It’s hard to believe, but it has already been two and a half months since this year’s Microsoft Build, where we highlighted the contributions of Microsoft MVPs in various roles in blog post Microsoft Build 2024 with MVP Communities – Microsoft Community Hub. Some people have taken the initiative to test new AI features themselves, while others have relied on community content to understand the latest technological advancements and consider how to apply them to their own businesses.

MVPs have been actively catching up with the newly announced information, writing blog posts and sharing insights on social media. They added a layer of excitement to the official releases by delivering valuable information to the community in their own words.

Microsoft Build 2024 Watch Party in the heart of New York City, United States

Peter Smulovics, a Developer Technologies MVP, hosted the Microsoft Build 2024 Watch Party in the heart of New York City, where community members gathered to deepen their knowledge together by watching the live conference.

This event allowed attendees to experience the excitement of watching the keynote address from Microsoft Build and learn about the latest announcements. They also enjoyed networking opportunities and engaged in many conversations about the newly unveiled technologies.

For those who couldn’t attend Microsoft Build in person, a Watch Party like this offers the chance to share in the spirit and excitement of this milestone event, but also connect with other tech enthusiasts locally… Check out Peter’s blog post Watching Microsoft Build in Good Company | Dotneteers.net for a recap of the event.

Microsoft Build: Developer Learning Day in London, the United Kingdom

Microsoft Build: Developer Learning Day was co-hosted with NVIDIA with over 300 attendees. The focus of the event was to share post-Build insights and viewpoints from the community and Microsoft employees.

Participants had the opportunity to deepen their knowledge of Dev Tools, Cloud Platform, AI Development, Copilot, and Azure Data & Analytics through technical sessions. Four out of the five sessions were co-presented by MVPs including Sue Bayes, Callum Whyte, Daniel Roe, and Alpa Buddhabhatti. Additionally, in the Lab space, there were two 60-minute Lab sessions offering practical learning experiences on Deep Learning and Transformer-Based Natural Language Processing. Furthermore, at the Ask the Expert Booth, MVPs interacted with participants and engaged in discussions based on their expertise.

Read the event recap posted on LinkedIn by Marcel Lupo, a Developer Technologies and Microsoft Azure MVP, who was one of the experts at the Ask the Expert Booth, here.

2024 Microsoft Build After Party & Microsoft Build 2024 – After Party with MVP in Seoul, Korea

At the Microsoft Korea office in Seoul, Korean MVPs hosted two community-led post-Build events over two days, helping enthusiastic participants learn about the latest AI technologies to enhance their knowledge.

On the first day, at the 2024 Microsoft Build After Party, five MVP/RDs shared insights on the latest Azure AI technologies with over 100 attendees through hands-on sessions, and panel discussions. They covered Copilot Studios, multi-modal generative artificial intelligence, responsible AI, low-code development, and cloud platform. On the second day, the Microsoft Build 2024 – After Party with MVP featured diverse speakers, including Microsoft Learn Student Ambassadors and community leaders, who provided new insights on emerging technologies, such as Power Platform and Microsoft 365, to the participants.

One of the MVP hosts of the Microsoft Build 2024 After Party with MVP, Inhee Lee, expressed what they were able to convey to the participants through this event, “we shared insights of the benefit of GenAI which is a disruption and democratisation of conventional technology. Anybody can access to utilise technology easily with affordable costs.”

Post Microsoft Build and AI Day in Shanghai, Beijing, and Greater Bay Area (Shenzhen and Hong Kong)

In collaboration with Microsoft Asia and Microsoft Reactor, and 16 technology communities, the Post-Microsoft Build and AI Day event series was held in June 2024. The three events in Shanghai, Beijing, and the Greater Bay Area (Shenzhen and Hong Kong) attracted significant interest from those eager to learn about the latest AI solutions. Over 400 participants attended the events in person, and online streaming reached more than 140,000 viewers.

This series of hybrid events offered opportunities to learn about the latest technology topics announced at Microsoft Build, including Azure AI, .NET, Copilot, Power Platform, Azure OpenAI, LLM, SLM, Data Analytics and Integration, and edge computing. 11 MVPs participated as speakers, providing technical insights and engaging in discussions with attendees at the booths, enhancing the event experience for both in-person and online participants.

The event in Shanghai coincided with Children’s Day, leading to a special “Hour of Code · Children’s Day Edition.” Hao Hu, an AI Platform MVP, conducted an AI hands-on workshop themed around marine conservation for children. This initiative demonstrated how AI can be utilized across different generations.

Microsoft Build Japan 2024 – Virtual event from Tokyo, Japan

As an opportunity for Japanese-speaking users to learn the latest technologies announced at Microsoft Build, Microsoft Japan held Microsoft Build Japan 2024. Eight MVPs contributed to this two-day virtual event as speakers. On Day 1, four MVPs shared important updates on Azure AI and developer-focused topics. On Day 2, another four MVPs covered Microsoft 365, including Copilot, as well as the latest devices such as Copilot+ PC and Surface.

Tomokazu Kizawa participated as a speaker at a Microsoft-hosted event for the first time. Reflecting on his experience and the key messages he wanted to convey to the participants, he shared his thoughts: “From my perspective as a user outside of Microsoft, I focused on specifically conveying how new technologies like Copilot+ PC can positively impact daily life and work. Additionally, I aimed to highlight the positioning of Surface and the technological trends of Copilot+ PC not only from Microsoft’s standpoint but also within the broader PC industry, in order to generate more interest in Windows Devices.”

You can watch the session videos from this event, including the presentations by the Microsoft MVPs, at the following link.

Microsoft Build Japan 2024 – YouTube

– MVP session Day 1: Microsoft MVP による “推し最新技術情報” Azure/AI + Dev 編 (youtube.com)

– MVP session Day 2: Microsoft MVP による “推し最新技術情報” Microsoft 365 + Windows Device 編 (youtube.com)

Starting November 19, another major Microsoft global conference, Microsoft Ignite, is set to take place both in Chicago and online. It’s exciting to think about the innovative technology announcements that will be revealed in just three months. If you’d like to stay updated on the latest conference information, we recommend signing up for email notifications via the [Join the email list] link on the official page (note: this is not for event registration).

Also, be sure to look forward to learning opportunities provided by the Microsoft MVP community during and after the Microsoft Ignite event!

——

To learn more about Microsoft Build, please visit the following websites.

Microsoft Build (Official website)

Microsoft Build 2024 Book of News (Announcements)

Build on Microsoft Learn (Microsoft Learn)

Microsoft Build 2024 (Playlist on Microsoft Developer YouTube)

The top 5 Microsoft MVP demos presented at this year’s event are now available on the Microsoft Developer YouTube channel.

– Extend your Copilot with plugins using Copilot Studio by M365 MVP Manpreet Singh

– Create a fully functional support bot in less than 10 minutes by Business Applications MVP Em D’Arcy

– Golden path with GitHub Actions by Microsoft Azure MVP/Regional Director Michel Hubert

– Optimize Azure Infrastructure as Code Deployments with VS Code by Windows and Devices, Microsoft Azure MVP

Freek Berson

– AI-Powered Personalized Learning by AI Platform MVP Noelle Russell

​Microsoft Tech Community – Latest Blogs –Read More 

Customer service is undergoing an AI revolution, driven by the demand for smarter, more efficient solutions. HyDE-powered RAG chatbots offer a breakthrough technology that combines vast knowledge bases with real-time data retrieval and hypothetical document embeddings (HyDE) to deliver superior accuracy and context-specific responses. Yet, building and managing these complex systems remains a significant challenge due to the intricate integration of diverse AI components, real-time processing requirements, and the need for specialized expertise in AI and data engineering.

Simplifying GenAI solutions with Microsoft and Dataloop

The Microsoft-Dataloop partnership abstracts the deployment of powerful chatbot applications. By integrating Microsoft’s PHI-3-MINI foundation model with Dataloop’s data platform, we’ve made HyDE-powered RAG chatbots accessible to a wider developer community with minimal coding. Developers can leave the documentation behind and start utilizing these capabilities instantly, accelerating time to value.

This announcement follows our successful integration with Microsoft Azure AI Model as a Service and Azure AI Video Indexer, further enhancing our ability to deliver advanced AI solutions. These integrations enable developers to seamlessly incorporate state-of-the-art AI models into their workflows, significantly accelerating development cycles.

About Dataloop AI development platform

Dataloop is an enterprise-grade end-to-end AI development platform designed to streamline the creation and deployment of powerful GenAI applications. The platform offers a comprehensive suite of tools and services, enabling efficient AI model development and management.

Key features include:

Orchestration: Dataloop provides seamless pipeline management, access to a marketplace for AI models, and a serverless architecture to simplify deployment and scalability.
Data Management: The Dataloop platform supports extensive dataset exploration, allowing users to query, visualize, and curate data efficiently.
Human Knowledge: Dataloop facilitates knowledge-based ground truth creation through tools for annotation, review, and monitoring, ensuring high-quality data labeling.
MLOps: With reliable model management capabilities, Dataloop ensures efficient inference, training, and evaluation of AI models.

Dataloop is also available on Azure Marketplace.

About Azure AI Models as a Service

Azure AI Models as a Service (MaaS) offers developers and businesses access to a robust ecosystem of powerful AI models. This service includes a wide range of models, from pre-trained and custom models to foundation models, covering tasks such as natural language processing, computer vision, and more. The service is backed by Azure’s stringent data privacy and security commitments, ensuring that all data, including prompts and responses, remains private and secure.

Add photo pink screen

Figure: HyDE-powered RAG Chatbot Workflow – This pipeline, created using the Dataloop platform, demonstrates the process of transforming user queries into hypothetical answers, generating embeddings, and retrieving relevant documents from a vector store. This internal Slack chatbot is optimizing information retrieval to ensure that users receive accurate and contextually relevant responses, enhancing the chatbot’s ability to search for answers in the documentation.

This is how we do it!

Powering Efficient AI Inference at Scale: Microsoft’s AI tools build upon a powerful foundation of inference engines like Azure Machine Learning and ONNX Runtime. This robust toolkit ensures smooth, high-performance AI inferencing at scale. These tools specifically fine-tune neural networks for exceptional speed and efficiency, making them ideal for demanding applications like large language models (LLMs). This translates to rapid inference and scalable AI deployment across various environments.

End-to-End AI Development with Drag-and-Drop Ease: Dataloop empowers users to build and manage advanced AI capabilities entirely within its intuitive no-code interface. Simply drag and drop models provided or developed by Microsoft through our marketplace to seamlessly integrate them into your workflows. Pre-built pipeline templates specifically designed for RAG chatbots further streamline development. This eliminates the need for additional tools, making Dataloop your one-stop shop for building next-generation RAG-based chatbots.

A Node-by-Node Look at a RAG-based Document Assistant Chatbot with Microsoft and Dataloop

This section takes you behind the scenes of our RAG-based document assistant chatbot creation, utilizing Microsoft’s AI tools and the Dataloop platform. This breakdown will help you understand each component’s role and how they work together to deliver efficient and accurate responses. Below is a detailed node-by-node explanation of the system.

Node 1: Slack (or Messaging App) – Prompt Entry Point

Description: This node acts as the interface between users and the chatbot system. It integrates with a messaging platform like Slack and receives user interactions (messages, queries, commands) and starts the pipeline.

Functionality: It captures and processes the user input to be forwarded to the predictive model.

Configuration:

Integration:

  Specify the target messaging platform (e.g., Slack API token, login credentials for other messaging apps).
  Define event types to handle (e.g., messages, direct mentions, specific commands).

Message Handling:

  Define how to pre-process messages (e.g., removing emojis, formatting, language detection).
  Configure how to identify user intent and extract relevant information from the message.

Node 2 – PHI-3-MINI – Predict Model

Description: This node utilizes a generative prediction model, PHI-3-MINI, optimized with Microsoft’s AI tools.

Functionality: The node takes input from the Slack node and generates hypothetical responses. Research in Zero-Shot Learning suggests that this approach, leveraging contextual understanding and broad knowledge, can often outperform traditional methods.

Configuration:

Model Selection: Choose any LLM optimized using Microsoft’s AI tools. In our chatbot, we leverage PHI-3-MINI, specifically optimized for efficient resource usage.
System Prompt Configuration: A system prompt guides the AI’s behavior by setting tone, style, and content rules, ensuring consistent, relevant, and appropriate responses. For our case, we configure the LLM to give a hypothetical and concise answer.
Parameters: Set parameters for the model (e.g., beam search size, temperature for sampling).

Node 3 – Embed Item

Description: This node is responsible for embedding items, transforming text or data into a format that can be easily used for further processing or retrieval.

Functionality: It generates vector embeddings from the text. These embeddings represent the text in a high-dimensional space, allowing for efficient similarity searches in the next node.

Configuration:

Embedding Model: Choose the model for generating vector embeddings from text (e.g., pre-trained Word2Vec, Sentence Transformers). You can also utilize Microsoft’s embedding tools. Each embedding model comes with its own dimensionality of the vectors.
Normalization: Specify the normalization technique for the embeddings (e.g., L2 normalization).

Node 4 – Retriever Prompt (Search)

Description: This node acts as a retrieval mechanism, responsible for fetching relevant information or context based on the embedded item.

Functionality: It uses the embeddings to search a database or knowledge base, retrieving information that is relevant to the query or input provided by the user. It could use various retrieval techniques, including vector searches, to find the best matching results.

Configuration:

Dataset: Specify your dataset, with all the existing chunks and embeddings.
Similarity Metric: Define the metric for measuring similarity between the query embedding and candidate items (e.g., cosine similarity, dot product).
Retrieval Strategy: Choose the retrieval strategy. In our case, we used our feature store based on SingleStore, a database optimized for fast searches. This allows for efficient vector-based search to quickly retrieve the most relevant information.

Node 5 – PHI-3-MINI – (Refine)

Description: Similar to the earlier PHI-3-MINI node, this node also involves a predictive model, another instance of the PHI-3-MINI model optimized by Microsoft.

Functionality: Processes the retrieved information using the predictive model to generate a response or further refine the data, ensuring a contextually accurate output for the user.

Configuration: Model Selection: Specify another instance of the PHI-3-MINI model optimized with Microsoft’s AI tools.

Task Definition: Instruct the model to take all chunks of documentation and reply accurately to the user’s question.
System Prompt Configuration: Instruct the chatbot on how to respond. In our case, we configured it to respond kindly, act as a helpful documentation assistant, clearly state when it doesn’t know an answer, and avoid inventing information.

Accelerate AI Development with Dataloop’s Integration of Microsoft Foundation Models

Discover a vast ecosystem of pre-built solutions, models, and datasets tailored to your specific needs. Easily filter options by provider, media type, and compatibility to find the perfect fit. Build and customize AI workflows with easy-to-use pipeline tools and out-of-the-box end-to-end AI and GenAI workflows. We are incredibly excited to see what you can create with your new capabilities!

​Microsoft Tech Community – Latest Blogs –Read More 

Dears, I’ve some important questions please

Is there any option to programmatically select Tables to Sync from finance and operations, currently it’s a manual process and time-consuming task? We’re open to any tool: PowerShell, Python, Power Automate & etcIs there any option to force the sync to start without waiting the interval settings in the advanced configuration?

Choose finance and operations data in Azure Synapse Link for Dataverse – Power Apps | Microsoft Learn

​Dears, I’ve some important questions pleaseIs there any option to programmatically select Tables to Sync from finance and operations, currently it’s a manual process and time-consuming task? We’re open to any tool: PowerShell, Python, Power Automate & etcIs there any option to force the sync to start without waiting the interval settings in the advanced configuration?   Choose finance and operations data in Azure Synapse Link for Dataverse – Power Apps | Microsoft Learn   Read More

​

Hi everyone, we are experiencing an issue where the “Reply-To” header in emails sent to our Exchanged hosted email account is being stripped. This behaviour started on the 7th of August, seemingly for reasons we haven’t been able to isolate.

Our current set up is that we have one primary email address that we receive all of our customer enquiries, orders, and emails through for 15+ websites. This email address is hosted through Exchange and we have set up SMTP. Our website is a WordPress based website, and we use WP Mail SMTP to connect our Exchange account to this plugin. Then, we filter this email account through MailGuard so that we mitigate 99% of the spam sent to that address.

Originally, we thought the problem was to do with this plugin, so we rolled back a version of the plugin and the issue was still not rectified. We also reached out to MailGuard asking them if they would strip Reply-To headers before they sent the email(s) back to us, and their reply from support was:

“We will add details into the headers of an email, but that will be in regards to recording the Hops of the email, whether it has passed SPF/DKIM/DMARC checks and specific logging regarding tour processing of the email. 
That all being said, MailGuard’s systems do not remove content from emails. 
 
If the emails do not have a reply-to in them, that is how they are when we have received them.”

As mentioned, we have 15+ other websites, but only 2 of them run through an OAuth connection with Exchange through the WP Mail SMTP plugin. The other websites, use Brevo (SendInBlue) as their SMTP provider. 

Thinking it was a plugin issue, we tested the enquiries being sent from those websites to our email address, to see if they were also getting their Reply-To headers stripped, however, none of them were having this issue. We use the free SMTP service through Brevo for these smaller sites, and would exceed their limit if we switched our main sites to Brevo in the meantime.

We believe we have isolated the issue down to Exchange/Office365, but admittedly, are finding it a bit of a challenge given the intricate settings and options available throughout the account. 

Below is a screenshot of two enquiries sent through to our email address, but 24 hours apart. The left indicates the the Reply-To header is present as normal, but the right image, indicates a missing Reply-To header. 

To add a note, it is interesting saying that the emails were not signed. We definitely have DMARC/DKIM DNS records present so I’m unsure why they would be being delivered as unsigned.

We have not changed any SMTP settings, any policy settings, mail rules or anything similar in our Exchange account. It seemingly appears to be an issue that randomly appeared overnight. 

Has anyone experienced similar issues with “Reply-To” headers being stripped in Office 365? Could there be specific settings or policies in Exchange Online or Azure that might affect this behaviour? Any advice or troubleshooting tips would be greatly appreciated.

Thank you in advance for your help. 

​Hi everyone, we are experiencing an issue where the “Reply-To” header in emails sent to our Exchanged hosted email account is being stripped. This behaviour started on the 7th of August, seemingly for reasons we haven’t been able to isolate. Our current set up is that we have one primary email address that we receive all of our customer enquiries, orders, and emails through for 15+ websites. This email address is hosted through Exchange and we have set up SMTP. Our website is a WordPress based website, and we use WP Mail SMTP to connect our Exchange account to this plugin. Then, we filter this email account through MailGuard so that we mitigate 99% of the spam sent to that address. Originally, we thought the problem was to do with this plugin, so we rolled back a version of the plugin and the issue was still not rectified. We also reached out to MailGuard asking them if they would strip Reply-To headers before they sent the email(s) back to us, and their reply from support was: “We will add details into the headers of an email, but that will be in regards to recording the Hops of the email, whether it has passed SPF/DKIM/DMARC checks and specific logging regarding tour processing of the email. That all being said, MailGuard’s systems do not remove content from emails.  If the emails do not have a reply-to in them, that is how they are when we have received them.” As mentioned, we have 15+ other websites, but only 2 of them run through an OAuth connection with Exchange through the WP Mail SMTP plugin. The other websites, use Brevo (SendInBlue) as their SMTP provider.  Thinking it was a plugin issue, we tested the enquiries being sent from those websites to our email address, to see if they were also getting their Reply-To headers stripped, however, none of them were having this issue. We use the free SMTP service through Brevo for these smaller sites, and would exceed their limit if we switched our main sites to Brevo in the meantime. We believe we have isolated the issue down to Exchange/Office365, but admittedly, are finding it a bit of a challenge given the intricate settings and options available throughout the account.  Below is a screenshot of two enquiries sent through to our email address, but 24 hours apart. The left indicates the the Reply-To header is present as normal, but the right image, indicates a missing Reply-To header.   To add a note, it is interesting saying that the emails were not signed. We definitely have DMARC/DKIM DNS records present so I’m unsure why they would be being delivered as unsigned. We have not changed any SMTP settings, any policy settings, mail rules or anything similar in our Exchange account. It seemingly appears to be an issue that randomly appeared overnight.  Has anyone experienced similar issues with “Reply-To” headers being stripped in Office 365? Could there be specific settings or policies in Exchange Online or Azure that might affect this behaviour? Any advice or troubleshooting tips would be greatly appreciated. Thank you in advance for your help.   Read More

​

Hello,

Trying to delete contacts from People. Checked the checkboxes on my contacts whom I want to delete from People.

Also tried to delete one by one at a time.

Then, for former way, the dust box icon is grey out.

For latter way, dust box appears, however, some particular contacts show the error message and says “Issues and cannot delete.” The screeshot of the error message is as follows. 

It appeared at the event when I deleted the contact in my People.

It says that “problem happened. Due to the problem, unable to delete.” Cancel in blue highlighted

Please advise how to delete contacts in People.

　https://people.live.com

​Hello,Trying to delete contacts from People. Checked the checkboxes on my contacts whom I want to delete from People.Also tried to delete one by one at a time.Then, for former way, the dust box icon is grey out.For latter way, dust box appears, however, some particular contacts show the error message and says “Issues and cannot delete.” The screeshot of the error message is as follows. It appeared at the event when I deleted the contact in my People.It says that “problem happened. Due to the problem, unable to delete.” Cancel in blue highlighted Please advise how to delete contacts in People.　https://people.live.com   Read More

​