Microsoft Dynamics 365 Sales - version 9.0.25111.10001

Update package

• Version number
• Service Update 211 for Microsoft Dynamics 365 Sales version 9.0.25111.10001 (or higher) 9.0.25111.10001

To determine whether your organization had this update applied, check your Microsoft Dynamics 365 version number. Click the gear icon in the upper-right corner, and then click About.

An (*) at the end of a fix statement denotes that this repair item was incorporated into multiple service update releases.

Please click here to view the list of features and functionalities included in this year's release wave.

Service Update 211 resolves the following issues:

New/Enhanced Functionality

• Adaptive card handling in the Chat Experience enhances security and reliability of CRM solutions.
• Sales agents RTB improvements in the Configuration Agent enhance security, functionality, and user experience.
• Inclusion of email field filter in selection criteria ensures accurate data retrieval and prevents missed records.
• New solution for Configuration Agent improves security and efficiency in customer interactions.
• APAC exclusion added to allow Sales Copilot features without cross-geo consent, improving security and functionality.
• Hierarchy viewer tab added to simplify entity navigation and boost productivity.
• Updates to strings, redlines, and accessibility fixes improve Sales Close Agent usability and compliance.
• Embed chat fixes enhance chat reliability and communication within OneCRM.
• ProcessEngageResult API updated for better test simulation and smoother deal closures (customer impact: more stable deal‑closing experience).
• Step‑by‑step setup topics created for Sales Close Agent to improve user guidance.
• Security fixes applied to Sales.Copilot and CRM.Solutions.AcceleratedSales for safer operations.
• Localized files correctly integrated for better regional user experience.
• Activation handling improvements allow direct record access from Dynamics 365 Sales Hub grids.
• Transition handling between Settings and Chat experience enhanced for reliability.
• Preview tags removed for finalized features, increasing trust and stability.
• Default enablement of CustomResearchInsight ECS flags provides enhanced research insights.
• AI‑driven insights integrated into Sales Close Collaboration Panel for better collaboration.
• Automated notification visibility improved for timely and relevant updates.
• 'Total Number of Risks' column added to risk indicator table for a complete risk overview.
• Microsoft 365 consent descriptions clarified for better user understanding.
• Empty Product and Quote Insights sections hidden in Opportunity Research to reduce UI clutter.
• Sales Insights package versions updated for improved reliability and performance.
• Email prompt upgraded and product recommendation fixed in Sales Close Agent for better guidance and accuracy.
• Rubrics updated for enhanced competitor insights.
• Product configuration improved with AI prompt and list rows connector, enhancing setup experience.
• Out‑of‑segment opportunities excluded from Opportunity Research refresh for more relevant insights.
• Deal Close Agent renamed to Sales Close Agent for consistency and clarity.
• AI prompt improvements enhance decision‑making in sales processes.

Please click here to get the list of new/enhanced functionalities details.

Repaired Functionality

• Account news content filtering improved for more accurate and reliable information.
• "Reset to default" button alignment fixed on the Admin Settings page for a cleaner UI.
  • Text area resizing fixed in MCAPS RO‑mode product section for better usability.
• Engage readiness grid loading issue fixed in UCI for smoother navigation.
• Sales.Copilot input payload reliability improved, enhancing stability.
• Link to Copilot Studio corrected for adding Knowledge Sources, improving workflow continuity.
• Agent emails Knowledge Source tab description updated for clarity.
• Records now open correctly from grids in Dynamics 365 Sales Hub for consistent behavior.
• Playbook path conversion fixed to prevent timeout issues during execution.
• Whitespace added in custom insight citations for better readability.
• Casing corrected in Key Deal Insights citations for consistency.
• Error message padding fixed in Sales Close Agent for improved readability.
• SharePoint URL editing enabled in DCA Admin UI for smoother configuration.
• Dropdown icon truncation removed for better accessibility.
• Privilege errors for salesperson users fixed, reducing access issues.
• Product creation limited to improve interface performance and reduce UI slowdowns.
• Notification added when no matching records are found in SQA RE testing—improves transparency.
• Default 'Name' field removed in product knowledge fields to reduce confusion.
• SharePoint URL editable when empty, improving admin flexibility.
• Product lookup search now queries CRM database, increasing accuracy.
• False unsaved‑changes alerts removed on product pages for smoother editing.
• Action buttons now visible in new notifications, ensuring options aren't missed.
• Customer‑facing error message added for "no record found" in LinkedInExtensions.
• Revenue display accuracy fixed in Opportunity Summary.
• Summary queries correctly directed to DVQnA, improving insight quality.
• Email filter issue fixed in D365 Sales App Copilot for more accurate filtering.
• LogicalName null issue fixed in MeetingPrep query expression.
• Banner summary cached when agent disabled, preventing misleading UI messages.
• Duplicate outreach emails prevented to avoid customer confusion.
• Auto‑reply email processing improved for reduced redundancy.
• Hotfix improves reliability of online evaluations.
• Query check for account research results relaxed for more accurate insight retrieval.

Accessibility Repaired Functionality

• Dropdown icon truncation issue fixed to improve accessibility in Deal Closing Agent.
• Screen reader tooltip announcements improved for Sales Qualification Agent Research Insights.
• Keyboard accessibility enhanced for Bing Search Tooltip.

Return to the all version availability page.

If you have any feedback on the release notes, please provide your thoughts here.

Original source Report a problem

Microsoft Dynamics 365 Sales - version 9.0.25112.10001

Service Update 212 for Microsoft Dynamics 365 Sales version 9.0.25112.10001 (or higher) - Version number 9.0.25112.10001

To determine whether your organization had this update applied, check your Microsoft Dynamics 365 version number. Click the gear icon in the upper-right corner, and then click About.

An (*) at the end of a fix statement denotes that this repair item was incorporated into multiple service update releases.

Please click here to view the list of features and functionalities included in this year's release wave.

New/Enhanced Functionality

• Added SMS providers to enhance communication capabilities in the Sales Accelerator Workspace.
• Enabled creating sequences with SMS steps, improving communication flexibility and data reliability.
• Enabled sending SMS from Sales Accelerator Workspace for reliable, multi‑channel outreach.
• Improved CRM functionality by removing owner ID in research result entity and introducing parent‑child relationships (clearer data modeling, fewer access issues).
• Saved custom research insight configuration in agent config to support enhanced localization.
• Added API to verify prerequisite status for features in Sales Generative AI Deal Close Agent (smoother feature activation).
• Improved AI prompt for generating value propositions and outreach email templates (higher‑quality suggestions).
• Improved AI prompt alignment for generating clear, guided messages.
• Added AI‑generated disclaimers and feedback controls for transparency in AI usage.
• Extended SQA handover to support attribute matching in Assignment Engine V2 for more accurate lead/record routing.
• Fixed security issues in CRM.Client.LeadResearch to enhance system safety for end users.
• Removed outdated CES triggers to improve performance and reduce noise.
• Enhanced solution import control using FCS similar to DCA, providing more stable feature rollout.
• Fixed InlineReferences bug improving reliability in core services that users depend on.
• Released version 10.4, ensuring stability and readiness of new customer‑facing features.
• Aligned guided prompt messages with design specifications for clearer user comprehension.
• Created feature flags for MCAPS Phase 2 UI updates, enabling progressive UI improvements.
• Updated competitor UI design for DCA to improve accessibility and clarity.
• Made "Add KS" button always visible for more intuitive knowledge source configuration.
• Fixed server configuration issues in competitor research API for dependable insights.
• Improved consent flow for salesperson users, reducing access friction.
• Updated MCS connector for improved email validation accuracy.
• Added existence check in Draft Outreach Email tool to prevent user‑facing errors.
• Improved Prerequisites screen for better customer understanding before feature activation.
• Added MDL workspace and FCS for sales agents improving evaluation and insight capabilities.
• Workflow activation added for new cleanup flow, improving workspace performance.
• Added error panel for COT to aid user troubleshooting.
• Migrated Email Copilot to new endpoint for improved email generation reliability.
• Updated rubrics for competitor insights, improving guidance and decision support.
• Added FCS for COT to enhance sales efficiency.
• Improved UI clarity and accessibility across various surfaces.
• Enhanced competitor research and outreach email personalization for more relevant insights.
• Enhanced system reliability and user experience through multiple stability and consistency improvements.

Repaired Functionality

• Resolved error in phone call sequence activity in work queue for smoother workflow.
• Ensured color contrast meets accessibility standards.
• Fixed quick campaign customization and content truncation issues.
• Improved account news content filtering reliability.
• Enhanced performance of ModernSA feature.
• Enabled automatic follow-up emails for DV record creation.
• Fixed retry iteration count bug in configuration topics.
• Corrected prediction status display errors.
• Restricted 'In Progress' banner visibility to opportunity owners.
• Corrected messages in DCA Setup Orchestrator.
• Resolved critical security bug in .NET SDK.
• Fixed truncation of Update and Cancel buttons.
• Improved screen reader announcements for error messages.
• Made 'Learn more' links distinguishable without relying on color.
• Ensured unique identifiers for 'remove' buttons.
• Fixed UI inconsistencies with scroll bars.
• Corrected AI Prompts completion status display.
• Migrated network isolation in pipelines for security.
• Assigned correct ownership in research result records.
• Fixed screen reader focus and heading structure issues.
• Ensured consistent pre-requisite notifications.
• Added discernible text to buttons for accessibility.
• Fixed intent detection in Orchestrator.
• Improved MSX onboarding stability.
• Fixed focus loss after activating 'Create Custom Research'.
• Corrected messaging when no knowledge source is added.
• Handled AggregateQueryRecordLimit exceeded error.
• Fixed styling issues in product dialog.
• Enhanced CRM.Client.LeadResearch stability and compatibility.
• Fixed Hand Off Criteria default error state.
• Improved screen reader focus on competitor research page.
• Corrected 'Quick setup' visibility.
• Fixed wrong options in Email Validation flow.
• Resolved mapping issues for opportunity IDs.
• Improved icon visibility in certain themes.
• Made summary visible immediately after task completion.
• Fixed content shifting due to scroll bar.
• Corrected FetchXML filter criteria for Link Entities.
• Aligned Deal Close Agent interface with design specifications.
• Fixed ownership tracking in M365 watermark.
• Disabled unintended feature activation for stability.
• Ensured visibility of related records with empty optional fields.
• Prevented unwanted email processing.
• Managed data cleanup after workflow activation failures.
• Ensured reliable data retrieval in MeetingPrep.
• Improved query routing accuracy.
• Directed users to configuration page after chat exit.
• Enabled viewing of owner update summaries during ongoing research.
• Set default Supervisorflags to true.
• Added detailed DLP policy information in error messages.
• Fixed revenue data issues in Opportunity Summary.
• Improved compatibility with latest Copilot Solutions.
• Fixed incorrect profile returns in SQA Orchestrator.
• Corrected agent name display when 'engage' is selected.
• Prevented email filter display regression.
• Disabled customization for AI models and topics for consistency.
• Streamlined configuration process by removing unnecessary prerequisites.
• Ensured accurate citation display in Generative AI module.
• Fixed ownership update failures for old research records.
• Enabled personalized banner text in App Copilot and PVA Integration.
• Removed duplicated agent processing state records.
• Optimized feature status checks for performance.
• Fixed products dropdown issue.
• Relaxed query checks for account research results.
• Prevented repetitive auto-reply email processing.
• Enhanced reliability of online evaluations.
• Fixed logic and logging in Deal Close Agent.
• Updated playbook content for improved response accuracy.
• Ensured consistent banner visibility when agent is disabled.
• Added error notifications for MCS failures.
• Fixed outreach mail generation errors due to privilege issues.
• Prevented duplicate outreach emails.

Accessibility Repaired Functionality

• Ensured color contrast meets WCAG 2 AA minimum thresholds for improved readability.
• Fixed truncation of Update and Cancel buttons for better visibility.
• Improved screen reader announcements for required‑field error messages.
• Made 'Learn more' links distinguishable without relying solely on color.
• Added discernible text to interactive buttons for improved accessibility.
• Improved screen reader focus on the competitor research page.
• Fixed focus loss after activating the Create Custom Research button.
• Ensured error messages are properly announced by screen readers.
• Improved accessibility of interactive controls to prevent keyboard focus problems.
• Provided unique identifiers for all "remove" buttons (improves assistive tech reliability).
• Fixed UI inconsistencies with multiple scroll bars to ensure smoother navigation.
• Fixed screen reader focus and heading structure issues in research insights.

Return to the all version availability page.

If you have any feedback on the release notes, please provide your thoughts here.

Original source Report a problem

Microsoft Dynamics 365 Sales - version 9.0.25123.10001

Update package

• Service Update 214 for Microsoft Dynamics 365 Sales version 9.0.25123.10001 (or higher) 9.0.25123.10001

To determine whether your organization had this update applied, check your Microsoft Dynamics 365 version number. Click the gear icon in the upper-right corner, and then click About.

An (*) at the end of a fix statement denotes that this repair item was incorporated into multiple service update releases.

Please click here to view the list of features and functionalities included in this year's release wave.

Service Update 214 resolves the following issues:

New/Enhanced Functionality

• Deal Risk & Importance customization now functions correctly, improving user experience and reliability.
• Latest localization files integrated into OneCRM Sales, improving accuracy and usability across regions.
• Feature dashboard now shows number of leads instead of runs and fixes filtering for RE mode.
• Multi-lingual support added for competitor research and Sales Copilot features.
• Introduced new BOT for custom research to improve efficiency and decision-making.
• Added Read-Only mode for secure and consistent interface in OneCRM D365 Sales.
• Added support for priority ranking in MCAPS powered by Generative AI to improve task prioritization.
• Integrated custom API calls in Power Automate flows for enhanced automation.
• Added real-time office availability fetcher service in EmailCopilotV2 for improved scheduling.
• Enhanced suggested action texts post-phone call and post-email sending for better user guidance.
• Integrated telephony events into OneCRM D365 Sales to improve communication efficiency.
• Added support for refresh in Opportunity Research page for real-time data updates.
• Improved multilingual support for agent language code attribute and various AI synthesizer features.
• Enhanced UI components and dynamic menu rendering for better user experience.
• Improved AI-driven insights and skills configuration for better deal risk management.
• Enabled sellers to get insights and recommendations relevant to products associated with opportunities.
• Supported provisioning and publishing of new bots in existing agents for organizational efficiency.
• Added ML service client and response processor in EmailCopilotV2 to boost email automation.
• Created FCS controlled UI component for Custom Insights to improve decision-making.
• Enhanced readiness prompts for better clarity and relevance in qualification areas.
• Implemented automatic stop of email processing when user consent expires or is revoked to ensure compliance.
• Added lifecycle progress tracking in Deal Close Agent components.
• Added multi-language support for AccountResearch and CustomizationAgent features.
• Improved SalesOpportunityResearch API with custom research insights.
• Added new Account Research Summary Synthesizer for efficient sales opportunity summarization.
• Enhanced upload quota upload functionality for reliability.
• Improved bot schema validation and event value reception in Deal Close Agent.
• Enhanced accessibility and UI validation for new attributes.
• Enabled use of EE instead of EELite during agent enablement for better performance.
• Improved email management with new v2 endpoint request builder.
• Enhanced pipeline skill accuracy in Sales Copilot.
• Improved caching for sales acceleration features.
• Fixed invalid email UI tagging.
• Improved system performance and reliability with UI refinements and reduced redundancy.
• Added multi-lingual support for various AI and research features.
• Enhanced scheduling and business closure data reliability.
• Improved system security and stability with critical vulnerability fixes.
• Enhanced software stability and user experience by refining UI interactions and accessibility.

Repaired Functionality

• Fixed lookup logic in focused view search for improved CRM functionality.
• Corrected filtering and sorting issues in Sales Insights for admins.
• Resolved display issues with the "Record type" icon on work queue cards.
• Fixed agentic memory bank bug to prevent unexpected behavior during app updates.
• Resolved overlapping and truncation issues in hierarchy visualization controls.
• Added server‑side validation for Agent Profile activation (prevents user‑facing activation failures).
• Fixed various NVDA screen reader announcements for improved accessibility.
• Corrected color contrast ratios and keyboard focus order to meet accessibility standards.
• Fixed UI access issues for buttons and controls in Opportunity Score and Relationship Analytics.
• Resolved issues with email validity tagging and status‑update announcements.
• Improved caching for Sales Acceleration configuration status for more responsive UI.
• Fixed label associations with spin buttons and tooltip announcements for accessibility.
• Addressed hallucination issues in Sales Copilot pipeline skill for more accurate insights.
• Fixed event‑value reception issues in Deal Close Agent.
• Corrected use of color for link differentiation in Digital Sales Prospecting settings.
• Resolved bot response schema validation failures (visible in bot interactions).
• Fixed data loading and flickering issues in scheduling components.
• Improved monitoring and telemetry for Deal Close Agent (improves reliability customers experience).
• Fixed invalid email UI tagging and improved email‑processing compliance.
• Enhanced UI validation and lifecycle tracking in Deal Close Agent components.
• Fixed various bugs related to multi‑language support and AI features.
• Fixed issues causing UI truncation and overlapping in various modules.
• Resolved bugs affecting user experience in sales and scheduling features.

Accessibility Repaired Functionality

• Improved accessibility by correctly associating visual labels with controls in hierarchy visualization.
• Enhanced link distinguishability without relying on color in Dynamics 365 Sales Workspace.
• Ensured NVDA screen readers announce links and button states with proper context.
• Improved color contrast ratios for buttons and indicators to meet accessibility standards.
• Fixed keyboard focus order and ensured focus remains within pages.
• Enabled keyboard access to buttons and controls in Opportunity score columns.
• Corrected name properties for toggle buttons to improve assistive technology usability.
• Ensured screen readers announce status updates and tooltip information correctly.
• Improved focus visibility on spin buttons and other interactive elements.
• Enhanced accessibility in Relationship Analytics and Predictive Opportunity Scoring screens.
• Fixed use of color for link differentiation in Digital Sales Prospecting settings.
• Improved screen reader compatibility for various UI elements in Dynamics 365 Sales Premium.
• Enhanced accessibility for visually impaired users by ensuring proper announcements and focus management.
• Corrected accessibility issues related to zoom and text truncation.
• Improved usability for screen reader users by simplifying tooltip text and announcements.

Return to the all version availability page.

If you have any feedback on the release notes, please provide your thoughts here.

Original source Report a problem

Microsoft Dynamics 365 Sales - version 9.0.25113.10001

Update package Version number
Service Update 213 for Microsoft Dynamics 365 Sales version 9.0.25113.10001 (or higher) 9.0.25113.10001

To determine whether your organization had this update applied, check your Microsoft Dynamics 365 version number. Click the gear icon in the upper-right corner, and then click About.

An (*) at the end of a fix statement denotes that this repair item was incorporated into multiple service update releases.

Please click here to view the list of features and functionalities included in this year's release wave.

Service Update 213 resolves the following issues:

New/Enhanced Functionality

• Outreach emails now have consistent paragraph spacing for better readability.
• EmailCopilotV2 adds an email data fetcher service, improving AI‑generated email accuracy.
• ‘Learn more’ links added to SQA helper cards to guide users more effectively.
• Deal Risk & Importance customization enhances Opportunity Research and Deal Acceleration insights.
• New email & call menu button improves user interaction options.
• New Account Research Summary Synthesizer Flow speeds up understanding of customer accounts.
• New topic added in OR bot for merging account research summaries.
• Update of SCA strings improves AI‑generated content accuracy.
• Update of rubrics for competitor insights improves guidance quality.
• FCS added for COT enhances Deal Close Agent capabilities.
• Additional filtering options added to the Enhanced Add Products grid for more precise selection.
• Prep sheet button moved to the top of the page for easier access.
• Support for right‑to‑left (RTL) languages added in AgentConfigControl for global usability.
• New custom API to get formatted opportunity values improves accuracy in sales workflows.
• Supervisor features enabled by default for better management visibility.
• Removal of the accessibility prompt streamlines agent interactions.
• Error panel added for COT improves troubleshooting clarity.
• Custom API to return rule‑to‑role mapping improves accuracy in user configurations.
• Integration of end‑to‑end simulation flow improves Deal Close Agent reliability.
• Uptake of the latest Sales Insights package versions ensures feature freshness and stability.
• Improved AI efficiency via new services (e.g., EmailCopilotV2 automation).
• Enhanced orchestration reliability via new logs and APIs in Opportunity Research.

Repaired Functionality

• Fixed truncation of content on the Opportunity Research screen during resize.
• Improved visibility of 'About' and 'Detail' tabs in dark mode.
• Fixed keyboard focus order in “Select field to map” dialog.
• Improved screen reader focus on competitor research page.
• Ensured screen reader announces required-field status.
• Eliminated duplicate screen reader announcements.
• Ensured buttons have discernible text in Sales Opportunity Research.
• Fixed toolbar visibility and dropdown truncation in research dialog.
• Improved clarity of summary page headings.
• Removed black border around focused text input box.
• Fixed bullet point display issues.
• Positioned loading text correctly above loading bar.
• Outreach emails have consistent paragraph spacing.
• Improved differentiation of 'learn more' links in outreach emails.
• Added salutation in outreach templates.
• Included AI disclaimers in outreach emails during simulation.
• Fixed outreach mail generation failure due to read privilege issues.
• Prevented duplicate outreach emails, including cases where a previous run was incomplete.
• Passed source application when calling unsubscribe API link.
• Corrected currency display in Opportunity Research Insights.
• Corrected revenue display issues in Opportunity Summary.
• Lead names now display correctly in Sales Agent interface.
• Corrected agent usernames in Deal Close Agent.
• Added additional details to agent summary aligning with design.
• Added static AI disclaimer in quick and step‑by‑step flows.
• Updated knowledge source for improved AI accuracy.
• Improved messaging clarity in value proposition flows.
• Corrected stakeholder entity type in citations.
• Improved citation display for COT.
• Ensured continuous SAR creation and research.
• Enabled custom text for banners.
• Ensured configuration summary is visible during chat.
• Improved Orchestrator reliability and accuracy.
• Made Opportunity navigation link visible on research page header (both initial and repeated cases).
• Fixed incorrect summary text for Target Opportunity.
• Improved fallback logic in Deal Close Agent ensuring smooth behavior.
• Verified bug fixes for reliable Sales Copilot functionality.
• Related records now show even if optional name fields are empty.
• Fixed save‑button enablement issue when changing agent prerequisites.
• Validated SharePoint URL in DCA.
• Used default values for compliance profiles in DCA.
• Fixed permission prompt failure for Dataverse connection.
• Enabled modification of email templates in onboarding.
• Enabled customization for Sales Close Agent search entity.
• Added DLP policy details in error messages.
• Ensured SAR creation not blocked by workflow activation failures.
• Restarted processes correctly after errors.
• Improved record switching speed in modern Sales Agent.
• Reduced unnecessary follow‑ups in value proposition generation.
• Corrected query routing to DVQnA.
• New filtering options added in Enhanced Add Products grid.
• Fixed product dropdown issues (initial and secondary).
• Ensured fetchxml selection criteria always include conditions.
• Ported MSX onboarding fixes for smoother Deal Close Agent onboarding.
• Aligned user experience to design specifications across surfaces.
• Renamed Sales Agent to Setup Agent for improved clarity.
• Chat interface now displays personalized agent names.
• Agent started banner shows agent‑specific information.
• Added introduction context in reentry flow.
• Fixed summary repetition in onboarding workflows.
• Removed manual/quick setup dialog when agent is on.
• Improved compatibility with latest Copilot Solutions versions (multiple instances).
• Improved fallback to options without resuming setup.
• Deal Close Agent recovers smoothly from errors.
• Fixed connector error for data retrieval.
• Improved event value transmission in Deal Close Agent.
• Provided hotfix for online evaluations.
• Fixed start agent event notification.
• Parsed agent profile ID correctly.
• Fixed issues with selected record loading in main form.
• Ensured reliable MeetingPrep logical name retrieval.
• Fixed playbook content modification in Sales Close Agent.
• Prevented repeated auto‑reply email processing.
• Checked feature statuses only when enabled.

Accessibility Repaired Functionality

• Fixed truncation of content on the Opportunity Research screen during resize.
• Improved visibility of ‘About’ and ‘Detail’ tabs in dark mode.
• Fixed toolbar visibility and dropdown truncation in the research dialog.
• Ensured appropriate role attribute values to improve accessibility.
• Improved identification of ‘Learn more’ links without relying solely on color.
• Ensured buttons have discernible text in Sales Opportunity Research.
• Fixed keyboard focus order in the “Select field to map” dialog.
• Screen reader now announces mandatory status for required fields.
• Eliminated duplicate screen reader announcements for input fields.
• Screen reader now announces button states correctly in mapping dialogs.
• Added descriptive alt text to preview images on the lead research page.
• Defined proper title/name for SVG images in Compliance section.
• Ensured appropriate role attribute values for better accessibility.
• Improved identification of 'Learn more' links without relying on color.
• Screen reader now announces button states correctly.
• Defined title/name for SVG images in Compliance sections.
• Added descriptive alt text to preview images on lead research page.

Return to the all version availability page.

If you have any feedback on the release notes, please provide your thoughts here.

Original source Report a problem

Release Notes: Sales Qualification Agent (SQA) — Dynamics 365 Sales

In October 2025, we announced the general availability of the Sales Qualification Agent (SQA) in Dynamics 365 Sales —a breakthrough in autonomous lead qualification. Sales Qualification Agent empowers sellers by helping build higher quality opportunity while eliminating tedious, repetitive work. Sales Qualification Agent autonomously researches every lead, initiates personalized outreach, and engages prospects to understand purchase intent, ensuring that sellers spend their time meeting prospects who are ready to take the next step. With modes enabling both seller-driven and fully autonomous qualification, the agent supports a key goal for sales organizations—increasing revenue per seller.

Customers are using Sales Qualification Agent in two ways

• Helping boost revenue beyond current sales capacity
  • Responding to inbound leads within minutes instead of days, increasing response rates and in turn, qualified opportunities.
  • Engaging leads that sellers are unable to follow up on due to capacity constraints, or those deemed economically unviable to pursue.
  • Increasing pipeline quality by focusing the seller’s time on a handful of high intent, engaged leads recommended by the agent.
• Helping reduce sales costs
  • Reducing back-office costs related to lead research and validation, using Sales Qualification Agent in “Research only” mode to hand-off only the leads that meet the ideal customer profile criteria.
  • Automatically disqualifying low-quality leads, saving hours of seller time during the week.

Continuing benchmarking the quality of sales AI agents

Microsoft is building the future of agentic Sales technology with prebuilt AI agents, such as Sales Qualification Agent, the Sales Research Agent, and the Sales Close Agent available in Dynamics 365.

At Microsoft, we’re committed to delivering quality, trust, and transparency with our agents, and that requires rigorous evaluation. As we continue to build new agents and improve existing ones for critical sales workflows, evaluation benchmarks provide a structured and transparent way for our customers to measure quality for the jobs the agent does.

Today, we’re announcing the Microsoft Sales Bench —a new collection of evaluation benchmarks designed to assess the performance of AI-powered sales agents across real-world scenarios. This framework brings together purpose-built metrics, hundreds of sales-specific scenarios, and composite scoring validated by both human and AI judges.

The Sales Bench isn’t starting from scratch. It now formalizes and expands what began with the Sales Research Bench, published on October 21, 2025, which evaluates how AI solutions answer business research questions for sales leaders.

Today, we’re extending the Microsoft Sales Bench with a second benchmark: the Microsoft Sales Qualification Bench, focused on measuring how effectively AI agents qualify leads and generate high-quality pipeline.

Introducing the Sales Qualification Bench for lead qualification

This Microsoft Sales Qualification Bench evolved from rigorous evaluations we conducted since the Sales Qualification Agent’s public preview in April, with the goal of objectively measuring quality as we further developed the agent, partnering with customers from a diverse set of industries. Since the preview, we measured every update against these standards, ensuring improvements are real and repeatable.

We generated a synthetic dataset modeled after companies from three different industries, with 300 leads, with attributes such as name, company, and email ID—representative of what sales teams typically work with before any enrichment or hygiene is performed. In addition to these typical attributes, we also added key knowledge inputs such as value proposition of the products being sold, customer case studies, and documentation for answering customer questions.

In addition to Sales Qualification Agent, we used the evaluation framework to measure ChatGPT by OpenAI on the same dataset. Since we didn’t have access to an autonomous agent from OpenAI, we mimicked how a human seller would use ChatGPT to recreate the three key jobs SQA performs. We provided each system—Sales Qualification Agent and ChatGPT—the exact same lead inputs, knowledge sources, and contextual signals under controlled evaluation configurations. We used a ChatGPT Pro license with GPT-4.1. This model is the closest match (and slightly better) to Sales Qualification Agent’s GPT-4.1 mini, which we intentionally chose to deliver optimal quality at lower cost per lead than newer models. Additionally, Pro license was chosen to optimize for quality: ChatGPT’s pricing page describes Pro as “full access to the best of ChatGPT.”

The framework evaluates outputs from the three jobs across Sales Qualification Agent and ChatGPT:

• Research: Company research for the lead—background, strategic priorities, financial health, and latest news.
• Outreach: A personalized email generated based on research, to make initial contact with the lead.
• Engagement: The agent’s conversation with a lead until it’s qualified or dispositioned.

Our scoring metrics span core quality (accuracy, relevance, completeness), trustworthiness (grounding and citations), and business-specific success criteria (e.g., relevancy of company research to highlight interest in the seller’s offerings, personalization of the initial outreach emails sent to catch the lead’s attention, accuracy of responses to the lead’s questions to drive purchase intent, and the timing of handoff to a seller when the lead is ready to engage).

Outputs were scored independently by both human reviewers and an LLM judge built with GPT-5.1, using a 1–10 scale for each metric. These metric-specific scores were then rolled up using a simple average to produce a composite quality score. The result is a rigorous benchmark presenting a composite score and dimension-specific scores to reveal where agents excel or need improvement. Our methodology, metrics, and their definitions are described in this technical blog.

Results

In evaluations completed on December 4, 2025, using the Sales Qualification Bench, Sales Qualification Agent outperformed ChatGPT on each of the three jobs required for sales qualification:

• Research: The Sales Qualification Agent outperformed ChatGPT with 6% higher aggregate scores, leading on relevancy and completeness in research results that highlighted the lead company’s interest in the seller’s offerings.
• Outreach: Sales Qualification Agent demonstrated 20% better results compared to ChatGPT, generating email drafts with accurate personalization and mentions of relevant recent events that will resonate with the lead.
• Engagement: Sales Qualification Agent’s email responses to engage a lead over a multi-turn conversation scored 16% higher than ChatGPT’s. SQA generated emails that responded to the lead’s questions with accurate answers that develop their purchase interest and with precise discovery questions that qualify the lead before handing off to a seller.

In addition to performing better on these metrics, Sales Qualification Agent has the ability to run autonomously, which can help significantly reduce the time spent generating pipeline while helping sales teams build better quality pipeline.

Sales Qualification Agent scores well on these three jobs as its optimized for sales-specific scenarios and uses the following techniques to get great results:

• It uses agentic Retrieval Augmented Generation (RAG) to relentlessly research each lead, ensuring greater completeness. More on this in the following section.
• With knowledge of what the company sells, it can contextualize every workflow to increase relevancy for both the seller and the lead.
• It can retrieve organizational knowledge from attached documents and internal repositories like SharePoint with greater precision, boosting accuracy of its responses when engaging with the lead.

The technical blog details which metrics SQA excels at relative to ChatGPT, where it falls short, and why.

Translating evals to real-world impact

Running evals led to major Sales Qualification Agent improvements during its six-month preview. Early results prompted us to try agentic AI design patterns, especially agentic RAG, which improved our company research by allowing iterative web searches and real-time reasoning. They also led us to enhance data coverage by auto-linking existing CRM records to each lead and inferring company names from lead emails. These updates provided sellers with deeper insights, revealing strategic opportunities and risks beyond basic facts.

For instance, when researching leads for a security company, Sales Qualification Agent can link news on recent cyberattacks to increased demand for its software. As highlighted in the technical blog, research synthesized by the agent makes such inferences more consistently than ChatGPT. Enhancing the agent’s research also improved the relevance and personalization of outreach emails, helping agents better engage leads and clarify their ability and intent to purchase before handing them off to sellers.

Sandvik Coromant, a leader in precision cutting tools, partnered with us to pilot Sales Qualification Agent for their Digital Commerce program. After the updates, Pia Cedendahl, Global Sales Manager for Strategic Channels/Partners and Online Sales, noted, “Sales Qualification Agent’s answers became far more on-point to our business—it’s like having a research assistant that already understands what we care about.” Sandvik Coromant saw improved lead conversion and higher engagement from their Digital Account Managers, validating the impact of our evaluation-driven approach. Pia joined Microsoft leaders at the Microsoft Ignite 2025 session, “Accelerate revenue and seller productivity with agentic CRM,” where she shared how the team saved more than 120 hours and $19,000 in just the first three weeks since launching a pilot, and forecasted a 5% increase in revenue with full rollout.

Better insights, more personalization, proven value

Equipped with agentic AI design and backed by data-driven evaluation, customers can confidently use the Sales Qualification Agents so that:

• Sellers receive comprehensive company overviews, timely news highlights, and actionable recommendations that are consistently delivered with high quality—drawing a clear line from insight to action.
• Sales leaders can expand their qualified pipeline cost efficiently, with the agent ensuring high lead quality.
• Prospects benefit from more personalized outreach, enhancing their experience and supporting increased conversion rates.

What’s next

We’ll continue to refine Sales Qualification Agent using agentic design patterns, aiming to make every improvement measurable and meaningful. Stay tuned for the full evaluation results and methodology for the Sales Qualification Bench, which will be published for transparency and reproducibility. We also intend to add more evaluation frameworks and benchmarks to the Microsoft Sales Bench collection including benchmarks that cover future sales agent capabilities.

Get started with the Sales Qualification Agent

Original source Report a problem

AI-powered Dataverse Search and Copilot Experiences

Imagine being able to ask your CRM system a question like, “Which opportunities are likely to close this week?” or “Who has met with Ernie Kerrigan at Contoso recently?” and getting an instant, accurate answer without writing a single query or navigating through multiple Views in Dynamics 365.

Whether you’re using Copilot in Dynamics 365 Sales, Power Apps customized through Microsoft Copilot Studio, or Microsoft 365 Copilot for Sales, under the hood, these experiences leverage one common engine: AI-powered Dataverse (DV) Search, which seamlessly connects business users to the underlying database schema, translating intent into action without requiring technical expertise. Thousands of enterprise customers already rely on this capability to power their business workflows.

Figure 1: How AI-powered Dataverse Search Connects Copilot Experiences Across Dynamics 365

We’ve reimagined the technology behind Dataverse Search from the ground up. Leveraging recent breakthroughs in agentic AI, the new system delivers answers that are more relevant, contextual, and accurate to your specific business data. Think of it as an intelligent assistant that not only understands your question but figures out the best way to answer it using an adaptive reasoning process.

In this blog, we’ll explore why this agentic approach was necessary, how it works under the hood, and how it scales to enterprise needs supporting complex schemas, massive datasets, and domain specific terminologies while adhering to Microsoft Responsible AI principles. In particular, the agentic approach is model-agnostic, and while different models or fine-tuned models can influence the quality of results, the choice of model is orthogonal to the architecture. For this post, our emphasis remains on the agentic loop and its role in delivering dynamic, context-aware answers. Further, we will demonstrate our success via evaluation results and show you ways to customize it for your business.

Queries to Conversations: Unlocking Your Live Business Data

Every organization’s Dynamics 365 environment is unique, and most customers customize it extensively. Over time, these customizations lead to complex schemas, ambiguous relationships, and massive datasets spanning millions of records and terabytes of data. Our original Dataverse Search system was pioneering, but it relied on a fixed-plan natural language to SQL pipeline. A user’s question was converted to SQL through sequential stages: parsing, schema mapping, data linking, and SQL generation. This design was prone to cascading failure in a sequential pipeline. Each stage operated in isolation without shared context, so a single error could invalidate the entire query. Every question followed the same fixed flow, even when certain steps were unnecessary. This resulted in brittle behavior and suboptimal answers for complex or ambiguous queries that spanned multiple tables.

We recognized the need for a more adaptable, resilient approach to tackle the complexities of enterprise data. This upgrade shifts DV Search beyond simple Search into intelligent, interactive conversations with your business data. For you, this translates into immediate, actionable value by providing:

• Real-Time, Actionable Answers: Ask, “Which of my open opportunities in New York are scheduled to close this month?” and get an instant answer from the live Dataverse data. This isn’t a report from last night’s data refresh; it’s the current state of your business.

• Democratized Data Access: A service manager can ask, “Show me active, high-priority cases that haven’t been updated in 3 days” without needing to understand the underlying table structure of incidents and case/activities.

• Deeper Contextual Conversations: The agent supports multi-turn conversations. After asking about opportunities in New York, you can follow up with, “Of those, which ones are for our ‘Pro’ license?” The agent remembers the context, providing a progressively refined answer.

Under the Hood: Agentic Architecture

To overcome some of the limitations of the earlier system and to meet the complex customer scenarios, the new DV Search architecture introduces an Agentic Orchestrator powered by GPT4.1. It transforms query handling from a static pipeline into a dynamic reasoning loop: plan → execute → refine. Instead of blindly converting text to SQL, the orchestrator treats each question as a goal, intelligently deciding the best steps to reach it.

Figure 2: Agentic Architecture for AI-powered Dataverse Search

Context Awareness and Conversations: When a user submits a new or follow-up question, a dedicated preprocessing component reviews prior conversation history and rewrites the query as a single, self-contained question, enabling coherent multi-turn conversations. For example, if you ask, “Show my top opportunities in Q4” and then follow up with “How about in Europe only?” the component understands the second question is a refinement of the first rather than starting from scratch or losing track of prior context. This conversational capability makes interactions feel natural and efficient. The refined question is then enriched with the business’s domain knowledge (glossary) to fully reflect the user’s intent within the specific business context.

Dynamic Planning and Execution: When the self-contained question comes in, the orchestrator doesn’t simply translate it into SQL. Instead, it breaks the query into logical steps and decides which tools to use and in what order, while also utilizing the domain knowledge encapsulated with the supplied glossaries. These tools include:

• schema_linking_tool: Schema lookup for understanding tables and relationships
• data_linking_tool: Semantic Search for finding relevant data values and resolving data ambiguities
• sql_execution_tool: SQL execution tool for retrieving results
• submit_plan_update_tool: Captures both the original plan and any course corrections made during execution

The orchestrator adapts on the fly if the first attempt fails or returns incomplete results. It analyzes the issue, revises the plan, and retries. This self-correcting loop is a major improvement over older systems that suffered from cascading failures.

Handling Relational Complexity: One of the most powerful aspects of this approach is its ability to handle relational complexity. Operational business application schemas often require multi-hop joins across multiple tables, including custom entities. The orchestrator understands these relationships and can navigate them intelligently, ensuring accurate joins and filters even in highly customized environments. For example, if a question involves linking Accounts to Opportunities and then to a custom Product table, the agent plans the steps and executes them seamlessly.

Personalization and Learning: Personalization further enhances the experience. Over time, the system learns from usage patterns within your organization. If you frequently work with the Accounts table or use certain custom fields, the agent prioritizes those interpretations in future queries. This learning is based on interaction signals, not external data, and is carefully scoped to respect privacy and organizational boundaries. The result is a system that becomes more aligned with your business logic the more you use it.

Real-World Example

Imagine you run Fourth Coffee Machines, a business selling premium espresso and grinder units to commercial and residential customers. It’s managed through a Power App built on Dataverse. A seller begins with a simple keyword search in top-bar search in Power Apps for “Fourth Coffee” to confirm the account record. Thanks to fuzzy matching and relevance re-ranking, even typos like forth coffee or 4thcoffee surface the right entity instantly.

From there, the seller asks Copilot: “Show me my open opportunity at risk with Fourth Coffee.” The agent rewrites the query, scopes it to the current user, interprets at risk as a cold rating, and joins Account → Opportunity. It executes SQL, returns the results, and summarizes them with citations—no manual filtering, no report building.

Finally, the seller pivots to a KPI question: “What is the HRR for Coffee Grinder 02?” Here, the agent consults the business glossary, which defines HRR as Happy Response Rate (positive sentiment ÷ total reviews in the Product Review table). It computes the metric, explains the formula, and cites the source records. The user now understands exactly how the number was derived.

Under the hood, this seamless experience is powered by an Agentic Orchestrator that plans, executes, and refines dynamically. It chooses the right tools, adapts when errors occur, and injects domain knowledge from glossaries. By combining dynamic planning, iterative refinement, relational understanding, and personalization, it represents a significant leap forward from static query pipelines. It’s not just about generating SQL it’s about orchestrating an intelligent, context-aware process that feels conversational and delivers real business value.

Evaluation Results

To measure how well our agentic system performs in practical enterprise scenarios, we evaluated it against curated datasets of user prompts each representing or assisting with a real job to be done. These prompts reflect the everyday questions and tasks that drive productivity for CRM users— from quick record lookups and aggregation analytics using keyword search or simple filters and joins, to complex multi-join queries requiring domain expertise. By categorizing prompts into levels of complexity, we ensure the evaluations capture the full spectrum of enterprise challenges.

For each complexity level, we report two practical metrics: Relaxed Execution Accuracy (EX Accuracy) and P80 Latency. Relaxed Execution Accuracy measures how often the generated SQL returns the same rows as the reference SQL when both are executed on the same data—extra columns in the predicted query are allowed, but extra or missing rows are not; order is ignored unless ORDER BY is specified. P80 Latency is the 80th percentile end to end response time, from request receipt through retrieval, model inference, and verification to the final SQL result. Together, these metrics give a transparent, action-oriented view of correctness and responsiveness as task complexity increases. It highlights where the Agentic framework delivers reliable, efficient answers that empowers users to get more done with natural language.

† Metrics averaged over multiple runs

In practice, higher accuracy often comes at the cost of increased latency. Conversely, pushing for low latency can reduce end to end quality. This Agentic system is designed to navigate that tradeoff, delivering strong accuracy while keeping latency within practical bounds. This achieves a practical balance for production use.

Tuning for Your Business: Glossaries and Enriched Schema

No AI system knows your business out-of-the-box. We’ve added tuning mechanisms that let makers refine how the Q&A agent understands your data:

• Glossaries: You can define a glossary to teach the agent your company’s unique vocabulary and acronyms. For example, if “QoQ” is common slang on your team for “quarter-over-quarter” or “CTX” refers to a particular set of products, you can add those to the glossary. The next time someone asks “What’s the QoQ growth for CTX?”, the agent will know exactly what that means. This helps align the AI with the lingo of your organization so it interprets queries the same way a knowledgeable employee would.

• Schema Descriptions: Dataverse allows adding custom descriptions to tables and columns. By populating these descriptions with meaningful info, you give the agent extra context. For instance, two fields might both be called “Status” – one on a custom entity and one on a standard entity. If you add descriptions like “(Order Status – custom)” vs “(System Status code)”, the agent can use that to pick the right field during SQL generation. Essentially, you’re able to clarify the semantics of your data model for the AI.

Using the inherent metadata in Dataverse (like relationships and display names) plus these maker-driven additions, the agentic system can be tailored to use the correct terms and relationships in your domain, boosting accuracy even further. And because you control these glossaries and descriptions, you can continuously refine the AI’s understanding as your business evolves.

Conclusion

By reinventing Dataverse Search with an agentic architecture, we’ve moved from a rigid query engine to an adaptive, intelligent assistant for your business. The system understands nuance, handles ambiguity through reasoning, and even lets you inject your domain knowledge. Early adopters are seeing more questions answered correctly and faster than before, turning previously buried data into actionable insights. One leading global financial services company saw an Execution Accuracy surge from 22% to 97% on their marquee set of scenarios. This marks a significant step toward making enterprise data truly conversational. It empowers everyone from business users to power makers to tap into complex data and get the answers they need instantly and accurately, simply by asking.

Original source Report a problem

Transforming sales with Sales Development Agent

Earlier in 2025, we introduced our vision for how AI agents will transform critical sales processes like building pipeline and qualifying leads. Today marks the next milestone in that journey with the Microsoft Sales Development Agent, available through the Frontier Program in December 2025. Many sales organizations are under pressure to deliver more revenue with limited resources, and the Sales Development Agent helps sales teams scale their impact. This allows sellers to focus on nurturing customer relationships and closing deals.

Features include:

• Revenue and pipeline growth: The agent continuously researches prospects, crafts personalized outreach, and automatically follows up to ensure no lead is left behind.
• Scalability: Fully independent, yet collaborative, the agent acts as a teammate, with the ability to hand off leads to human sellers when needed.
• Security and governance: Built on Microsoft’s trusted security and compliance foundation and when enabled with Agent 365, the agent adheres to robust policies and access controls to ensure user data and workflows are protected.

Sales Development Agent connects with leading CRM systems like Salesforce and Microsoft Dynamics 365, and the Microsoft 365 apps your teams already use like Microsoft Outlook and Microsoft Teams.

The Microsoft sales team is among the first to use Sales Development Agent to reinvent the sales engagement process. With the use of Sales Development Agent, there was a 15.1% increase in the lead-to-opportunity conversation rate.

Sales leaders want to help sellers act on more leads, reach more customers, grow faster, and improve revenue per seller. Microsoft Sales Development Agent can make that possible by creating an infinitely scalable sales organization, so no lead is left behind. Accenture plans to pilot Sales Development Agent across our global inside sales-as-a-service business—which helps clients sell to customers around the world—to boost their reach and revenue while maintaining cost to serve. We’ll use what we learn to help clients leverage Sales Development Agent, scale their teams, and unlock new growth.

—Chris Hergesell, Sales Reinvention Lead, Accenture Song

Learn more about Sales Development Agent with Accenture

From System of Record to System of Action

In October 2025, we shared our vision for agentic business applications—built on agents, Copilot, and unified data. These components are what define Dynamics 365 as a system of action.

Today, we’re taking that vision further with updates to Model Context Protocol (MCP) servers across Dynamics 365 and Microsoft Power Platform, strengthening the foundation for agentic capabilities across your entire business. MCP servers are configurable bridges between the business data within your line-of-business (LOB) apps, and the agents you build using tools like Microsoft Copilot Studio. It serves as a universal intermediary, unlocking a unified platform agnostic access to app data, modernizing how AI agents are interoperable with your apps.

For customers of Dynamics 365 Sales and Customer Service, we’ve used MCP to simplify integration between agents in Dynamics 365 and the platforms used by sellers and service reps to execute complementary workflows, like lead research, engagement, and qualification, as well as case management and case resolution, available in public preview on November 21, 2025.

Discover how the Dynamics 365 ERP MCP server unlocks real-time functions and AI-driven insights for faster, smarter decisions

For customers of Dynamics 365 ERP, we are announcing the public preview of the MCP server that unlocks hundreds of thousands of ERP functions for real-time use. We are also introducing a new analytics MCP server in public preview starting in December 2025. These two servers provide a secure, standardized foundation to connect ERP data with AI-powered analytics, helping customers make faster, more accurate decisions and innovate without sacrificing governance.

We are also announcing the Power Apps MCP server in public preview that enables agents to seamlessly trigger app capabilities such as approvals, form submissions, and data retrieval. This makes every Power App a composable, reusable building block in your organization’s AI ecosystem empowering both citizen and professional developers to expose app functionality to agents with confidence and control.

Lastly, the Dataverse MCP server, now generally available, allows people to benefit from natural language interactions, receiving real-time answers grounded in Dataverse data, while makers and admins gain powerful, built-in tools for data operations, search, and prompt execution.

We see tremendous excitement from customers and partners for agentic Dynamics 365 applications. Take Ramp, a financial operations platform designed to save companies time and money. Ramp built an agentic solution, currently in preview, using Microsoft Foundry that integrates with Dynamics 365 Business Central and Teams to streamline employee expense management.

Join the movement to the Frontier with Copilot, agents, and agentic business applications

We know that moving to the Frontier isn’t just about technology. That’s why we’re partnering with Harvard Business School to collaborate on research and executive education to help you put this into practice at your own company. We’re also sharing new resources for leaders on their journey to the Frontier Firm with Frontier Function Guides for Sales, HR, and IT and a look inside our learnings at Microsoft–including three ways to turn insight into action. We’re committed to helping you transform—we’ll see you at the Frontier!

Microsoft Ignite 2025: Copilot and agents built to power the Frontier Firm

If you’re interested in learning more:

• Explore the Microsoft Ignite 2025 sessions to see agents and agentic business applications in action.
• Register for our year-end webinar to learn about more agents in Dynamics 365 (December 2, 2025)
• Join us at the Convergence ERP Conference (December 9-11, 2025).

Internal Microsoft sales team data based on time period January 1 to November 7, 2025. Total customers outreach by the agent: 61,734. Lead-to-opportunity ratio (sales qualification): 15.1%.

Original source Report a problem

New/Enhanced Functionality

• Bulk email functionality in D365 Sales Accelerator Workspace is restored, enhancing communication efficiency and workflow for case entity users.
• New agentic memory bank enhances CRM capabilities, boosting sales and lead management efficiency.
• Reduction in verbosity of competitor research results improves decision-making for sales teams.
• Enable company resolver flag ahead of branch cutoff to ensure seamless outreach.
• SalesPro integrates autonomous agent capabilities, enhancing data analytics and customer interactions.
• NSAT Survey onboarding improves user experience and operational efficiency.
• Improved clarity and user experience on research page and message bars.
• Handling of error states in SharePoint uploads enhances reliability and user experience.
• AI disclaimers updated and relocated to enhance user trust and legal compliance.
• Custom APIs for Configuration Agent improve deal closing efficiency.
• Addition of debugging info in branch preview enables faster issue resolution.
• Removal of hardcoded endpoints improves system flexibility and reliability.
• Custom API for Synthesizer Response enhances user experience in handling responses.
• Improved error handling during async activation provides accurate error codes.
• Localized error messages improve usability for diverse users.
• New customAPI for DraftOutreachEmail tool boosts email drafting capabilities.
• Improved error handling during connection creation enhances system reliability.
• Admins receive clear, localized error messages for faster issue resolution.
• Accurate product pricing ensured in backend API.
• Enhanced reliability and functionality of Opportunity Research Updates.
• Addition of new attribute in Sales agent profile entity to store async activation errors.
• M365 E2E feature reliability improved for smoother user experience.
• Custom API for Engage MCP Tool enhances user interaction and efficiency.
• Fixes in UI bugs improve user experience in Deeper Insights.
• New explanatory strings added to sales agent UX feature for better understanding.
• Accurate access roles assigned to app users for enhanced functionality.
• Improved error handling in sync API provides clearer validation messages.
• New API skeleton implemented for retrieving old sales records.
• Tailored insights and research sources improve decision-making efficiency.
• Localization support added for citations.
• MCP server features marked with preview tag for clarity.
• Integration of MCS connector v2 streamlines sales processes.
• Security upgrade to dotnet-sdk enhances data protection.
• Summary agent-specific naming improves clarity in automated workflows.
• Updated display name for DCA enhances UI consistency.
• Improved consistency and readability of agent outputs.
• Enhanced account and competitor analysis through updated copilot connector.
• Improved copilot connectors ensure seamless user experience.
• Talking points relocated within deeper insights for better organization.
• Automated weekly updates improve Digital Workspace reliability.
• Relationship Intelligence features enhanced for better performance.
• Agent creation and start features disabled when AI prompts are inactive to prevent confusion.
• Updated MCS connector improves OpportunityAccountResearch Flow.
• Helper card content updated for clearer guidance.
• Resolver bot functionality enhanced for efficient sales query handling.
• UI clarity and flexibility improved by making preferred knowledge settings optional.
• Remaining MCP tool definitions integrated for comprehensive solution.
• Enhanced error handling in read-only mode improves reliability.
• Synthetic data and scripts improve AI-generated summary accuracy.
• Optimized getConsent API enhances efficiency and reduces latency.
• Reliable deployment of updates ensures system stability.
• AI-driven insights integrated into D365 Sales for improved decision-making and collaboration.

Repaired Functionality

• Bulk email functionality for case entities restored, enhancing communication efficiency.
• Advanced memory bank features integrated to improve data management.
• 'Save Failed' error resolved for smooth seller assignment.
• Inventory bootstrapping bug fixed to improve lead routing reliability.
• Critical security vulnerability fixed to ensure safer usage.
• Improved clarity in UI messaging reduces user confusion.
• Write permission issues fixed to ensure seamless sales qualification processes.
• Accurate error state detection during product information retrieval enhanced.
• Reliable saving of sales agent profiles ensured.
• DCA profile deactivation errors resolved to maintain system integrity.
• Citation filtering accuracy improved.
• AI-driven sales opportunity research reliability enhanced.
• AI transparency disclaimers added for trust and clarity.
• Consistent and accurate citation formatting ensured.
• Latest feature and fix updates incorporated for improved system reliability.
• Email preview functionality fixed to prevent repeated display issues.
• Bug related to missing entity resolved to prevent operational disruptions.
• Opportunity summaries now display complete research generation information.
• Reliable insights triggering ensured for improved sales strategies.
• Clarified lead categorization in AI-generated leads.
• High severity security alerts resolved for better data protection.
• Agent setup process improved by enforcing AI Prompts prerequisite.
• Email rendering issues fixed for better communication.
• Custom Insights prompt structure improved for clarity.
• Accurate insights provided for different company categories.
• Unnecessary notifications prevented after ORA activation.
• Warning messages removed during successful agent activation.
• Missing activation button issue fixed.
• Confusing UI messages eliminated when preview records are missing.
• JSON input errors fixed in CustomsInsights flow.
• Improved integration and functionality of Outreach PA flow.
• UI distortion fixed when AI Agents disabled in Copilot Hub.

Accessibility Repaired Functionality

• Improved usability for users relying on accessibility features, ensuring better visibility and interaction in Hierarchy Visualization settings.
• Integration of agent playbooks with SharePoint API enhances accessibility and organization.
• Accessibility improvements ensure better visibility and interaction.
• Accessibility and functionality improvements in LinkedInExtensions.

To determine whether your organization had this update applied, check your Microsoft Dynamics 365 version number. Click the gear icon in the upper-right corner, and then click About.

An (*) at the end of a fix statement denotes that this repair item was incorporated into multiple service update releases.

Please click here to view the list of features and functionalities included in this year's release wave.

Return to the all version availability page.

If you have any feedback on the release notes, please provide your thoughts here.

Original source Report a problem

The New Frontier: AI Research Agents in Sales

In today’s hyper-competitive business landscape, sales leaders face a relentless challenge: how to drive growth, outpace competitors, and make smarter decisions faster in a resource constrained environment. Thankfully, the promise of AI in sales is no longer theoretical. With the advent of agentic solutions embedded in Microsoft Dynamics 365 Sales, including the Sales Research Agent, organizations are witnessing a transformation in how business decisions are made, and teams are empowered. But how do you know if these breakthrough technologies have reached a level of quality where you can trust them to support business-critical decisions?

Today, I’m excited to share an update on the Sales Research Agent, in public preview as of October 1, as well as a new evaluation benchmark, the Microsoft Sales Research Bench, created to assess how AI solutions respond to the strategic, multi-faceted questions that sales leaders have about their business and operational performance. We intend to publish the full evaluation package behind the Sales Research Bench in the coming months so that others can run these evals on different AI solutions themselves.

Sales Research Agent in Dynamics 365 Sales empowers business leaders to explore complex business questions through natural language conversations with their data. It leverages a multi-modal, multi-model, and multi-agent architecture to reason over intricate, customized schemas with deep sales domain expertise. The agent delivers novel, decision-ready insights through narrative explanations and rich visualizations tailored to the specific business context.

For sales leaders, this means the ability to self-serve on real-time trustworthy analysis, spanning CRM and other domains, which previously took many people days or weeks to compile, with access to deeper insights enabled by the power of AI on pipeline, revenue attainment, and other critical topics.

Image: Screenshot of the Sales Research Agent in Dynamics 365 Sales

Image: Screenshot of Sales Research Bench

“As a product manager in the sales domain, balancing deep data analysis with timely insights is a constant challenge. The pace of changing market dynamics demands a new way to think about go-to-market tactics. With the Sales Research Agent, we’re excited to bridge the gap between traditional and time-intensive reporting and real-time, AI-assisted analysis — complementing our existing tools and setting a new standard for understanding sales data.”

Kris Kuty, EY LLP
Clients & Industries — Digital Engagement, Account, and Sales Excellence Lead

What makes the Sales Research Agent so unique?

• Its turnkey experience goes beyond the standard AI chat interface to provide a complete user experience with text narratives and data visualizations tailored for business research and compatible with a sales leader’s natural business language.
• As part of Dynamics 365 Sales, it automatically connects to your CRM data and applies schema intelligence to your customizations, with the deep understanding of your business logic and the sales domain that you’d expect a business application to have.
• Its multi-agent, multi-model architecture enables the Sales Research Agent to build out a dedicated research plan and to delegate each task to specialized agents, using the model best suited for the task at hand.
• Before the agent shares its business assessment and analysis, it critiques its work for quality. If the output does not meet the agent’s own quality bar, it will revise its work.
• The agent explains how it arrived at its answers using simple language for business users and showing SQL queries for technical users, enabling customers to quickly verify its accuracy.

Why Verifiable Quality Matters

Seemingly every day a new AI tool shows up. The market is crowded with offers that may or may not deliver acceptable levels of quality to support business decisions. How do you know what’s truly enterprise ready? To help make sure business leaders do not have to rely on anecdotal evidence or “gut feel”, any vendor providing AI solutions needs to earn trust through clear, repeatable metrics that demonstrate quality, showing where the AI excels, where it needs improvement, and how it stacks up against alternatives.

While there is a wide range of pioneering work on AI evaluation, enterprises deserve benchmarks that are purpose-built for their needs. Existing benchmarks don’t reflect 1) the strategic, multi-faceted questions of sales leaders using their natural business language; 2) the importance of schema accuracy; or 3) the value of quality across text and visualizations. That is why we are introducing the Sales Research Bench.

Introducing Sales Research Bench: The Benchmark for AI-powered Sales Research

Inspired by groundbreaking work in AI Benchmarks such as TBFact and RadFact, Microsoft developed the Sales Research Bench to assess how AI solutions respond to the business research questions that sales leaders have about their business data.

Read this blog post for a detailed explanation of the Sales Research Bench methodology as well as the Sales Research Agent’s architecture.

This benchmark is based on our customers’ real-life experiences and priorities. From engagements with customer sales teams across industries and around the world, Microsoft created 200 real-world business questions in the language sales leaders use and identified 8 critical dimensions of quality spanning accuracy, relevance, clarity, and explainability. The data schema on which the evaluations take place is customized to reflect the complexities of our customers’ enterprise environments, with their layered business logic and nuanced operational realities.

To illustrate, here are 3 of our 200 evaluation questions informed by real sales leader questions:

1. Looking at closed opportunities, which sellers have the largest gap between Total Actual Sales and Est Value First Year in the ‘Corporate Offices’ Business Segment?
2. Are our sales efforts concentrated on specific industries or spread evenly across industries?
3. Compared to my headcount on paper (30), how many people are actually in seat and generating pipeline?

Judging is handled by LLM evaluators that rate an AI solution’s responses (text and data visualizations) against each quality dimension on a 100-point scale based on specific guidelines (e.g., give score of 100 for chart clarity if the chart is crisp and well labeled, score of 20 if the chart is unreadable, misleading). These dimension-specific scores are then weighted to produce a composite quality score, with the weights defined based on qualitative input from customers, what we have heard customers say they value most. The result is a rigorous benchmark presenting a composite score and dimension-specific scores to reveal where agents excel or need improvement.

Sales Research Bench uses Azure Foundry’s out-of-box LLM evaluators for the dimensions of Text Groundedness and Text Relevance. The other 6 dimensions each have a custom LLM evaluator that leverages Open AI’s GPT 4.1 model. 100-pt scale has 100 as the highest score with 20 as the lowest. More details on the benchmark methodology are provided here.

Running Sales Research Bench on AI solutions

Here’s how we applied the Sales Research Bench to run evaluations on the Sales Research Agent, ChatGPT by OpenAI, and Claude by Anthropic.

• License: Microsoft evaluated ChatGPT by OpenAI using a Pro license with GPT-5 in Auto mode and Claude Sonnet 4.5 by Anthropic using a Max license. The licenses were chosen to optimize for quality: ChatGPT’s pricing page describes Pro as “full access to the best of ChatGPT,” while Claude’s pricing page recommends Max to “get the most out of Claude.” Similarly, ChatGPT’s evaluation was run using Auto mode, a setting that allows ChatGPT’s system to determine the best-suited model variant for each prompt.
• Questions: All agents were given the same 200 business questions.
• Instructions: ChatGPT and Claude were given explicit instructions to create charts and to explain how they got to their answers. (Equivalent instructions are included in the Sales Research Agent out of box.)
• Data: ChatGPT and Claude accessed the sample dataset in an Azure SQL instance exposed through the MCP SQL connector. The Sales Research Agent connects to the sample dataset in Dynamics 365 Sales out of box.

Results are in: Sales Research Agent vs. alternative offerings

In head-to-head evaluations completed on October 19, 2025 using the Sales Research Bench framework, the Sales Research Agent outperformed Claude Sonnet 4.5 by 13 points and ChatGPT-5 by 24.1 points on a 100-point scale.

Image: Sales Research Agent – Evaluation Results

Results: Results reflect testing completed on October 19, 2025, applying the Sales Research Bench methodology to evaluate Microsoft’s Sales Research Agent (part of Dynamics 365 Sales), ChatGPT by OpenAI using a ChatGPT Pro license with GPT-5 in Auto mode, and Claude Sonnet 4.5 by Anthropic using a Claude Max license.

Methodology and Evaluation dimensions: Sales Research Bench includes 200 business research questions relevant to sales leaders that were run on a sample customized data schema. Each AI solution was given access to the sample dataset using different access mechanisms that aligned with their architecture. Each AI solution was judged by LLM judges for the responses the solution generated to each business question, including text and data visualizations.

We evaluated quality based on 8 dimensions, weighting each according to qualitative input from customers, what we have heard customers say they value most in AI tools for sales research: Text Groundedness (25%), Chart Groundedness (25%), Text Relevance (13%), Explainability (12%), Schema Accuracy (10%), Chart Relevance (5%), Chart Fit (5%), and Chart Clarity (5%). Each of these dimensions received a score from an LLM judge from 20 as the worst rating to 100 as the best. For example, the LLM judge would give a score of 100 for chart clarity if the chart is crisp and well labeled, score of 20 if the chart is unreadable or misleading. Text Groundedness and Text Relevance used Azure Foundry’s out-of-box LLM evaluators, while judging for the other six dimensions leveraged Open AI’s GPT 4.1 model with specific guidance. A total composite score was calculated as a weighted average from the 8 dimension-specific scores. More details on the methodology can be found in this blog.

The Sales Research Agent outperformed these solutions on each of the 8 quality dimensions.

Image: Evaluation Scores for Each of the Eight Dimensions

The Road Ahead: Investing in Benchmarks

The Road Ahead: Investing in Benchmarks

Upcoming plans for the Sales Research Bench include using the benchmark for continuous improvement of the Sales Research Agent, running comparisons against a wider range of competitive offerings, and publishing the full evaluation package including all 200 questions and the sample dataset in the coming months, so that others can run it themselves to verify the published results and benchmark the agents they use. Evaluation is not a one-time event. Scores can be tracked across releases, domains, and datasets, driving targeted quality improvements and ensuring the AI evolves with your business.

Sales Research Bench is just the beginning. Microsoft plans to develop eval frameworks and benchmarks for more business functions and agentic solutions—in customer service, finance, and beyond. The goal is to set a new standard for trust and transparency in enterprise AI.

Why This Matters for Sales Leaders

For business decision makers, the implications are profound:

• Accelerated Decision-Making: AI-driven insights you can trust, when delivered in real time, enable faster, more confident decisions
• Continuous Improvement: Thanks to evals, developers can quickly identify areas for highest measurable impact and focus improvement efforts there
• Trust and Transparency: Rigorous evaluation means you can rely on the outputs, knowing they’ve been tested against the scenarios that matter most to your business.

The future of sales is agentic, data-driven, and relentlessly focused on quality. With Microsoft’s Sales Research Agent and the Sales Research Bench evaluation framework, sales leaders can move beyond hype and make decisions grounded in demonstration of quality. It’s not just about having the smartest AI—it’s about having a trustworthy partner for your business transformation.

Original source Report a problem

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.

What’s not changing

• Earlier summary customizations will be honored in the new experience.
• Ability to copy the generated summary.
• Providing thumbs-up or thumbs-down feedback on summary quality.
• Using copilot sidecar chat to generate summary for any specific record.

Launch plan and next steps

The new summary experience is part of the 2025 Release Wave 2 updates for Dynamics 365 Sales:

• Early access of the new experience is available from July 2025. Opt in to early access updates.
• 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.

Original source Report a problem