This article is contributed. See the original author and article here.
As AI transforms customer service, sales, and operational workflows, organizations are eager to harness its potential. However, questions about control, security, compliance, and performance linger. That’s why we built Agent hub in Dynamics 365. It’s a one-stop hub that empowers customer service and contact center admins and supervisors to safely adopt AI, monitor its impact, and make informed, responsible decisions.
In this blog post, we’ll walk you through why it matters, what it offers, and how it works — featuring our key pillars: Learn, Rollout, and Measure.
Why do we need Agent hub?
Adopting AI in the enterprise isn’t as simple as flipping a switch. Business leaders and IT teams often ask:
Which AI agents are running in our environment?
Are they compliant and secure?
What business value are they driving?
How can we safely test and roll out AI capabilities without disrupting operations?
Agent hub answers those questions by providing transparency, governance, ROI and actionable insights — all in one place.
With Agent hub in Dynamics 365, customers gain:
Transparency — Gain clear visibility into AI agent behavior, security, and compliance posture through the Learn pillar.
Control — Safely adopt AI workflows incrementally by intents and workloads using the Rollout manager.
Performance monitoring — Measure AI agent performance and key KPIs via the performance dashboards in the Measure pillar.
Governance and trust — Drive responsible AI adoption aligned with business priorities and regulatory requirements.
Pillar 1: Learn
Before enabling AI capabilities, admins can access plain-language, guided overviews of AI agents, security protocols, compliance impacts, and adoption workflows. This helps demystify AI and empowers decision-makers with the knowledge to act confidently.
Key highlights:
Insights into AI agents, Copilot features, and Fully Autonomous Contact Center (FACC) flows
Security, privacy and compliance insights
FAQs on AI in Dynamics 365
Pillar 2: Rollout
Adopting AI can be safe and controlled. With Rollout manager, you can selectively activate AI agents and autonomous workflows based on specific intents and business rules, giving you full control over which workloads are handled by AI.
Key highlights:
Define rollout plans
Track adoption status and control exposure incrementally
Pillar 3: Measure
Once an AI agent is live, you need to measure what matters. Performance dashboards for AI agents highlight KPIs like:
Autonomous rate
Resolution rate
Average handle time
Abandon rate
With seamless drill-down to L2 dashboards and actionable insights for AI agents like Knowledge Management Agent, supervisors can continuously measure and optimize AI impact.
The Agent hub in Dynamics 365 isn’t just a tool, it’s a framework for safe, transparent, and value-driven AI adoption. Whether you’re starting your AI journey or scaling enterprise-wide automation, it equips you with the insights and controls you need to move forward with confidence.
Learn more about Agent hub
Ensure your organization stays ahead of customer expectations. Preview Agent hub in Dynamics 365 and share your feedback.
This article is contributed. See the original author and article here.
In today’s connected world, voice communication remains a cornerstone of customer engagement. Whether it’s a support call for customer service or a telehealth session with a doctor, call quality and reliability are critical. That’s where our enriched telemetry and insights come in. Equipped with comprehensive telemetry data, developers and IT teams can monitor, detect, diagnose, and resolve issues with voice call performance, regardless of the calling service provider.
This blog post will guide you through the powerful diagnostics and telemetry tools available in Dynamics 365. You’ll see how they can enhance your contact center’s efficiency and customer satisfaction. By leveraging these tools, you can ensure seamless voice communication, proactively address potential issues, and deliver an exceptional experience to your customers!
For either an inbound call where callers are calling into the contact center, or outbound calls where agents are contacting customers, there is a lifecycle to every conversation. This lifecycle is typically as below.
We have a wide range of Azure monitoring tools, including Application Insights and Azure Communication Service (ACS) Call Diagnostics in Call Diagnostics Center (CDC). These tools, integrated through Azure Monitor and AppInsights, serve different layers of the communication stack and can be complementary when used together. The telemetry in these tools is usually available within 15 minutes, making them apt for monitoring.
The conversation lifecycle in Application Insights
The conversation lifecycle paints a full picture of the call and does the following:
Captures operationalconversation events: initiation, voice agent handoff, routing to queues, and agent assignment until resolution.
Enables monitoring workflow health, agent performance, and customer service representatives’ performance, as well as customer experience.
Integrates directly with Application Insights to track conversation telemetry and build custom dashboards.
Enables telemetry analysis using our pre-built Azure Data Explorer dashboards. Or, you can simply use these queries to create your own custom queries suited to your business needs. See the sample query here: Configure conversation diagnostics (preview) | Microsoft Learn
You can now enable out-of-the-box workbooks for viewing all this telemetry in one place. These are in preview right now to try out. Reach out to D365CS_Diagnostics@microsoft.com to enable the reports.
You can also build and edit your own queries in the editor to answer your business questions.
ACS call diagnostics
Azure Communication Service (ACS) call diagnostics in Call Diagnostics Center (CDC) help you analyze call telemetry and does the following:
Focuses on media telemetry: audio/video quality, jitter, packet loss, latency, device issues.
Enables technical troubleshooting of call quality and client-side performance.
Can be used for calls from any PSTN operator.
Enables data to be routed to Log Analytics via Azure Monitor for querying and alerting.
ACS recently rolled out additional telemetry on performance that is handy for identifying and debugging scenarios that have higher than normal latency. You can:
Identify calling SDK APIs that are high latency, for P95 or even P99.
Drill down into individual API scenarios to show detailed performance trend.
You can also see the P95 latency thresholds on this page to use as guidance.
Use cases
Let’s understand how you can use these tools through a couple of common use cases.
Case 1: Optimizing for assignments
As a supervisor, you are tasked with keeping customer service representative assignment time around 3 minutes on average. If assignment time begins to rise, maintaining the same service level requires proactive measures. With assistance from an IT admin, you configure a monitor in Application Insights using conversation lifecycle telemetry. You set the average assignment time to 2 minutes and receive email alerts if the number rises, enabling adjustments.
traces
| extend customDim = parse_json(customDimensions)
| extend
conversationId =tostring(customDim["powerplatform.analytics.resource.id"]),
subscenario = tostring(customDim["powerplatform.analytics.subscenario"])
| where subscenario in ("RTQ", "AgentAccept")
| project timestamp, conversationId, subscenario;
let latestRTQsBeforeAgentAccept = subscenarios
| where subscenario == "RTQ"
| join kind=inner (subscenarios
| where subscenario == "AgentAccept"
| project agentAcceptTime = timestamp, conversationId) on conversationId
| where timestamp 2min
| project conversationId, assignmentTime
With this query, the alert has a severity of 2, indicating Warning. Additionally, you can select how and when to summarize results, and how frequently to evaluate the calls, and where to send the alerts to. For a critical metric such as assignment time, selecting your evaluation to run every 15 minutes will cost $0.50 a month.
In the midst of a typical day, an alert notifies you that assignment time has exceeded 150 seconds for more than 10 calls in the past 15 minutes. You reach out to the IT admin, who swiftly jumps into action.
Leveraging the tools at their disposal, they begin diagnosing. They first look at the conversations exceeding 150s in the dashboard they set up using Azure Data Explorer Dashboards. There are more than 30 conversations by now where assignment time has exceeded 150 seconds. They choose a few and view their conversation state flow within the built-in views. The IT admin observes an unusually high queue volume. To manage the surge, an overflow rule is triggered, initiating callbacks. The callback duration is then factored into the assignment time, resulting in a higher-than-normal average assignment times.
The IT admin quickly runs a query in AppInsights and identifies a queue with lower call volume. By routing calls to this queue as an overflow action, they can alleviate the strain on the queue experiencing higher assignment times. What once required extensive troubleshooting with Microsoft Support is now effortlessly resolved, with the answers at your fingertips.
Case 2: Optimizing for network issues
As a supervisor, a few of your Customer Service Representatives (CSRs) report dropped calls and network error messages during calls. To investigate, you gather the conversation IDs from your team and reach out to your IT admin for support. The IT admin retrieves the call ID for these conversations by using a query in Application Insights.
The IT Admin then filters for these call IDs in ACS Call Diagnostics and uncovers a recurring no network error confirming a contact center-wide outage rather than isolated network failures.
To prevent future disruptions, the supervisor ensures calls automatically switch to a backup connection when the primary network goes down, maintaining stability and avoiding dropped calls.
Case 3: Optimizing for call connectivity with SBC
As an IT admin, you are responsible for diagnosing calling issues that may involve a non-Microsoft telephony system connected to Azure Communication Services (ACS) via Direct Routing. These complex calling issues will span both Direct Routing SBCs and ACS. When you see a support ticket about a specific incoming call that traversed your Direct Routing SBC, you start with the call ID generated by the SBC. Your goal is to map this trunk call ID to its corresponding ACS correlation ID and uncover the root cause using end-to-end telemetry.
Inside your ACS resource, you navigate to Azure Monitor, then to Monitoring > Logs. There, you run a targeted query on the ACSCallSummary table. Replace trunkCallId with the specific call ID from the Direct Routing SBC for the call you want to troubleshoot.
ACSCallSummary
| where ParticipantType == "PSTN"
| project
| CorrelationId, PstnParticipantCallType, ParticipantEndReason, ParticipantEndSubCode,
| trunkCallId = parse_json (CallDebuggingInfo).trunkCallId, CallDuration
| where trunkCallId has ""
This query returns the ACS correlation ID linked to your SBC-generated call ID. With this correlation ID in hand, you proceed to ACS Call Diagnostics. Running the correlation ID through the diagnostic tools, you discover a recurring pattern: “No Network” errors appear consistently for calls routed through this path, confirming that the problem is not isolated to a single user or device.
Instead, your investigation reveals a contact center-wide network outage impacting all calls passing through the affected Direct Routing SBC. With actionable evidence, you escalate the incident for resolution, ensuring future calls are routed via healthy trunks, and document your findings for compliance and proactive monitoring.
By leveraging intuitive dashboards, real-time alerts, and deep integration with Azure services, organizations can quickly identify bottlenecks, optimize performance, and deliver consistently exceptional customer experiences. Embrace these powerful tools to transform your operations, delight your customers, and stay ahead of the competition.
This article is contributed. See the original author and article here.
For decades, growing revenue in business-to-business (B2B) sales meant expanding the sales team. More sellers, more deals. But AI is providing a once-in-a-generation opportunity to reimagine customer relationship management (CRM), and business leaders are keen to use its potential to boost sales outcomes and do more with less. Organizations are building the sales teams of the future by investing in generative AI and autonomous AI agents that can empower sales teams to deliver faster, hyper-personalized buying experiences—deeply understanding customer intent and proactively guiding decisions to influence pipeline.
Autonomous agents can handle the manually intensive parts of a typical sales workflow; for example, researching sales leads while allowing reps to spend more time in front of the customers selling and closing revenue. This is what we call agentic sales—where humans guide agents through fully autonomous workflows, transforming the sales journey and delivering meaningful customer engagements. Becoming an agentic sales organization is top mind for leaders, but many don’t know where to start.
Microsoft Dynamics 365 Sales
Close more deals and increase seller efficiency with an AI-powered CRM solution.
The pressure to deliver on customer expectations is higher than ever. Buyers want faster responses and better customer experience and are willing to walk away if those needs are not met. But with data barriers and organizational silos teams globally are struggling to meet these demands. In the face of these challenges, yesterday’s CRM systems are taking time away from what matters—building relationships and delivering personalized interactions across the sales journey. Sales leaders now rely on AI to provide sales insights and recommend next best actions from their customer data; and they are increasingly looking to agents to automate and augment work like researching, qualifying, and drafting outreach. Gartner predicts that by 2028, at least 15% of day-to-day work decisions will be autonomously through agentic AI, up from 0% in 2024.1
Fig. 1: 2025 Gartner Magic Quadrant for Sales Force Automation Platforms**2
How Microsoft is making selling easier
Reimagine resource-intensive workflows across the sales pipeline
Microsoft Dynamics 365 Sales enables sellers to boost sales outcomes and improve customer experience powered by a CRM system that embeds AI and agents throughout the key stages of the deal cycle. Sellers can develop, prioritize, and close pipeline faster by adopting a consistent cadence across teams with autonomous AI agents and Copilot. Dynamics 365 helps sellers stay on top of their deals and deliver high-quality customer engagements across touchpoints with AI-powered engagement guidance and real-time action recommendations. With conversational intelligence built-in, sellers get real-time call transcriptions, sentiment analysis, and actionable insights that help them stay focused and responsive. Sales managers are able to use these insights to scale winning teams and grow their business with intelligent forecasting. Sales operations leads are able to tailor the agentic sales solution to meet the needs of the business and deliver sales efficiency with trust and accountability.
Integration with an expanded ecosystem
Organizations can harness the breadth of the Microsoft Cloud to empower their sales teams with intelligent, connected experiences—easily integrating data, collaboration, and AI-powered insights. Integrated collaboration tools that streamline communication and drive accountability across marketing, sales, and service departments. Embedded Microsoft Teams chat within Dynamics 365 enables real-time discussions through dedicated teams and channels, fostering cross-functional alignment. With Microsoft 365 Copilot for Sales sellers can easily share opportunities, leads, and account information plus set up deal rooms directly in Teams with automatic sharing of data and files from Dynamics 365 Sales. Copilot in Power Apps makes it easier than ever to tailor the sales experience. Whether it’s customizing dashboards, building forms, or automating workflows, sellers can use natural language to optimize the user interface around how you work. It’s a smarter, faster way to extend Dynamics 365 Sales—without needing to write a single line of code.
Our customer’s success
Ricoh Japan drives digital transformation with Dynamics 365 Sales incorporating generative AI for enhanced sales capabilities and seamless integration with Microsoft 365.
Among the most significant benefits of implementing Dynamics 365 Sales for Ricoh was their new access to generative AI technology. As an example of how Ricoh Japan is using generative AI, product recommendations from four sources appear when users access the new system: from daily reports entered in Dynamics 365 Sales, from industry information on the web, from purchase history, and top-selling products by customer segment. “These all appear automatically,” says Kazunari Sakai, CRM Promotion Group Leader in the CRM Planning Office, Marketing Center, Digital Service Sales Division at Ricoh Japan. “Microsoft 365 Copilot is used to summarize Outlook emails as well as chats and meetings conducted using Teams.”
There are many strengths in our sales process that we have honed over a 20-year period and hope to carry forward. Dynamics 365 Sales integrates with Power Platform, a line of products facilitating low-code/no-code development and able to meet our Fit to Standard framework.”
—Makoto Nagai, General Manager of the CRM Promotion Office, DX Promotion Center, Corporate Planning Division, Ricoh Japan
As organizations continue to begin adopting AI agents, Microsoft is here guiding each team as they become an agentic sales organization built on trust and security in leading products like Dynamics 365 Sales.
2Gartner, Magic Quadrant for Sales Force Automation Platforms, Adnan Zijadic, Guy Wood, Steve Rietberg, Wendy Butler-Mafuz, 21 July 2025.
*The report was titled Magic Quadrant for Sales Force Automation from 2007-2008. Microsoft was recognized as Microsoft Dynamics CRM from 2011-2014 and as Microsoft (Dynamics CRM Online) in 2015-2016. GARTNER is a registered trademark and service mark of Gartner and Magic Quadrant is a registered trademark of Gartner, Inc. and/or its affiliates in the U.S. and internationally and are used herein with permission. All rights reserved. Gartner does not endorse any vendor, product or service depicted in its research publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner research publications consist of the opinions of Gartner’s research organization and should not be construed as statements of fact. Gartner disclaims all warranties, expressed or implied, with respect to this research, including any warranties of merchantability or fitness for a particular purpose.
**This graphic was published by Gartner, Inc. as part of a larger research document and should be evaluated in the context of the entire document. The Gartner document is available upon request from Microsoft.
This article is contributed. See the original author and article here.
We’re excited to announce a major upgrade to how sellers interact with Copilot summaries in Dynamics 365 Sales. Beginning with the 2025 Release Wave 2, Copilot summaries for Opportunities, Leads, and Accounts will appear directly at the top of the record in a sleek insights bar. This update brings AI-powered insights directly into the seller’s workflow, thereby reducing clicks, improving focus, and enabling faster decisions.
Why This Matters
The sidecar experience has been useful, but many sellers find it disconnected from the main form and difficult to use due to limited space. Scrolling through long summaries in a narrow pane often slows down productivity and disrupts focus.
The new insights bar presents key insights directly on the form, at the top of each record. This eliminates the need to open a separate pane. With this streamlined experience, sellers can ramp up faster, stay in context, and respond more effectively to customer needs.
This change is not just a visual update. It is a step toward making selling more intelligent and contextual. Whether you’re new to the sales team or an experienced seller, this improvement ensures that essential insights are always visible when you need them.
What’s Changing
Summary displayed at the top of the record form
The new insights bar provides a one-line synopsis for quick scanning. It remains visible in a collapsed state and can be expanded to view more details. An example synopsis for a lead is:
“Acme is exploring Airpot coffee machines for their new manufacturing site with a $24.9K budget expected to close by May 25th, 2025”
You can expand the insights bar to read more details:
You can click on options like “See full summary“ to open the lead’s research page:
For organizations using the Sales Qualification Agent, the insights bar displays agent-generated summary. Sellers can navigate to the agent’s research page to access deeper insights about the lead’s company, view tailored recommendations, and identify clear next steps.
What’s coming next
We are working to bring the same agent-powered experience to Opportunity and Account records. Until then, these records will continue to display summaries in a popup.
Once the agentic experience is available, sellers will get access to a full research page for these records as well.
General availability starts in September 2025, with that, the new experience will be default enabled for users.
We recommend enabling early access in your environments and preparing your sellers for the new summary experience. Share any feedback or challenges with us so we can continue to make selling easier and more effective.
Recent Comments