Update your D365 Customer Service Knowledge Base with Copilot

5 minutes reading time

Update your D365 Customer Service Knowledge Base with Copilot

A strong knowledge base is the bedrock of successful Customer Service teams. Investing in it pays off by accelerating future case resolutions. But what if we could streamline the process of creating these resolutions? Enter Copilot’s Customer Knowledge Management Agent, an autonomous AI designed to speed up and simplify knowledge authoring.

Released in preview in December 2024 for Dynamics 365 Customer Service, this new feature promises to help service teams quickly draft knowledge base articles by scanning information in a case. Copilot will analyse case-related notes, conversations, and emails. 

The Customer Knowledge Management Agent also examines the case content against your existing knowledge base to identify the need for new articles while preventing content duplication. It ensures compliance by removing sensitive data and can be enhanced with custom automated compliance checks tailored to your organisation’s standards. It is one of 10 preconfigured agents in Dynamics 365 that will help organisations move to AI-first business processes. You can also create custom autonomous agents inside Copilot Studio

How will this Copilot Agent help your Knowledge Base?

The added business value is that it will harvest information across different data sources and compile the draft in moments. This reduces the traditionally long knowledge authoring process. Typically, service teams would have to sift through email chains and case notes to begin writing the article when they could solve other cases. 

It’s another example of how Dynamics 365 Customer Service can support your business in delivering positive experiences.

Additionally, actionable insights and tailored analytics empower supervisors to monitor the system’s performance and improve the relevance and quality of knowledge articles, boosting productivity, decision-making accuracy, user satisfaction, and operational efficiency.

Let’s look at an example of how this new AI agent can support Knowledge article creation.

It requires opting in and light configuring in the app settings, but you are good to go once you have set it up.

Configuring Copilot Service Agent

Copilot Drafted Knowledge Articles

When the AI agent is turned on, customer service people will have the option to propose a new knowledge article when a case is closed from the command menu. Copilot is the interface for interacting with autonomous agents, and clicking this menu item will surface a window to let the AI agent draft a article. 

propose-a-new-article

Copilot will automatically begin analysing your resolved case and draft an article that outlines the issue, cause and clear bullet point instructions on how to solve the problem. You will get the opportunity to edit the text yourself or ask Copilot to try again with another revision. For example, if it had overlooked a detail, you could ask it in the prompt box to consider adding an extra step.

Draft article for knowledge base article with copilot customer service

In our example above, a marketing manager had an issue copying email campaigns in their system. Copilot examined the correspondence and case notes and crafted an article that outlined the issue as being unable to copy existing email campaigns. It also understood the cause and provided a number of listed resolution steps. A support team person can then follow these instructions in future cases.

As we are happy with its output in our demo, we will create the proposal for the article. Of course, we can refine this like any other article and collaborate with other service people and supervisors before it’s published in the knowledge base.

A Couple of Caveats…

Because this update was initially released as a preview, some features are missing, at least on our end. At the time of writing, we didn’t see the option to scan historical cases and publish articles automatically. This will help organisations efficiently fill gaps in their knowledge base, a powerful addition to Customer Service. 

In addition, we can’t yet see evidence of knowledge insights.  This will enable supervisors and content managers to oversee the Customer Knowledge Management Agent and track the health and utilisation of the knowledge applied by Copilot. We expect to see this option available when it is out of preview. 

Knowledge Base Insights Preview Copilot
Microsoft has stated this will be available for general availability in April 2025, so fortunately, it’s just around the corner.

Lastly, Copilot’s output will vary depending on the case. More detailed and organised case records with clear information on the issue, cause, and resolution will feed Copilot better data, which will ultimately deliver a better outcome in your proposed article.

Streamlining Knowledge Base Updates with Copilot

Copilot’s Customer Knowledge Management Agent offers a transformative approach to updating Dynamics 365 Customer Service knowledge bases. Automating the creation of knowledge articles from case data reduces response times and enhances efficiency with shorter knowledge article lifecycles. Although still in preview, it can add value to your service team by reducing effort to update your knowledge base. It promises significant improvements in operational workflows and knowledge management.

If you need help configuring your agent to enhance your services, please contact us today.

First Published: January 10, 2025

Receive Updates from ServerSys

Join our mailing list to receive Dynamics 365 and Power Platform insights in your mailbox, typically once or twice each month. You can unsubscribe at any time, and we will never share your data.

Daniel Norris - ServerSys Insights and Resources Author for Dynamics 365 and Power Platform

Daniel Norris

Daniel Norris is the communications manager for ServerSys. His role is to bring you the latest updates, tips, news and guides on Dynamics 365.

If you have any questions, please get in touch with us at hello@serversys.com

Daniel Norris - Linkedin profile