The Sales Qualification Agent (SQA) in Dynamics 365 Sales introduces a new class of autonomous sales AI, one that does far more than assist with drafting or summarization. SQA performs multi-step reasoning, conducts live web research, generates personalized outreach, and engages prospects in multi-turn qualification conversations. These capabilities directly shape pipeline quality, seller productivity, and customer relationships. 

As agentic AI becomes deeply embedded in revenue-critical workflows, trust must be earned through transparent, repeatable, and rigorous evaluation—not anecdotal wins or point demos.

Today, we’re announcing the Microsoft Sales Bench—a collection of evaluation benchmarks designed to assess the performance of AI-powered sales agents across real-world scenarios. Adding to the Sales Research Bench already published as part of this collection to evaluate Sales Research Agent, today we are also publishing the Sales Qualification Bench to evaluate Sales Qualification Agent in Dynamics 365 Sales.

This post presents the detailed evaluation methodology and results for the agent, including a head-to-head comparison against chatGPT using identical data, tasks, and scoring rubrics. These efforts establish the first benchmark purpose-built to measure end-to-end sales agent workflows, from research to outreach to live qualification. 

SQA Architecture  

The Dynamics 365 Sales Qualification Agent (SQA) architecture is designed as an end-to-end, enterprise-grade AI system that autonomously researches leads, synthesizes insights, and generates seller-ready outreach. It combines an intelligence engine powered by large language models with iterative web and enterprise data research, tightly integrated with Dynamics 365 Sales and Microsoft Copilot Studio for orchestration. Built on secure enterprise foundations, the architecture enforces governance, compliance, and data protection while enabling scalable, trustworthy AI-driven sales workflows. 

Evaluation Metrics and Methodology 

To understand how well the Sales Qualification Agent (SQA) performs in real-world sales qualification workflows, we designed the Sales Qualification Bench, a comprehensive evaluation that mirrors how sellers actually research leads, personalize outreach, and engage with prospects. Our goal was straightforward: measure whether SQA can help reps qualify faster, personalize more effectively, and carry higher-quality customer conversations—using the same signals and information they rely on every day. 

To ensure that the evaluations accurately represent real-world conditions, we developed a testbed that closely mirrors the complexity and ambiguity found in contemporary sales environments. This allowed us to evaluate SQA end to end, from autonomous research and reasoning to grounded, actionable research briefs, outreach messages, and multi-turn qualification conversations. 

Evaluation Setup

To ensure real-world fidelity, we constructed a production-like lead evaluation environment that mirrors how SQA operates in Dynamics 365 Sales. 

Lead and Data Corpus 

• Three synthetic but realistic seller companies (C1) across distinct industries, with unique: 
  • Product offerings 
  • Knowledge sources 
  • Ideal customer profiles 

• 300+ lead dataset (C2) expanded into a scenario-rich corpus: 
  • Companies across 6 global regions (North America, Europe, Asia, South America, Australia, Africa) 
  • 33 industries 
  • Mixed clarity (well-known brands and long-tail companies) 
  • Structured attributes (name, role, email) 

• CRM roles represented: 
  • Sales representatives 
  • Digital specialists 
  • Customer success managers 
  • Each linked to relevant accounts, opportunities, and cases 

• Company segment coverage: 
  • Enterprise 
  • Mid-Market 
  • Small Business 
  • Government 
  • Education 

• 500+ email exchanges simulating real sales interactions: 
  • Technical product questions 
  • Meeting requests 
  • Ambiguous or low-intent inquiries 

Simulated Agent Workflows 

All evaluations reflected real SQA behavior: 

• Autonomous web-based research 

• Role-aware outreach generation 

• Multi-turn qualification conversation handling 

Tasks Evaluated and Evaluation Metrics 

1. Company Research 

For each lead, the agent generates a structured research brief including: 

• Business overview, strategy and priorities 

• Financial signals 

• Recent news relevant to the seller 

2. Lead Outreach 

Based on its research, the agent generated a personalized email aligned to: 

• The lead’s role 

• The seller’s value proposition 

• The company’s business context 

• Value-based positioning 
   

3. Qualification Conversations (Engage) 

The agent then autonomously engages back and forth with the lead, progressively asking them questions for customer-configured qualification criteria such as budget, need, and timeline and answering the lead’s questions such as: 

• “What does your solution do?” 

• “How are you priced?” 

• “How do you compare to competitors?” 

• “Who else uses this?” 

Each metric is scored independently on a 0–10 scale, where higher scores indicate stronger performance. We used an LLM-as-a-judge approach to score outputs against the ground truth and rubric and manually reviewed a sampled subset of evaluations to calibrate the judges and validate scoring consistency. To reduce judge variance and mitigate hallucination risk, each sample was evaluated five times, and the mean across runs was recorded as the final score. 

Benchmarking Strategy with ChatGPT 

To ensure an objective and fair comparison, we replicated a standard seller workflow in ChatGPT UI using GPT-4.1 with Pro license, a more advanced model than the GPT-4.1-mini variant currently used by SQA. 

Standard Prompting 

This setup simulates how a seller naturally interacts with a general-purpose LLM: 

• High-level contextual instructions only 
• Mirrors SQA’s autonomous research-to-outreach flow 

This ensures: 

• Workflows remain representative and unbiased 
• Comparisons reflect real-world usability, not prompt-engineering skill 

Identical Knowledge Sources and Context 

ChatGPT was given the exact same knowledge sources as SQA, including: 

• Full lead information and seller value proposition 
• Seller Q&A documentation via the SharePoint connector 
• Historical conversation context for reply generation 

This isolates differences in agent reasoning and orchestration, not data access. 

Evaluation Results  

Microsoft evaluated the Sales Qualification Agent (SQA) and ChatGPT with over 300 leads, covering research, outreach, and qualification tasks with identical knowledge sources. Evaluations completed on December 4, 2025, showed that SQA consistently outperformed ChatGPT-4.

• Research: SQA was 6% more effective at relevant, thorough company research. 
• Outreach: SQA was 20% better at personalized communication and timely event references. 
• Engagement: SQA scored 16% higher for precise responses and targeted qualifying questions. 

SQA also operates autonomously, reducing overhead and boosting pipeline quality for sales teams. 

Results by Task Category 

1. Company Research 

SQA was 6% better than ChatGPT, winning in its ability to perform more relevant and complete research that highlighted the lead company’s interest in the sellers offerings: 

• SQA provided more relevant results: To ensure sellers spend their time on the most important leads, they need to determine whether a lead is good fit for their offerings. While both SQA and ChatGPT were given the same context (seller company and value proposition of the offerings), SQA consistently did better at tying its research back to this context, helping sellers determine fit. Appendix A shows an example where SQA was able to tie the company’s strategic priorities to its need for a collaboration platform and infer strong purchase ability from its robust operational health and minimal leverage burden.

• SQA synthesized results with higher level of fidelity and completeness: The agent’s value is directly correlated to its ability to eliminate tedious work for the seller. SQA produced more detailed research synthesis (as demonstrated in Appendix A), giving a single, trusted source for the seller to get equipped with any insights they may need.  

These results stem from numerous experiments aimed at optimizing web research for the best outcomes at minimal cost, rather than relying on costly advanced models. Sellers get deeper insights with SQA’s agentic RAG for real-time reasoning with iterative web search results, combined with unique capabilities that increase data coverage, for example, auto-linking CRM records and extraction of company name from lead emails. 

2. Personalized Outreach 

SQA was 20% better than ChatGPT, notably ahead in the level of personalization and mentions of relevant recent events that will resonate with the lead. 

• More personalized and customer-centricity: A lead is more likely to respond to a cold outreach email that directly explains how the seller’s offering can address their needs. SQA did so effectively by starting with the lead’s situation and recent events, while ChatGPT often focused on the seller and uses heavier technical jargon. A clear, actionable call to action bookends the email and guides the conversation forward. Appendix B shows an example of how SQA was able to tie a recent acquisition the lead’s company made to the value proposition of the seller’s offering. 

These results are based on direct engagement with sellers – every sales team that deploys SQA gives us precious feedback that all other customers benefit from.   

3. Qualification Conversations (Engage) 

SQA was 16% better than ChatGPT. It responded with greater precision to the lead’s questions to develop purchase interest and asked pointed discovery questions to better qualify the lead before handing off to a seller. 

• Answers accurately by correctly understanding the lead’s intent and maintaining conversation context effectively. To drive deeper buyer consideration, SQA independently answered even the most technical questions that leads had about the seller’s offerings while maintaining the context from earlier messages in the simulated conversation, delivering clear, direct, and well-structured responses. Appendix C demonstrates SQA’s ability to pull the most relevant information from provided knowledge sources (in this case, files with technical specifications) during an ongoing conversation with a lead. 

• Handles uncertainty responsibly, handing off to a supervisor/seller when appropriate. Both SQA and ChatGPT were instructed to handoff a lead to a supervising seller when a suitable response cannot be generated or when the lead is considered qualified as per pre-defined criteria. SQA handed off accurately and at the right moment in more tests than ChatGPT.  

• Demonstrates strong discovery coverage. To maximize the value exchange from each follow-up conversation with the lead, SQA and ChatGPT were instructed to include discovery questions in their response to assess pre-configured qualification criteria (covering lead’s need, budget, buying authority and purchase timeline). SQA was able to ask pointed discovery questions to cover more of these criteria than ChatGPT in our simulated conversations. This resulted in SQA identifying and handing off better qualified leads through its engagement.

These gains are attributable to the hard lessons we have learnt through close collaboration with customers to understand the diversity of needs on intent detection and knowledge retrieval across AI agents for Dynamics 365 Sales, Service and Contact Center applications.  

Conclusion 

Sales Qualification Agent (SQA) is not a simple productivity tool—it is a complex multi-step agent directly influencing revenue outcomes. The Sales Qualification Bench represents a foundational step toward enterprise-grade trust, transparency, and continuous quality improvement for agentic AI in sales. 

Through rigorous, scenario-driven benchmarking, SQA demonstrated clear leadership across research, outreach, and qualification—while also surfacing concrete architectural and rule-quality investments for the next phase of growth. 

Upcoming plans for the Sales Qualification Bench include using the benchmark for continuous improvement of the Sales Qualification Agent, running further comparisons against a wider range of competitive offerings, and publishing the eval package so customers can reproduce it on their own data. Evaluation is not a one-time event. It is now embedded as a first-class engineering discipline in the SQA development lifecycle—ensuring the agent evolves safely, measurably, and in lockstep with seller needs. 

Appendix

Sample inputs and responses for each category  

Appendix A. Sample of research synthesis generated by SQA

Appendix B. Sample of an initial outreach email generated by SQA 

Appendix C. Sample of an engagement email generated by SQA 

The post Sales Qualification Agent: How we evaluated and improved AI quality with benchmarks appeared first on Microsoft Dynamics 365 Blog.

In today’s world, sellers struggle to meet their goals due to competing priorities, manual processes and increased customer expectations. Most spend their time on administrative and non-selling tasks. However, it’s now the age of AI. Agents help free up sellers’ time to focus on higher value activities, engaging customers and moving them through sales cycles faster. For example, the recently announced Sales Qualification Agent (available soon in Microsoft Dynamics 365 Sales) automatically researches and prioritizes inbound leads and develops personalized sales emails to initiate sales conversations.  

This week at Microsoft Ignite, we announced new capabilities to further enhance agents in Dynamics 365 Sales by grounding them in your company’s unique data and taxonomy, as well as enriching the agents’ knowledge with third-party data. This allows the agent to assess a lead’s intent to buy with greater precision, while saving sellers precious time they may currently spend piecing together information from disparate sources. These capabilities will be rolling out in early 2025. 

Enhance Copilot and agents with your business terminology and knowledge sources 

Organizations will be able to enhance their interactions with Copilot and agents by training them to understand and use specific business acronyms and terms through a customized glossary. This means tailoring AI to the unique language and terminology of a particular business or industry, improving interactions with Copilot and enabling agents to perform tasks on your behalf with higher relevancy. 

For example, if a company frequently uses the acronym “TCV” to refer to “total contract value,” they can train the agent to recognize and use this term instead of the more generic “estimated revenue for opportunities.” This customization ensures that the agent’s work aligns with the company’s internal language, improving communication and reducing misunderstandings. 

Additionally, organizations will be able to add various knowledge sources to Copilot and agents, such as documents created in Word or Excel, files from SharePoint and tables from databases and lake houses such as Microsoft Fabric or Azure SQL, to complement the Sales data in Dataverse. Agents are built on Microsoft Copilot Studio, which announced new knowledge integrations this week at Ignite and will continue expanding the portfolio–meaning access to even more options over time. This allows the agent to leverage the full power of your organizational data, no matter where it is stored or which apps you use. 

By incorporating a business-specific glossary and relevant knowledge sources, the agent becomes more powerful, capable of understanding and responding in a way that is consistent with the company’s unique terminology and data needs. 

Enrich your CRM with data from third party enrichment providers  

Integrations with third-party data providers and Dynamics 365 Sales, as listed on AppSource, provide data and insights to augment the agents’ customer understanding beyond conventional sources.  

We announced a new data integration with Clay, a leading enrichment and orchestration provider. Clay combines first-party data with over 100 enrichment providers and an AI research agent, maximizing data coverage to create a more comprehensive view of the customer.  

Through the integration between Microsoft and Clay, Dynamics 365 Sales customers can add insights that would typically not be available in first party sources, such as valuation of private companies, headcount, key competitors and more. With these additional insights seamlessly synced back to Dynamics 365 Sales, agents can perform tasks with more precision, such as identifying leads that fit your ideal customer profile or their intent to buy. 

We’ve designed this integration to be user-friendly and efficient. Here’s how it works: 

Setting Up Connection: You can easily connect Dynamics 365 Sales to Clay using the out-of-the-box integration and select the specific data tables and fields you want to enrich. 

Populating Insights: Once set up, you can enrich your selected Dynamics tables with a variety of insights that can help your sales teams – either from one of 100+ data providers or from scraping public web sources through Clay’s AI agent. 

Automatic Synchronization: The enriched data is then synchronized back to Dynamics 365 Sales automatically, ensuring that your agents always have access to accurate and up-to-date information. 

Clay joins other integrations already available on Microsoft’s AppSource that can similarly augment your first party data. While data-hungry autonomous agents in Dynamics 365 Sales work tirelessly on behalf of your sales team to reduce time spent while increasing the number of closed deals, these integrations feed unique insights to them to power even the most complex sales playbooks. 

Summary 

In summary, you can customize your agent to meet your business needs by integrating relevant data sources that are bespoke to your business.  You can configure the agent to use your business-specific terminology and response styles, ensuring it aligns with your internal language. Finally, enrich your data with one of the many data enrichment integrations and ensure a perfectly optimized agent for your requirements.  

Take the next step 

Today’s sellers need the right data and tools to find, qualify, and close deals – all while offering personalized engagement at every step. The innovations introduced this week at Microsoft Ignite can not only help sellers with time-consuming sales activities but also provide access to actionable insights and superior agent performance to build stronger customer relationships and win more business. 

To learn more about these updates and how they can benefit your organization, be sure to explore the resources below: 

• Check out the recorded session on Dynamics 365 Sales from Ignite 

• Learn more about Clay for Dynamics 365 Sales  

• Learn more about Dynamics Sales 

• Not yet a Dynamics 365 Sales customer? Take a tour and start your free trial today. 

The post Customize Dynamics 365 Sales Agents with your data sources and taxonomy appeared first on Microsoft Dynamics 365 Blog.

The world is getting noisier, which makes it harder to earn customer attention. We’ve previously described the importance of hyper-personalization to break through the noise and enable customers to explore brands and products on their own terms. Regardless of whether they are consumers or business-to-business (B2B) buyers.

At Ignite 2023, we announced a unique Copilot-powered real-time web personalization solution in Dynamics 365 Customer Insights in partnership with Optimizely*. Today, we’re excited to announce the availability of this solution in preview to customers worldwide. Current Customer Insights customers can sign up now to access the public preview.

_{*To use Optimizely with Dynamics 365 Customer Insights you need to acquire a license for Optimizely Web Experimentation}

The state of web personalization today 

According to recent research from Econsultancy, 93% of businesses see an uplift in conversion rates because of personalization. Yet only 6% of businesses believe they are doing it well. They face three main challenges.

First, traditional tools for personalization have limited data about your customers. It’s no longer sufficient to show content based on a customer’s browsing history, location, and other derived signals alone. The shift away from 3^rd party cookies further exacerbates this problem.

Second, even the companies that have collected a wealth of data through their Customer Data Platform (CDP) often struggle to synchronize the customer identity and data between their CDP and personalization tools. This synchronization is essential for real-time personalization. It enables companies to use comprehensive customer understanding from all data sources unified in CDP to tailor experiences based on both current behavior and predicted actions.

Third, personalization is disconnected across channels due to the fragmentation of marketing and web technologies and the data silos within each tool. A customer might see one offer option on the web but get a different message in an email or through an ad on social media. With companies expanding the channels through which they engage with users, it becomes increasingly challenging to connect the dots of a customer’s journey.

Dynamics 365 Customer Insights to the rescue

Dynamics 365 Customer Insights and Optimizely* enable organizations to deliver hyper-personalized omni-channel experiences across web, social, email and offline channels without writing custom code. Marketers and web admins can seamlessly collaborate to create personalized campaigns using unified data from Customer Insights. This enables companies to:

1. Go beyond browsing history by using comprehensive data from Customer Insights to personalize experiences. For example, leverage the predicted lifetime value of a customer to create targeted experiences.
2. No-Code Personalization using segments from Customer Insights in Optimizely. For instance, create a segment for high-churn customers in Customer Insights and use it in Optimizely to increase engagement when they visit the website next.
3. Ensure uniform personalization across all channels with bi-directional integration between Customer Insights and Optimizely. For example, an audience in Optimizely can be created using the predicted lifetime value from Customer Insights and repeat browsing history from Optimizely. This audience can then receive targeted monetary offers. Marketers can also show the same offer in messages sent via a customer journey in Customer Insights, using Optimizely’s signal (activity) on which treatment they received earlier. This can be done through segments refined based on customer activities or real-time triggers based on specific customer actions.

4. Activate audience across channels in journeys to further target the original visitors with the same offer if the prior web and message touchpoints failed to convert them and export the segments into advertising and social platforms for re-targeting.

There are even more possibilities for customer experience teams. They can, for example, use defined audiences to create ‘lookalike’ segments on social media platforms. This strategy helps them identify and engage new potential customers who share characteristics with their existing audience, expanding their reach and intensifying customer engagement efforts.

“Copilot in Customer Insights and Optimizely not only enable hyper-personalization but democratize it-any marketing or Customer experience team can now deliver such a campaign quickly and without requiring specialized skills – creating segments, journeys and content with the help of Copilot and then setting up the experiments with Optimizely’s market-leading capabilities.”

Kevin Li, VP of Product Strategy at Optimizely.

Leveraging website personalization to accelerate B2B sales

Web personalization can boost B2B sales by showing the right product to the right customer at the right time. CommScope, a leading telecommunication and wireless network company, uses web personalization to increase purchase intent for web visitors and then routes them to a seller based on their cross-channel engagement. This way, CommScope can generate higher quality leads and revenue from its website.

“Customer Insights and Optimizely enable us to personalize each customer’s experience in real-time with consistency across website and email marketing, enabling self-exploration and demand generation, while also accelerating our sales pipeline by empowering our reps to identify the highest intent leads at the right moment.“

Bob Vonderheide, Director of Customer Experience Technologies at CommScope.

What’s next 

This is just the beginning, and there’s much more to come. Working with early adopters, we know that our customers often rely on their marketers and developers collaborating to add scripts to their websites and mobile apps. We will facilitate this collaboration with a developer portal that gives developers tools to test and verify that the script has successfully been added and functioning as the marketer intended. To enable bespoke scenarios such as personalized e-commerce product pages, we will enable collection of custom events including data such as product details, category, and price. Finally, we will reduce noise from unwanted events through filtering based on pages, location, and other attributes. You can follow the release plans to stay updated on when these features become available.

Meanwhile, we will continue to work with customers as part of the preview to measure and optimize real-world latency and performance. We estimate general availability beyond 2024 wave 2 with the enhancements outlined above.

Learn more about Dynamics 365 Customer Insights

• To learn more about Dynamics 365 Customer Insights explore Dynamics 365 Customer Insights.
• Watch the video to discover how Optimizely enable web personalization with our Contoso scenario.
• Leverage all our new AI innovations for Dynamics 365 Customer Insights – Journeys by transitioning to real-time marketing.
• Get a full view of what is coming in 2024 release wave 1 release plan for Dynamics 365 Customer Insights.
• Get Optimizely Optimizely is a third-party app which requires a subscription.

The post Omni-channel real-time personalization with Dynamics 365 Customer Insights and Optimizely appeared first on Microsoft Dynamics 365 Blog.