Generative AI capabilities are rapidly changing the customer service space. You can use Copilot in Dynamics 365 Customer Service today to help agents save time on case and conversation summarization as these features do not require your organization’s support knowledge. However, before agents can use Copilot to answer questions and draft emails, you need to ensure Copilot is using accurate knowledge content. 

Good knowledge hygiene is key to bringing Copilot capabilities to life. For Copilot to successfully ingest, index, and surface the right knowledge asset, it’s important to ensure each asset meets defined ingestion criteria. Also, preparing knowledge assets for Copilot ingestion is not a finite process. It is essential to keep ingested knowledge assets in sync with upstream sources, and use proper curation and governance practices. 

While every organization has its own unique systems, we aim to provide a general set of best practices for creating and maintaining your Copilot corpus. We’ll cover four main topics here: 

• Defining the business case 
• Establishing data quality and compliance standards 
• Understanding the content lifecycle and integrating feedback 
• Measuring success

Defining the business case

It is imperative that you look at your organization’s goals holistically to ensure they align with the content you intend to surface. Consult with different roles in each line of business to capture the different types of content they already use or will need. Determine the purpose of each content element to ensure its function and audience are clear. Look at your organization’s common case management workflows that require knowledge to see the greatest impact on productivity. 

You may want to take a phased approach to roll out Copilot capabilities to different parts of your organization. The use case for each line of business will enable you to create a comprehensive plan that will be easier to execute as you include more agents. Administrators can create agent experience profiles to determine which groups of agents can begin using Copilot and when. 

For example, there may be some lines of business that are more adherent to your established content strategy. Consider deploying to these businesses first. This will create an opportunity to observe and account for variables within your businesses which today are under the surface. 

Establishing data quality and compliance standards 

Identify the correct combination of content measures and values before bringing content into your Copilot corpus. Careful preparation at this stage will ensure Copilot surfaces the right content to your agents.  

The following is a general list of must-haves for high-performing knowledge content: 

• Intuitive title and description 
• Separate sections with descriptive subheadings  
• Use plain language and avoid technical jargon 
• No knowledge asset attachments; convert them into individual knowledge assets 
• No excessively long knowledge assets; break them into individual knowledge assets 
• No broken or missing hyperlinks in the content body 
• Descriptions for any images that appear in knowledge assets; Copilot cannot read text on images 
• No customer or personal information about employees, vendors, etc. 
• A review process for authoring, reviewing, and publishing articles 
• A log of all actions related to ingesting, checking, and removing knowledge assets 

If you’re storing knowledge assets in Dataverse, they should always be the latest version and in Published status.  

Understanding the content lifecycle and integrating feedback

As mentioned above, clearly defined processes for authoring, reviewing, publishing, synchronizing, curating, and governing knowledge assets will help ensure Copilot surfaces responses based on the most recent knowledge assets. Determine which roles in your organization will author knowledge assets and the review process they will use to ensure accuracy.  

After publishing a knowledge asset, determine how your organization will gather feedback to signal when to update or deprecate the asset. Set an expiration date for each asset so you have a checkpoint at which you can determine whether to update or remove it. 

You can use the helpful response rate (HRR) to gather initial agent feedback. HRR is the number of positive (thumbs-up) ratings for each interaction divided by the total ratings (thumbs up + thumbs down). You can correlate this feedback with the knowledge assets Copilot cites in its responses. Gather more detailed feedback by creating a system that enables users to request reviews, report issues, or suggest improvements.

Measuring success 

While knowledge management is an ongoing process, so is its measurement. You’ll want to periodically track usage and performance to ensure Copilot is useful to agents and identify areas for improvement.  

Tracking analytics

First, you can measure the performance of your knowledge content based on the purpose you outlined at the beginning. You can view some metrics directly within your Customer Service environment. To view Copilot analytics, go to Customer Service historical analytics and select the Copilot tab. Here, comprehensive metrics and insights provide a holistic perspective on the value that Copilot adds to your customer service operations. 

You can also build your own Copilot interaction reports to see measurements such as number of page views for each knowledge asset, the age of the asset, and whether the agent used the cited asset. The asset age is based on the date it was ingested by Copilot, so it’s important to ensure publication and ingestion cycles align.

Serving business processes

Some other key metrics that you’ll want to consider will be more closely tied to your organization’s business processes. Some examples include:

• Number of cases related to a knowledge article 
• Number of escalations prevented 
• Time saved when agents access these articles 
• Costs saved from reduced escalations and troubleshooting time 

Overall, introducing and expanding Copilot capabilities in your CRM is an iterative and ongoing process. Include stakeholders from every role to ensure your organization is using Copilot to help solve the right problems and enhance the agent experience.  

AI solutions built responsibly

Enterprise grade data privacy at its core. Azure OpenAI offers a range of privacy features, including data encryption and secure storage. It allows users to control access to their data and provides detailed auditing and monitoring capabilities. Copilot is built on Azure OpenAI, so enterprises can rest assured that it offers the same level of data privacy and protection.  

Responsible AI by design. We are committed to creating responsible AI by design. Our work is guided by a core set of principles: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability. We are putting those principles into practice across the company to develop and deploy AI that will have a positive impact on society.

Learn more

For more information, read the documentation: Use Copilot to solve customer issues | Microsoft Learn 

The post Knowledge management best practices for Copilot ingestion appeared first on Microsoft Dynamics 365 Blog.

Earlier this year, we’ve introduced the public preview of Field Service Mobile’s refreshed user experience. As this year comes to a close, we are excited to announce a new set of updates to further enhance this new user experience. 

Agenda View Update 

The Agenda View is the main landing experience for frontline workers using Field Service Mobile. In this wave, we are continuing to add to this experience to make it easier for your technicians to see and manage their bookings. In this wave, enhancements to the Agenda view include: 

• Bi-directional scroll of up to 90 days of bookings in the past or future. 
• Date separators that help your technicians better see the bookings of each day. 
• Makers can configure the data that gets shown in each row through existing view configuration experience. 

These improvements will give your technicians more visibility and control over their schedule, and help them plan their work more effectively. To learn more about this feature, go here.  

Configurable List View 

Another heavily used part of Field Service Mobile is the list view. To improve the item browsing experience for your technicians, the team has built from the ground up a new mobile-first list view for the new Field Service Mobile experience: 

• Makers can choose up to five columns per table to display in the mobile list view. 
• The icon in the list view is removed, saving limited mobile screen real estate. 
• List view has smoother scrolling and is more performant with in-built lazy load. 

These new capabilities will improve the productivity of your technicians by enabling them to see more data and at higher density on their mobile devices. To learn more about this feature, go here. 

Copilot Work Order Summary and Update 

To empower frontline workers with the latest AI advances, we’ve brought the power of Copilot to Field Service Mobile! With these new features, your technicians can both quickly get up to speed on a Work Order or update it using a speech-first Copilot experience.  

To learn more about this groundbreaking experience, see Experience the power of Copilot in Dynamics 365 Field Service in the mobile application – Microsoft Dynamics 365 Blog. 

How to try this? 

These are some of the features that we have delivered in the latest wave of the Field Service Mobile app. We hope that you will try them out and share your feedback with us. To enable these features, log in with an admin account and turn them on in the settings section in Field Service Mobile. Enable the “New Mobile Experience” and “Copilot for New Mobile Experience” options. For more information, please visit our documentation page here.   

Thank you for choosing Dynamics 365 Field Service Mobile app. We are committed to delivering the best mobile service experience for you and your customers. Stay tuned for more updates and enhancements in the future. 

We hope that these new enhancements in Field Service mobile will make your work even more productive. We would love to hear your feedback and suggestions on how to improve the product. Please feel free to leave comments in the Dynamics 365 Community Forum or Ideas portal. Thank you for using Field Service Mobile! 

The post What’s new in Dynamics 365 Field Service Mobile app in 2023 Wave 2  appeared first on Microsoft Dynamics 365 Blog.

Introducing Copilot for the new Field Service mobile user experience 

Field Service mobile is a powerful application that helps frontline workers manage their tasks, access information, and communicate updates with the back office. But we know that sometimes, using an app can be cumbersome or distracting, especially when you are busy with your hands-on work. That’s why we are excited to announce Copilot for the Field Service mobile app, a new feature that makes Field Service mobile even more user-friendly and efficient. 

The new Field Service mobile (Preview) user interface has two Copilot skills that help to summarize and update work orders. Copilot update uses natural language processing and artificial intelligence to understand your input via text or voice command, then suggests form updates based on that input. While the Copilot summary provides the Frontline Worker a concise summary of their booking with the click of a button.  

Let’s learn more about these features and how they work. 

How Copilot Summarizes You Work 

Copilot Summarize provides a quick overview of the scheduled booking for the frontline worker. This gives frontline workers a better understanding of the job to be done without needing to click through multiple forms to find the information. Copilot will summarize a booking based on the following fields related to that booking:  

• Booking information 
• Activity details 
• Notes from the work order and bookings 
• Work order product details 
• Work order service details 
• Work order service tasks 
• Asset information and work order History 

Copilot work order summary is also available for the back office or from the web-based Field Service application. For more information please see Work order recap with Copilot in Field Service (preview) – Dynamics 365 Field Service | Microsoft Learn

How Copilot updates data on forms 

Another benefit of Copilot is that it can help you easily fill out forms. Instead of hunting for fields within the mobile app, you can simply tell Copilot what you want to update.  Tell Copilot to update data with phrases such as: 

• I’ve completed all tasks and finished this booking at 10:00AM 
• I’ve used {product name} as part of my work to complete this booking. 
• I’ve completed {service task name}.  

Copilot will understand your natural language input and propose updates to data on the form accordingly. All changes proposed by Copilot will be presented to the frontline worker where they can exclude or accept recommended updates.  

Today the Copilot update is limited to updates of the forms within the new mobile UX only. Scope of these updates are: 

• Update your booking status and times 
• Change the state of at task to completed 
• Consume estimated products 
• Complete work order services 
• Complete service tasks assigned to the work order 

Keep an eye out for additional enhancements and capabilities of this feature! 

How to Get Started with Copilot for Field Service Mobile 

Copilot Summary and Update are available for the new Field Service mobile (Preview) experience today. To enable Copilot, the org admin will need to enable the features within Field Service Settings. Once enabled, app users will find the copilot entry point in their application under the Copilot logo located in the header of the booking form.  

We hope that Field Service mobile with Copilot will make your work even more productive. We would love to hear your feedback and suggestions on how to improve Copilot. Please feel free to leave comments in the Dynamics 365 Community Forum or Ideas portal. Thank you for using Field Service Mobile! 

The post Experience the power of Copilot in Dynamics 365 Field Service in the mobile application appeared first on Microsoft Dynamics 365 Blog.

How often do you find yourself spending too much time reading through long and complex customer cases, trying to figure out the main problem and the best solution? What amount of cases do you handle per day, and how do you ensure quality and consistency in your responses? How do you keep track of the most relevant and updated information from multiple sources and channels?

These are some of the challenges that support agents face every day, and they can affect their productivity, performance, and satisfaction. Customers expect fast and accurate answers to their questions and issues, and they don’t want to repeat themselves or wait for long periods of time. Support agents need to be able to quickly understand the context and history of each case, identify the root cause and the best action, and communicate effectively with customers and colleagues.

This is where summarization comes in. Summarization is an AI-powered feature that provides support agents case summaries to help them quickly understand the context of a case and resolve customer issues more efficiently. It uses large language models and natural language processing to analyze and condense information from various sources and formats, such as emails, chat messages, phone calls, documents, and web pages, into concise and relevant summaries. Summarization can save you time, improve your accuracy, and enhance the customer experience.

This blog post explains how summarization works, what benefits it can bring to your support team and your organization, and how you can turn it on and use it with Dynamic 365 Customer Service Copilot, the leading AI platform for customer service.

Summarization: The gateway to generative AI Innovation

Summarization stands out as an ideal first use case, primarily due to its immediate, measurable impact on efficiency and productivity. It automates the extraction of crucial details such as the case title, customer, subject, product, priority, case type, and description. The AI-generated summaries offer context and communicate the actions already undertaken to address the issue. Summarization delivers tangible benefits, showcasing the power of generative AI in a clear and demonstrable manner.

Compared to other AI use cases, the implementation of summarization is less complex. It is a straightforward starting point for organizations new to generative AI, reducing barriers to entry and integration time. The success of summarization in enhancing productivity and achieving measurable outcomes serves as a confidence-building milestone for organizations. Experiencing the transformative power of generative AI fosters trust in the technology. Additionally, it lays a robust foundation for delving into more advanced use cases.

Starting with summarization brings immediate operational improvements. It also helps organizations to embrace the broader potential of generative AI, setting the stage for future business process innovation.

By selecting the Make case summaries available to agents checkbox, administrators can bring their organization a quick win that adds immediate business value. We have invested in summarization features to allow more customization options. Admins now can customize the format of how agents view conversation summaries. They can also customize the entities and fields that are used for case summary.

Learn more

To learn more about summarization, read the documentation: Enable summarization of cases and conversations | Microsoft Learn

The post Begin your copilot journey with summarization appeared first on Microsoft Dynamics 365 Blog.

Microsoft has separated all Czech-specific functionalities into distinct applications as part of the delocalization process of the Czech version of Dynamics 365 Business Central. The process intended to pave the way for the seamless integration of Czech local functionalities on top of the Worldwide (W1) version of the Business Central. 

Technical Overview

Business Central has been undergoing major changes over the past few years and one of the strategy areas is application modularization, that includes localization layers. This led to critical changes in the Czech localization layer, which has now been converted into a suite of distinct localization apps. The suite contains the following apps: Core Pack, Advance Pack, Banking documents, Cash Desk, Compensation, Advance Payments, and Fixed Assets.

To ensure that both old and new Czech functionalities work in parallel in that transition period. Microsoft made sure that the old code integrated into the Base Application was gradually cleaned up. The last step is to remove Czech specific fields from the Czech Base Application.

In the next major release of Business Central 2023 wave 2 (version 23), the following Czech-specific fields will be removed from the tables, while primary keys will be updated:

• Table 1251 “Text-to-Account Mapping”, field 11700 Text-to-Account Mapping Code: Code[10]
• Table 1252 “Bank Pmt. Appl. Rule”, field “Bank Pmt. Appl. Rule Code” Code: Code[10]

The removal of Czech-specific tables and fields from the Czech Base Application, has also been announced in the list of deprecated features, see https://learn.microsoft.com/en-us/dynamics365/business-central/dev-itpro/upgrade/deprecated-features-platform#changes-in-2024-release-wave-2-version-250.

Action Required: Upgrade to Business Central 2023 Release Wave 2

To ensure a successful upgrade to Business Central 2023 release wave 2 (version 23) Czech, perform a forced synchronization of the database schema. Microsoft will ensure a seamless upgrade process for users of the online version of Business Central. However, for those upgrading to this version using Business Central on-premises, it is necessary to set the “schemaUpdateMode” parameter in CZ Base Application to “ForceSync” to synchronize the data model.

Users who are upgrading to the on-premises version of Business Central 2023 release wave 2 (version 23) Czech and higher must verify that there are no duplicate records in both tables 1251 “Text to Account Mapping” and 1252 “Bank Payment Application Rule” after the Czech fields have been removed from the primary key. This can be accomplished either by manually deleting the data or by upgrading to any version of BC 22.x where data modifications will be included as part of the upgrade procedures. It is highly recommended to back up the data in these tables before proceeding.

Summary

Czech-specific fields that were previously part of the primary key in Table 1251 “Text to Account Mapping,” specifically Field 11700 “Text-to-Account Mapping Code,” and in Table 1252 “Bank Payment Application Rule,” “Bank Payment Application Rule Code,” will be removed in this new version.

The post Impact of Delocalization Process in the Czech Version of Business Central 2023 Wave 2 Release appeared first on Microsoft Dynamics 365 Blog.