internal mechanism supports the normal functionality of the bot. Events within this lane, like "Conversation Start," can be customized to query user information, infusing the conversation with data from previous interactions stored in Azure Cosmos DB or retrieving information from a SharePoint List to present to the user at the conversation's outset. Caution is advised with customizations, as certain events in this lane are crucial for the bot's expected behavior.


Conclusion

Essentially, a bot is comprised of various topics, spanning a spectrum from minimal to substantial complexity. Regardless of the scale of your project, it ultimately aligns with no more than 5 development lanes, covering a spectrum from fundamental to intricate. Importantly, none of these lanes is mutually exclusive; you have the flexibility to incorporate all of them into your bot.

Moreover, if desired, you can selectively disable all system topics within your bot (if this is a requirement in your project).

While there is much more to explore, my intention was to provide you with an initial overview of what you can anticipate within a Copilot Studio project. I hope all of this makes sense in your journey. Happy trails!



#copilot #m365copilot #copilotstudio #azureai #azureopenai #ai

要查看或添加评论,请登录

Alex G的更多文章

  • Batch Updating Windows Task Scheduler

    Batch Updating Windows Task Scheduler

    Have you ever heard of the proverbial needle in the virtual haystack? Well, if you haven't, allow me to introduce you…

  • Bringing OpenAI to SharePoint Online

    Bringing OpenAI to SharePoint Online

    In this article, I will explain how I built a fully functional chat assistant powered by Azure OpenAI, which uses my…

    26 条评论
  • The SharePoint Online "User Information List" - a Graph API approach

    The SharePoint Online "User Information List" - a Graph API approach

    In the past when looking for SharePoint users I would go down with Get-PnPUser to get the user list from a given…

    14 条评论
  • Updating M365 User Profiles (Delve)

    Updating M365 User Profiles (Delve)

    About two or three years ago I was asked by a customer to develop a way to update Delve user profiles, the customer was…

    2 条评论
  • Building a Scalper Bot

    Building a Scalper Bot

    How it started? A while ago, back in December, I was telling my wife about an article I just read on how difficult was…

社区洞察

其他会员也浏览了