Tag: ai

Exam AB-731: AI Transformation Leader

What better way to start 2026 then to talk about a Microsoft certification, especially one for a totally NEW type of user!

Following on the steps of the other AB exams I’ve been writing about my experience with (see Exam AB-730: AI Business Professional, Exam AB-100: Agentic AI Business Solutions Architect and Exam AB-900: Microsoft 365 Copilot and Agent Administration Fundamentals ), this article will cover the AB-731 exam.

This exam is focusing on the Microsoft AI capabilities from a Business Leader perspective, and to the best of my knowledge is the first time that Microsoft has ever created an exam from a ‘Business Leader’ perspective. Taking this exam was a complete mindset shift to me, especially when seeing the questions – it’s not about understanding the in depth technical capabilities, but more around the breadth of technology options (spanning Azure, Microsoft 365 Copilot, Copilot Studio & other tools), and what they bring/enable from a BUSINESS perspective.

The official description of the proposed exam candidate is:

As a candidate for this Microsoft Certification, you should understand how to recognize opportunities for AI transformation, identify the right AI tools and resources, plan for AI adoption, optimize business processes, and drive innovation by using Microsoft 365 Copilot and Azure AI services.

This Certification is designed for business decision-makers at all levels who are responsible for guiding transformation and innovation within their teams or organizations. In this role, you’re expected to demonstrate AI fluency, strategic vision, and the ability to lead AI adoption across teams and functions but are not expected to write any code.

As a candidate for this Certification, you should be able to evaluate AI opportunities, champion responsible AI practices, and align AI investments with business goals. You need experience leading adoption or change management in a business context. You must also be familiar with Microsoft 365 services, Azure AI services, and general AI capabilities.

The overall information for the exam can be found at Microsoft Certified: AI Transformation Leader, and there is an official Learning Path available for it.

As I’ve posted before around my exam experiences, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). It’s also in beta at the moment, which means that things can obviously change for when it comes out of beta.

Overall, the exam approach was quite different to me – though I do talk with organisations frequently around general AI matters, I’ve never taken an example written in this way beforehand. However, I do feel that it’s very helpful to have this in place, to ensure that business leaders can demonstrate that they actually do know what they’re talking about 😉

I’ve tried to group things as best together as I feel (in my recollection), to make it easier to revise.

  • Azure Components & Capabilities
    • AI Vision – what it can be used for, benefits of using it, capabilities that it has
    • AI Language – what it can be used for, benefits of using it, capabilities that it has
    • AI Document Intelligence – what it can be used for, benefits of using it, capabilities that it has
    • Machine Learning – what it can be used for, benefits of using it, capabilities that it has
    • AI Foundry – what it can be used for, benefits of using it, capabilities that it has
    • AI Search – what it can be used for, benefits of using it, capabilities that it has
  • Microsoft 365 Copilot Chat
    • What license is needed
    • What data does it have access to
    • What security controls are in place
  • Microsoft 365 Copilot
    • What is it, what can it be used for
    • What can it do
    • How does it connect to data
    • What are the connectors for it (standard & custom)
    • Benefits of using it (vs 3rd party AI tooling)
    • Different agents (eg Analyst & Researcher) within it – what they do, how to access and use them
  • Microsoft Copilot Studio
    • What is it, what can be used for
    • What can it do
    • What license is needed
    • What data can it access
  • Microsoft Security Copilot
    • What is it, what can be used for
    • What can it do
    • Benefits that it provides
  • Security & Governance
    • Content filtering controls within Copilot
    • Policies
    • Handling requirements to prevent inappropriate language & responses
    • Responsible AI principles
    • Governance ownership, responsibility & requirements
  • Generative AI
    • AI model hallucinations
    • Grounding in data
    • Improving response quality
    • Prompt engineering
    • Pre trained models vs fine tuned models
    • Reasoning models vs non-reasoning models
    • Understanding usage costs (including different pricing models)
    • What is RAG, and how can it be used for business scenarios
    • Adoption throughout organisations – personas to involve in adoption team

    I hope that this is helpful for anyone who’s thinking of taking it – good luck, and please do drop a comment below to let me know how you found it! I’d also be interested in your thoughts/opinions around the direction that Microsoft has taken for this!

    Exam AB-900: Microsoft 365 Copilot and Agent Administration Fundamentals

    Following on the steps of the other AB exams I’ve been writing about my experience with (see Exam AB-730: AI Business Professional & Exam AB-100: Agentic AI Business Solutions Architect), this article will cover the AB-900 exam.

    This exam is focusing on the Microsoft 365 Copilot capabilities from a user & administration perspective, and doesn’t cover/include anything from Copilot Studio.

    Now, though it’s a Fundamentals exam, to be honest it’s the HARDEST fundamentals exam that I’ve ever taken!

    The approach is around being able to demonstrate understanding of how to use the Microsoft 365 Copilot, as well as a lot of focus on how to control & administer it.

    The official description of the proposed exam candidate is:

    As a candidate for this Microsoft Certification, you should be familiar with Microsoft 365, including core services, security, identity and access, data protection, and governance, along with Microsoft 365 Copilot and agents.

    Additionally, you should be familiar with the admin centers used to access Microsoft 365 workloads, such as Exchange Online, SharePoint in Microsoft 365, Microsoft Teams, Microsoft Entra, and Microsoft Purview. You need to have experience with AI-driven productivity tools and modern IT management practices.

    You must be able to identify the roles of the core features and objects available in Microsoft 365, such as users, groups, teams, sites, and libraries. Plus, you should understand the core security features of Microsoft 365, such as authentication methods, conditional access policies, and single sign-on (SSO).

    The overall information for the exam can be found at Microsoft 365 Certified: Copilot and Agent Administration Fundamentals, and there is an official Learning Path available for it.

    As I’ve posted before around my exam experiences, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). It’s also in beta at the moment, which means that things can obviously change for when it comes out of beta.

    One thing to keep in mind about this exam – though I do mention Microsoft Purview in the list of items below, I haven’t gone into it extensively. However, there were a LOT of questions that touched on Purview (& other governance stuff as well) – you REALLY need to be knowing & understanding these capabilities to be able to take & pass the exam. Just guessing the answers is not going to help at all!

    Overall, the exam seemed to me to be pretty decent, though with indeed a heavy focus on security & governance (as I’ve mentioned above). I don’t see this as a bad thing though, as it can help to show that administrators really do know what they’re talking about.

    I’ve tried to group things as best together as I feel (in my recollection), to make it easier to revise.

    • Agent types
      • Native Microsoft 365 Copilot agent
      • Native Microsoft 365 Copilot advanced agents (eg Researcher & Analyst). What they are, how to access, what to use them for
      • Custom Microsoft 365 Copilot agent
      • SharePoint agent
    • Creating/using Agents
      • Using natural language to create agents
      • How to handle/perform multi-step reasoning
      • Use of notebooks
      • Custom instructions
      • Scheduling prompts
      • Querying data types
        • Structured
        • Unstructured
    • Governance & security
      • Blocking access to different types of searches & collateral
      • Blocking access to specific agents
      • Tools to use for blocking
      • How to share agents with other users
      • Assigning licenses to users
      • Data retention policies
      • Data labelling policies
      • Use of Microsoft Purview, covering capabilities, tools, auditing, how to use, etc
      • Use of DLP
      • Data source permissions
      • Conditional access policies
      • Microsoft Defender – what it is, capabilities it has, how to use it, etc.
      • Types of authentication
    • Reporting
      • Licensing & usage
      • Adoption & interactions
    • Payment options & capabilities
      • Credit usage – internal vs external users
      • Pay As You Go Billing, and scenarios you can use it for

    I hope that this is helpful for anyone who’s thinking of taking it – good luck, and please do drop a comment below to let me know how you found it! I’d also be interested in your thoughts/opinions around the direction that Microsoft has taken for this!

    Exam AB-730: AI Business Professional

    Following on from the recent launch of the new Exam AB-100: Agentic AI Business Solutions Architect exam, Microsoft has now developed & released other exams in the AB series – this post is on the AB-730 exam.

    The approach continues to be around how to use AI within technology for business purposes, rather than needing to be able to create AI or code. This exam focused on the Microsoft 365 Copilot experience, how to use it within various Microsoft Office applications, etc.

    The official description of the proposed exam candidate is:

    As a candidate for this Microsoft Certification, you should have experience using generative AI–powered productivity tools, including Microsoft 365 Copilot, Researcher, and Analyst. You take advantage of AI to improve daily work, drive business outcomes, and make informed decisions in business contexts—without building AI apps or writing code.

    You should have a basic understanding of Microsoft 365 and should be comfortable navigating core apps, such as Outlook, Word, Microsoft Teams, PowerPoint, and Excel. You should also be familiar with common business processes, including drafting emails, creating presentations, generating images, and managing documents.

    The overall information for the exam can be found at at Microsoft Certified: AI Business Professional (beta) – Certifications | Microsoft Learn, and there is an official Learning Path available for it.

    As I’ve posted before around my exam experiences, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). It’s also in beta at the moment, which means that things can obviously change for when it comes out of beta.

    One thing that I found I didn’t like about the exam is the new question type of ‘Best Answer’. This question type gives various options, whilst telling you that more than one answer choice may achieve the goal, but asking you to select the BEST answer. I believe that questions like this are subjective, and the answers will vary based on each person’s knowledge, understanding & experience, so I’m not quite sure why Microsoft have decided that this would be good to use. It will be interesting to see what happens when the exam comes out of Beta, and if these questions are still around or not then.

    Overall, the exam seemed to me to be pretty decent – I initially thought it would be quite generic, but you really do need to know how all the Copilot offerings work including Copilot Chat and Copilot in the Office applications.

    If you’re new to Copilot, and/or not really sure as to how it actually works & the capabilities, I’d suggest not to take the exam yet. Instead, go and take a look at the learning paths, and look to find out how it actually works & operates.

    I’ve tried to group things as best together as I feel (in my recollection), to make it easier to revise.

    • Microsoft 365 Copilot vs Microsoft 365 Copilot Chat
      • What each one does/doesn’t do
      • When to use each one
    • What to include when prompting Copilot
    • Copilot security framework
      • How data is used
      • The different data controls that are in place
      • How data protection works, different data protection capabilities & using them
      • Removing data & prompts from Copilot,
    • Copilot capabilities in Microsoft Word
    • Copilot capabilities in Microsoft Excel
    • Copilot capabilities in Microsoft Outlook
    • Copilot capabilities in Microsoft PowerPoint
    • Copilot capabilities for Teams
      • Using Copilot within Teams for queries
      • Using Copilot within Teams for meetings (preparing for them, during the meeting, after the meeting)
    • Collaboration with Copilot report outputs
    • Copilot Researcher agent – getting access, capabilities & use cases, inputs & outputs
    • Copilot Analyst agent – getting access, capabilities & use cases, inputs & outputs
    • Using custom instructions within Copilot – how to do this, how it is used/applied, etc
    • Using documents with Copilot for answers & generating material. Updating new versions of documents, and how Copilot will behave
    • Microsoft 365 agents – creating, configuring, sharing, security etc
    • Creating, sharing & scheduling prompts, including limitationsent

    I hope that this is helpful for anyone who’s thinking of taking it – good luck, and please do drop a comment below to let me know how you found it! I’d also be interested in your thoughts/opinions around the direction that Microsoft has taken for this!

    Exam AB-100: Agentic AI Business Solutions Architect

    It’s always interesting when Microsoft release a new type of exam, especially when it’s not tied to specific functionality, but rather to an overall approach. The AB-100 exam (don’t pay too much attention to the ‘100’ designator, in my opinion) follows the approach that we’re seeing Microsoft taking – needing to use technology (& here, specifically AI in technology) holistically across multiple solution.

    I took the exam in Beta as soon as it launched, though due to preparing for the Power Platform Community Conference (which I’m currently writing this at), it’s taken a bit of time to get this blog post up and published.

    As an architect, AI isn’t new to us – we know of multiple different capabilities (spanning Microsoft 365, Copilot Studio & Azure AI Foundry), which we need to use appropriately to handle customer scenarios. AI isn’t new to exams either – there are multiple Azure exams with AI in them, we have multiple Business Application exams with Copilot Studio in them, etc.

    However, exams to date focus on a specific part of the technology stack. For example, the PL-600 focused on Power Platform & Dynamics 365 Customer Engagement. The MB-700 focused on Dynamics 365 Finance & Operations, and so on and so forth.

    This new exam is somewhat of a paradigm shift – needing to understand AI holistically as an architect across multiple parts of the technology stack, what & how it’s used for and where, etc. This is most definitely a new approach, and it will be interesting to see how it users react to it.

    Truthfully, having taken it, I’d personally say that it feels a bit more like an enterprise architect exam approach (which also doesn’t exist in the Microsoft stack), albeit focused around Business Applications. Given the way in which Microsoft partners have specialists in each technology part of the stack, it will be interesting to see if this approach will pivot the way in which people are trained/skilled, and deliver projects. I think that there’s likely to be a lot of feedback to Microsoft that it’s not the way that the partner landscape currently works – though perhaps Microsoft is specifically trying to influence this itself to change. Only time will tell…

    The overall information for the exam can be found at Microsoft Certified: Agentic AI Business Solutions Architect (beta) – Certifications | Microsoft Learn, though there is NO learning path that’s been created (at the time of writing). I think that this is because Microsoft may want to see the reaction to this new approach, and pivot appropriately, rather than needing to create a lot of content that may potentially need to be re-done.

    The official description of the exam can be found at the link above (it’s too long to post here), so please go take a look!

    So, as I’ve posted before around my exam experiences, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). It’s also in beta at the moment, which means that things can obviously change for when it comes out of beta.

    I’ve tried to group things as best together as I feel (in my recollection), to make it easier to revise.

    • Business usage of AI
      • Different agents usage and results
      • How to use appropriately for business/agent analysis
      • Different types of metrics and results
      • Best practices for building Copilot Studio agents, and using Copilot Studio agents
      • Looking at the ROI for using Copilot Studio agents
      • Designing the usage of different AI and agent capabilities for business needs
    • Building agents
      • What Copilot Studio agents need to work
      • Data types that agents can use
      • Data sources that agents can use
      • Use of knowledge sources for agents
      • Usage of custom connectors
      • Handling token usage with Azure AI Foundry
      • How to handle testing for Copilot Studio agents
      • Different testing types & approaches
      • Extending Microsoft 365 Copilot
      • Using Power Automate with Copilot Studio agents
      • Speech to Text/Text to Speech
      • Handing conversation to live customer service representative using Dynamics 365 Contact Centre
      • Using RPA within an agent
    • Models
      • Different types of models that could be used within Azure AI Foundry
      • Orchestration
      • Improving performance
    • Security
      • How to handle Copilot Studio security
      • Governance & compliance tooling (eg Purview)
      • Handling/restricting connectors for Copilot Studio agents
      • Ensuring user security when using agents (ie not able to retrieve data that the user cannot access directly)
    • Reporting
      • Monitoring tools for Copilot Studio agents
      • Metrics, usage & analytics for Copilot Studio agents
      • Investigating Copilot Studio agent transcripts
      • Monitoring tools for Azure AI models
      • Evaluating Azure AI Foundry model outputs
    • Application Lifecyle Management
      • Focusing on AI Agents for Dynamics 365 CE, Finance & Operations, and Power Platform
      • How/what components to use and include
      • What tooling to use for ALM

    Overall, the exam seemed to me to be pretty decent – I was worried that it would focus just on Copilot Studio, with not much else in it, but there’s a good balance across other AI capabilities as well.

    The big change, for me at least, were the questions around Dynamics 365 Finance and Operations – this isn’t an area that I’m an expert in generally, and most definitely not for AI tooling. I think that this, as I mention above, is what may get the biggest pushback/feedback into Microsoft.

    I’m going to be quite interested in seeing how the exam is actually launched (as it’s currently in Beta of course). Having chatted with a few others who have taken the exam (whilst obviously respecting the NDA!), they also think that this is an approach pivot from Microsoft, and are wondering about the real world application of it.

    I hope that this is helpful for anyone who’s thinking of taking it – good luck, and please do drop a comment below to let me know how you found it! I’d also be interested in your thoughts/opinions around the direction that Microsoft has taken for this!

    Error in Customer Insights – Data

    Not a long blog post, but something that may come in handy for some people!

    I was recently playing around with Customer Insights – both the Data & Journeys side of thing for a Proof of Concept I was creating for a customer. It’s definitively interesting to see how Microsoft have been evolving the product over the last year or so (which was the last time I played around with it).

    One of the components that we were very interested to play around with specifically is the ‘Discovery’ part of Customer Insights – Data. As shown in the screenshot below, this is where you’re able to use natural language to query your data, to then get results using AI. This means that you don’t have to understand any specific query language (SQL, R, M etc), but rather just ‘converse’ with it as you would another person.

    You’ll perhaps note that there’s NO mention of Copilot here, though perhaps Microsoft may at some point decide to call this Copilot functionality as well?

    The team had loaded in the data – we had a fair few number of rows (multiple millions of them!), gone through the unification process, enrichment process, etc etc. All of this was set up & working properly.

    However, when I tried to go to the ‘Discovery’ tab in my own browser, I was getting an extremely strange error:

    As you can see, it’s incredibly informative…NOT!!! I mean, what does ‘Value cannot be null. (Parameter ‘key’)’ actually mean to the average person?

    At first, I thought it was something to do with the underlying data, so went back to check that. However the data seemed fine. Furthermore, other people on the team were able to access Discovery in their own browsers without any issues.

    Having no other option (turning it off & on again didn’t work), I raised a support ticket with Microsoft. This was responded to in a timely fashion, and I found myself working with Rohan, the Microsoft Support Representative.

    In my initial ticket submission, I had included details of what was going on, what I had clicked on, that others in the team didn’t have the problem, the Organisation ID, URL’s – you name it!

    Rohan jumped on a call with me, and it turned out to be the shortest support session I have EVER had. He asked me to change the system language to another language (I had been using English, to decided to change it to German). Once the language change had been applied, we navigated back to the ‘Discovery’ tab (all in German, I may add), and when the screen loaded, there was no error! Holding our breath, we then changed the language back to English (more complicated than I had imagined, with navigating in a different language).

    Once this was done, and everything was back in familiar English, the ‘Discovery’ tab then loaded without issues (again!), and I was able to go ahead and start running queries in it using natural language. It was great!

    In fact, it’s actually taken me longer to type out the above than the length of the support call – it was indeed that quick! Obviously lots of praise to Rohan (he did mention he had seen this once before, which is why he knew how to fix the issue).

    The bigger question in my mind is what exactly was happening/going wrong underneath – I have asked this to Microsoft, but haven’t gotten a response. My guess is that something in the user/language settings hadn’t been populated properly, and therefore resulted in that error message. Updating/changing this forced it to then populate properly, and it worked.

    Have you ever seen something like this, where changing a system setting (such as language) helped resolve an issue? I’d love to hear more about it –

    AI, Microsoft Copilot, and Copyright

    Firstly, a Happy New Year to everyone – I’m sure that you have amazing plans for 2024, and wish you the best of luck with them!

    Over the last few months, I’ve been keeping a close eye on Copilot (since it was announced as being in GA), and various happenings around the wider AI scene. It seems almost impossible to find someone who is NOT aware of the OpenAI happenings towards the end of 2023, and so many more conversations now include mention of ChatGPT, Azure OpenAI, etc.

    But there’s one item I’d like to pick up on & discuss, which given the news events of last week, is extremely pertinent. This is the topic of copyright, which is a very important topic to understand. However in order to understand it properly, we need to understand how AI offerings are generated in the first instance.

    All of the various AI offerings rely on LLM’s. This stands for ‘Large Language Model’, and these are deep learning models that are pre-trained on vast amounts of data, and by vast, the number of data points are truly staggering:

    Incidentally, users should consider the use case that they’re using AI for, and look to use the best optimum model for it. As an example – if wanting to find out the best routine for making a cup of coffee, it is unlikely that a GPT-4 model would be needed – a suitable model could be one with less parameters in it. This is in part due to the amount of resources needing to be used to run queries on more advanced data models.

    When using an AI offering, these datasets are used to present answers back to the users. Some AI models are not limited to just their LLM datasets, and are able to actively trawl & access websites as well for more up to date information.

    But there are two inherent problems with the way that this can work:

    Data

    When users interact with chatbots or other AI capabilities, they’re inputting data into them. This data could be used by the AI capability to further train models forward, ingesting the data provided to them. Given that data could be sensitive or proprietary, this can be problematic. Not all AI organisations use data just for processing, as has been discovered by various users.

    Copyright

    Given that responses back to users (whether in text format, image format, or other formats) are based on the datasets from the underlying LLM’s, users could potentially be provided with information that is actually copyright, and which they’re not able to use. This is very problematic, as it can result in users passing off material as their own, whilst it actually belongs to someone else.

    Microsoft’s approach

    Microsoft’s approach to AI capabilities has been made extremely clear. You may be familiar with seeing slides similar to the following slide:

    What this means is the following:

    • Microsoft will not use any customer data to train AI models & capabilities for any standard AI offering
    • Any custom Copilots created by Microsoft customers will remain their own – Microsoft will not use data or capabilities from customer created collateral within the Microsoft AI offerings. This means that a bespoke Copilot will only offer its functionality to the customer that created it – other organisations, even within the same sector & creating Copilots themselves, will not benefit from this

    Microsoft has also confirmed publicly that any information generated through the usage of Copilot or Azure OpenAI can be used without concern about copyright claims (Microsoft announces new Copilot Copyright Commitment for customers – Microsoft On the Issues). In fact, Microsoft has even gone so far as to say that Microsoft will assume responsibility for any potential legal risks involved.

    If a third party sues a commercial customer for copyright infringement for using Microsoft’s Copilots or the output they generate, we will defend the customer and pay the amount of any adverse judgments or settlements that result from the lawsuit, as long as the customer used the guardrails and content filters,

    Brad Smith, Microsoft Chief Legal Officer

    This is quite important – customers are able to use Copilot & Azure OpenAI capabilities, and be assured that they will not have to be concerned about copyright issues or challenges. There are of course some conditions around this, in the way that prompts & interactions need to be handled (see Customer Copyright Commitment Required Mitigations | Microsoft Learn for further information on this).

    Microsoft has this called out specifically within their Universal License Terms, available to view in full at Microsoft Product Terms.

    Recent news events

    With the announcement last week that the New York Times has filed suit against the OpenAI Corporation & Microsoft, this is very timely to look at (New York Times Sues OpenAI and Microsoft Over Use of Copyrighted Work – The New York Times (nytimes.com)).

    The implications of such a lawsuit will affect how AI capabilities will be able to be created & used on an on-going basis. Copyright is of course very important to respect, and it will be quite interesting to see how this plays out. Having taken a look at some of the material included in the lawsuit, there are most definitely similarities between the New York Times information, and the AI generated output.

    So, in my opinion, this is going to be a very interesting space moving forward, and I look forward to seeing how it goes, and any effects that it has on the usage of AI within organisations.

    ‘Swarming’ for Customer Service

    You might be wondering as to what I mean by ‘swarming’ in the title for this post. Don’t worry – it’ll become clear pretty soon! But first of all, let’s understand the story behind this new functionality.

    Where to begin? Well, let’s take a look within an organisation. It doesn’t really matter what sort of organisation it is, as most organisations will have something similar scenarios overall. So, what are we actually talking about?

    Customer Service is, of course, a very important functionality of any organisations. Customers who have purchased products may need support, or perhaps are having issues, and need them to be resolved. Customer service agents are there to handle the customer queries, and look to resolve them as soon as possible.

    However, it’s possible that the customer service agents don’t actually know how to resolve the customer query/issue themselves. They can, of course, use the Knowledge Base, but that requires knowledge articles to be created & maintained.

    Now within the organisation, there will be SME’s (Subject Matter Experts). These are the people who know the matter in precise detail, often being the people who have created the product and/or process to begin with. But these people aren’t usually carrying out the customer service function.

    So what this means is that the customer service agents need to try to work out who might actually know the answer/s, be able to help resolve the customer issue, etc. This can take time, be laborious, and perhaps not even be able to be carried out (depending on the organisation).

    Hmm. So, what if the system might be able to actually SUGGEST the right people for a problem or issue? Even better, what if the system could support them being involved directly with the record/s, regardless of whether they’re a user within Dynamics 365 or not?

    Enter the swarming capability onto the Dynamics 365 scene….

    The aim of swarming is to bring together the necessary experts within Dynamics 365. Now, having said that, not all users will actually be interacting directly within Dynamics 365. What happens is that a specific Teams chat is created, so that users outside of the system can see the necessary information, and give input on the situation.

    This builds on the existing functionality of being able to use Teams chats directly within Dynamics 365, but takes it to a whole new level, by having the system automatically suggest relevant people within the organisation, and bring them into the swarm chat!

    There are some necessary steps to configure to enable this to happen.

    Firstly, Teams needs to be enabled within Dynamics 365:

    Once we start to turn things on, we can then see the following. This allows us to be able to specify the types of records that we can use swarming on. This is great, as we may be building out custom functionality using other tables, and can enable swarming on these as well

    Once Teams chat has been enabled, we can then start setting up the swarming capabilities:

    As part of the setup, we have:

    • The ability to set the general message that users will see when they create a swarm
    • Activating the case form that’s used for swarming (as this will include the functionality for swarming on the case form)
    • A Power Automate flow that will be used for sending notifications & invites within Teams for suggested (internal) users
    • Creating swarm condition rules, which allows us to bring in specific conditions around skills etc

    So, how does this work in practise, once the system has been initially configured?

    Users can go to the relevant record, such as a case record. They’re able to select the ‘Create swarm’ from the menu bar:

    This then allows the user to provide a summary of what the swarm is for, the scenario, as well as selecting the skills needed for the swarm. Dynamics 365 can also suggest skills that it thinks would be helpful as well:

    Users from across the organisation are matched, according to the skills identified:

    Notifications are sent to them within Teams, requesting their help with the matter:

    When they accept the invitation, they’re then brought into the swarm:

    In fact, the members of the swarm aren’t actually accessing the swarm information within Dynamics 365. Instead, they’re seeing & interacting with the swarm within Teams itself!

    Once the swarm is active, information can be shared, and a solution found. The swarm can then be successfully closed down:

    This is truly amazing. Obviously collaboration on issues is important, especially when considering that we’re trying to resolve customer issues as quickly as possible! I’m also really excited about this, as I was part of the initial group that Microsoft reached out to initially for feedback on the capabilities of it.

    To now be able to collaborate with users who sit outside of Dynamics 365, but have them access the necessary information to help resolve things, is just mind-blowing. So many scenarios that come to mind as to how this can really empower organisations!

    Can you think of a way in which this could change things in your own organisation, or at a client? Drop a comment below – I’d love to hear more!

    AI Translation for Omnichannel

    How to start off this post? I’ve been trying to work out how exactly I can express my excitement around this new feature for Omnichannel. Included in the Wave 2 2020 release, it’s just AMAZING. That, however, doesn’t give it true justice. So let’s see how I can describe it properly to give it due respect.

    Previously I’ve mentioned the ability to use skills within Omnichannel (see https://thecrm.ninja/omnichannel-for-dynamics-365-queues-users-skills/). This can be used to indicate, for example, agents who can communicate in a certain language. That’s useful of course, but what happens when you don’t have anyone who can speak the language that the customer wants to use? It’s a problem, and one that’s really not easily solved. At least, not until now.

    So, what exactly does this new translation feature do? Simple – it translates from one language to another. OK, it’s actually a little more awesome than just that. Having delved into it quite a bit over the last week or so, there are (in my view) three main benefits (with a bonus one as well!):

    1. It translates incoming text from the customer (through chat) from the language that they’re using to the language that the agent is using
    2. It translates outgoing text from the agent (through chat) from the language that the agent is using to the language that the customer is using
    3. It translates text between agents from one language to the other & vice versa (eg on an internal consult)

    Now for the bonus. It doesn’t just translate text from one language to another. It follows the languages being used! So if the customer switches in mid-conversation to a different language, the system picks it up. Not only is the new incoming language translated into the agents language, but the replies from the agent are shown in the (new) language being used by the customer. It’ll automatically show text in the ‘last used’ language, which is really quite incredible (at least in my opinion).

    There’s no fiddling around of needing agents to select the language that they need, or anything else. It’s a simple click to turn it on, and then another click to turn it off. I’m going to go through the setup of it below, as there are a few fiddly bits that did confuse me for a bit.

    It’s also possible to use different translation tools. At the time of writing this post, it’s possible to use Bing, Google or Azure translation models. I’m sure that there will be other options available in the future as well to use, which really opens up possibilities for clients with differing digital estates.

    Translation happens in real time, so there’s no waiting around for it to actually get on with it. It’s displayed immediately on the screen for the agent to see.

    Setup for translation

    I found the general guides to be alright, but weren’t too clear on a few items. I’m therefore sharing below how I went about it, in order to get things working properly. Please be aware that this isn’t in the order specified in the documentation, but in retrospect means less switching between screens:

    1. Ensure that you have the latest updates to your Omnichannel environment (this is always a good idea, regardless of anything else!)
    1. Go to https://github.com/microsoft/Dynamics365-Apps-Samples/tree/master/customer-service/omnichannel/real-time-translation & download the ‘webResourceV2.js’ file there (if you’re unfamiliar with how to do this, click to open the file, click the ‘Raw’ button, and then save the page (ensure it’s got the ‘.js’ extension when you save it!).
    1. Ensure you have an API key to enter into the web resource file! This is what tripped me up at first. You can use any text editor (I use Notepad++) to open it up. How you get the API key will depend on the provider. For example, to set up a free account in Azure, take a look at https://docs.microsoft.com/en-us/azure/cognitive-services/translator/translator-how-to-signup. There are also some additional things that you can configure in the web resource file, but I’m not going to go into that here
    1. Go to your solutions (this can either be through the Classic interface, or through http://make.powerapps.com). You can either create a new solution to hold the web resource file, or alternatively if you have existing solutions that you’d deploy, you can add the web resource file to that. Either:
      1. In the classic interface, navigate to Web Resources, click to create a new web resource, and upload the file (ensure you select the type to be ‘Script (JScript)’, or
      2. In the modern interface, click the ‘New’ button, select ‘Web Resource’ from the ‘Other’ section, and then follow the steps above

    Once it’s saved, it’ll give you a URL. Copy that, and publish the solution.

    1. Go to the Omnichannel Administration Hub, find ‘Real Time Translation’ under Settings, and set this to Yes. You can also select a default input language from the selection. Also enter the URL that you copied above. Save it
    1. You’re all done!

    Agent Experience

    Depending on how you’ve configured your web resource, auto translation will either by on by default, or be off. If it’s not on by default, the agent can simply click within their chat window to select it to be active:

    Once active, it’ll then start to translate everything, in both directions. Below are side by side screens of the customer & agent experiences. You’ll note that the customer is seeing the initial agent response in English, as the agent was the first in the conversation

    From the agent side of things, both the original language, as well as the translated language, are shown. The customer is only shown the language that they’re actually using

    If the agent isn’t sure what language the customer is using (as it’s being auto-translated for them), they can hover over the text, and it’ll show the details for it:

    If the agent will consult, or transfer the session to another agent, the second agent will see the conversation in the language that they are themselves using (with the original text as well). This allows for the possibility to pass a customer to a specialist to assist them, even if they don’t speak the same language! It’s really cool to see this in action.

    Even more wonderfully, this is even stored down to the transcript level:

    This is really opening up major new concepts that Omnichannel can be used for, which will be supported entirely by this feature. As I said at the beginning of this post, I’m absolutely excited for it, and we’re already envisioning how this will be able to empower our clients even more.

    Do you have any questions around this? Can you think of any scenarios that this could solve for you? Drop a comment below – I’d love to hear!

    AI-900: Microsoft Azure AI Fundamentals

    One of my recent decisions has been to explore the Azure space. There are several reasons behind this. CDS, as we (hopefully!) know sits on top of Azure, and it’s useful to know the broader digital estate available on the platform.

    I’ve also been looking into some of the Cognitive Services functions that are available within Power Platform. These all live in Azure, and are surfaced into Power Apps etc. It’s therefore good to know what can be done outside of the ‘Power Platform bubble’, and the options there.

    Incidentally, a year ago I even built a canvas app that allowed you to take a picture of a motorbike tyre. Using AI Builder functionality, it then analysed if the tyre tread was legal or not! That was a really cool proof of concept.

    So a good place to start, I thought, would be with the AI-900. This covers the fundamentals of the AI offerings that are in Azure. I had forgotten though that with fundamental exams, there’s only 60 minutes available! Seeing the timer ticking down from that give me a little surprise, though I managed to get through it (& pass!) in good time.

    The official description of the exam is

    Candidates for this exam should have foundational knowledge of machine learning (ML) and artificial intelligence (AI) concepts and related Microsoft Azure services.

    This exam is an opportunity to demonstrate knowledge of common ML and AI workloads and how to implement them on Azure.

    This exam is intended for candidates with both technical and non-technical backgrounds. Data science and software engineering experience are not required; however, some general programming knowledge or experience would be beneficial.

    The official page for the exam is at https://docs.microsoft.com/en-us/learn/certifications/exams/ai-900, where it gives quite a good overview of things. Go take a look at it, and also take a look at the associated learning paths.

    Once again, I sat the exam through the proctored option (ie from home). Honestly I think that my experience this time has probably been the best so far. I went through the usual system checks for signing in. The proctor came alone, and within 30 seconds they had released the exam!

    So, as before, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). I’ve tried to group things together as best as possible for the different subject areas.

    • Image recognition types
      • What each one is, what it’s used for
      • When to use for a specific scenario
    • Facial recognition
      • Different types available
      • What each one is, what it’s used for, when to use for a specific scenario
      • Limitations & issues that can occur when using it
    • Text:
      • Different recognition types
      • What each one is, what it’s used for, when to use for a specific scenario
      • Analytics. How this works, how to set up & use
      • Translation. Different options available, how they work, when to use for a specific scenario
      • Sentiment analysis. How it works, limitations, what’s needed to train a model
    • QnA Maker
      • What this does, how to set it up, how to train it
      • Generating material with it
      • Use with chatbots
    • Machine Learning
      • What this actually is, and what it does
      • How it works
      • Different types that are available, how they work, how to train a model
      • Classification options
    • Machine Learning Designer
      • How to use & set up
      • Different types of data/options used within it
      • Training & evaluation models. The steps needed for this, how to set it up correctly
      • Types of modules available
      • Validation sets
    • Chatbots
      • What they are
      • How/where they can be used
      • Limitations
      • Integration with other systems
    • Charts
      • Different charts that are available for use
      • Reading them correctly
      • Model types shown on them
      • Metrics!
    • Microsoft AI Principles
      • The different principles that are published
      • What each one means/refers to

    Overall, it was quite good. The Microsoft AI Principles were new to me, and I had to guess at those (I went to look them up afterwards!). Other than that, some bits I breezed through, other parts I took careful stock of.

    This is definitely an area that I’m going to continue exploring, and will be writing up further exams that I take in it. I’m curious what your experience of it has been – please drop a comment below to let me know!