wedoAI 2024

Something a little different…

Head over to https://wedoai.ie to checkout a new online event that just launched on August 22nd.

The idea of this event is to promote learning and sharing of knowledge within the Microsoft AI community. To achieve this, we have community driven articles that highlight best-practises, lessons learned, and help with some of the more difficult topics of Microsoft AI.

For anyone familiar with Azure Spring Clean – you will see some similarities!

Microsoft MVP Summit 2024

This week was the MVP Summit for 2024. As with all previous events, all content is completely under NDA. That means this post isn’t going to disclose any of the information that was discussed, but I can mention some areas/ideas that I am excited about.

Most years, Microsoft runs several conferences. Some are more impactful than others, and this year is no different. I am really looking forward to Build and the developer focussed content that will accompany it. And not since 2019 am I looking forward to Ignite as much as I am this year. It appears to be almost back to its full strength, being run this year in Chicago across several days.

While we were at Summit, the GA of Copilot for Security was announced for April 1st, another major milestone for Microsoft’s Copilot products. It doesn’t take much foresight to guess that this pace and innovation of AI products will continue into 2024.

One non-technical item that was very important was my fellow MVPs. This year had an increased in-person turnout to last year, and everyone was in fantastic form for the week. As evidenced in the photo below which includes myself, and other Irish MVPs we could round up on short notice for a quick picture at Microsoft’s new building courtyard.

And for the first time ever, I was joined by a colleague! Alan Kinane is new into our team, and it was great to be able to chat on different levels about content.

And lastly, a massive thank you to those who organised, ran, and made sure everything went as planned for the week. I can only imagine how complex it all is. It’s very much appreciated!

Exploring: Microsoft Copilot for Azure

Recently, I was lucky enough to gain access to Microsoft Copilot for Azure as part of a limited preview. For anyone who missed the announcement at Ignite, here is what Microsoft describe it as:

Microsoft Copilot for Azure (preview) is an AI-powered tool to help you do more with Azure. With Microsoft Copilot for Azure (preview), you can gain new insights, discover more benefits of the cloud, and orchestrate across both cloud and edge. Copilot leverages Large Language Models (LLMs), the Azure control plane, and insights about your Azure environment to help you work more efficiently.

So – what does that mean in practice? For me, this means reading the docs, then getting stuck into actually trying elements of this out. To be transparent, I had low expectations for this service. I am not 100% sure whether it is aimed at me, or someone with less Azure experience. I was also conscious that this is the limited preview I am working with, so there will be some oddities.

First up, the integration into the Portal UX – I like it. It’s simple, and consistent. As it is a tenant level service, it stays in place as you jump around the Portal from a Subscription to a Resource to Entra ID for example.

Next, what can I use this for that is quicker than me doing this myself? I will be honest, I struggled a bit here. This is for two reasons. One, this is enabled in my MVP tenant, so I have very little Production or day-to-day work to be done. Two, I was looking for something interesting rather than ‘tell me how to build a VM’.

So, I started with a question I know the answer to, but anyone who follows #AzNet knows we are all dying for progress on…

Imagine my surprise with how confident that response is! OH MY GOD I FOUND A THING. Well no, it doesn’t work. And I have no idea what it means in Step 3. If you find out – please let me, Aidan and Karl know, thanks 🙂 But I do like that it attempts to back up its answer with links to documentation.

As you make requests, it dynamically updates the text to tell you what it is ‘thinking’ which I really like.

And that ability to write queries, is a real winner for me. saves a lot of time, but you need to be quite specific with the ask and detail, but that’s no real surprise at this stage.

I do like its ability to take quite a non specific question and offer a decent and useful output in response

However, I am finding myself trying to find things for it to do. This is OK during preview, where there is no additional cost, however, it’s not clear on what pricing will actually be just yet, vague language on the landing site makes me think this will be charged for

Overall, I think it’s a welcome addition to the AI assistant space from Microsoft. I think those of us working with Azure would feel quite left behind otherwise. But I do think that as the platform is so vast and as each environment is unique, the core use case for different people will vary and that could significantly impact whether this is used widely or not. Having said that, I am looking forward to how this progresses, and more people having access can only mean improvements.

Can Azure OpenAI Write This Blog Post?

This is the fear right? Or maybe it’s not a fear, and is a desire for some people, but it’s still not clear what the impact may be. What am I talking about? AI of course; specifically for this post, Azure OpenAI. Now, my idea here is to see what I think of the quality of responses it can give me based on specific prompts to try and tie together a simple blog post. I will pick a topic, an objective for the post, and I will be 100% transparent on what is AI written and what is me – just in case it is not obvious! I will also include the settings being used for my model at the end and whether I adjusted them during.

Ok, let’s get started. My topic is going to be Virtual Network Manager in my usual style of exploration.

What is Azure Virtual Network Manager? Write an opening paragraph for a blog post.

Azure Virtual Network Manager is an essential tool for managing and organizing your cloud-based virtual networks. With virtual networks, you can securely connect and isolate your Azure resources, control traffic flow, and expand your on-premises network into the cloud. However, managing virtual networks can be a challenging task, especially when you have multiple resources and services scattered across different regions. This is where the Azure Virtual Network Manager comes in, offering a centralized and user-friendly interface to help you efficiently manage and monitor your virtual networks. In this blog post, we will take a closer look at the Azure Virtual Network Manager and explore its features and benefits.

What are the top three use cases for Azure Virtual Network Manager? Write a detailed paragraph including bullet points and examples for each.

Azure Virtual Network Manager is a versatile tool that can support various use cases, depending on your organization’s needs. Here are the top three use cases for Azure Virtual Network Manager:

  1. Hybrid Cloud Connectivity: Azure Virtual Network Manager can help organizations establish secure, high-speed connections between their on-premises datacenters and Azure resources. This allows companies to take advantage of the scalability and flexibility of the cloud while maintaining the security and control of their own infrastructure. With Azure Virtual Network Manager, organizations can easily configure VPN gateways, express routes, and other connectivity options to seamlessly integrate their on-premises networks with Azure.

    Examples:
  • Connecting an on-premises Active Directory to Azure to manage identity and access for cloud resources.
  • Extending a corporate LAN to Azure to host applications and services in the cloud.
  • Using Azure as a backup and disaster recovery site for on-premises datacenters.
  1. Multi-Tier Application Architecture: Azure Virtual Network Manager enables organizations to create complex multi-tier application architectures in the cloud, with the ability to isolate and secure different layers of the application. This is done by creating multiple virtual networks, each with its own subnets and security groups. This approach provides better control over network traffic and reduces the risk of security breaches by limiting the attack surface.

    Examples:
  • Hosting a web application in Azure with a separate virtual network for the web server, application server, and database server.
  • Creating a DMZ in Azure to host public-facing services, with a separate virtual network for internal services.
  • Separating development, testing, and production environments into different virtual networks to ensure isolation and security.
  1. Global Network Management: Azure Virtual Network Manager provides a centralized interface to manage virtual networks across different regions and subscriptions. This allows organizations to monitor network traffic, troubleshoot connectivity issues, and optimize network performance from a single location. With Azure Virtual Network Manager, organizations can also implement advanced networking features, such as traffic routing, load balancing, and network security groups.

    Examples:
  • Creating a global load-balancing solution to distribute traffic across multiple regions and availability zones.
  • Implementing Azure Firewall to provide centralized network security management across multiple virtual networks.
  • Enabling Azure Traffic Manager to route traffic to the nearest endpoint based on geographic location or network latency.

What are the current limitations or known issues of Azure Virtual Network Manager? Write a paragraph in the blog post.

While Azure Virtual Network Manager is a powerful tool for managing virtual networks in the cloud, there are some limitations and known issues that organizations should be aware of. Some of the current limitations of Azure Virtual Network Manager include:

  • Limited support for hybrid networking configurations: Currently, Azure Virtual Network Manager has limited support for hybrid networking configurations, which can make it challenging to manage virtual networks that span multiple cloud providers or on-premises datacenters.
  • Limited visibility into network traffic: Azure Virtual Network Manager provides limited visibility into network traffic, which can make it difficult to troubleshoot connectivity issues or monitor network performance.
  • Limited integration with third-party tools: Azure Virtual Network Manager has limited integration with third-party tools, which can make it challenging to implement advanced networking features or security solutions.

    Organizations should carefully evaluate their networking needs and consider these limitations before deploying Azure Virtual Network Manager. However, Microsoft is continually improving the tool and addressing these limitations through updates and new features.

Is there a tutorial or general steps that should be recommended as part of this blog post for people who are interested in now trying Azure Virtual Network Manager? Include high level steps and a link to the appropriate site if possible

Yes, Microsoft offers a comprehensive tutorial on how to set up and manage virtual networks using Azure Virtual Network Manager. Here are the high-level steps for getting started with Azure Virtual Network Manager:

  1. Create a virtual network: The first step is to create a virtual network in Azure. This involves specifying the name, address space, and subnets for your network. You can also configure advanced network settings, such as DNS servers and network security groups.
  2. Create a gateway subnet: If you plan to connect your virtual network to an on-premises network, you need to create a gateway subnet. This subnet is used to deploy a VPN gateway or an ExpressRoute gateway.
  3. Configure VPN or ExpressRoute: Once you have created your virtual network and gateway subnet, you can configure a VPN or ExpressRoute connection to connect your on-premises network to Azure.
  4. Set up network security: Azure Virtual Network Manager provides several tools for securing your virtual network, including network security groups, application security groups, and Azure Firewall. You can use these tools to control inbound and outbound traffic, restrict access to specific resources, and monitor network activity.
  5. Monitor and troubleshoot your network: Azure Virtual Network Manager provides several tools for monitoring and troubleshooting your virtual network, including network performance monitoring, packet capture, and network watcher.

    For more detailed instructions on how to use Azure Virtual Network Manager, check out the official Microsoft tutorial: https://docs.microsoft.com/en-us/azure/virtual-network/tutorial-create-virtual-network.

Based on your previous responses do you think there is anything else that is important to know about Virtual Network Manager? Write a closing paragraph with a call to action to get in touch if you have any questions

In conclusion, Azure Virtual Network Manager is a powerful tool that can help organizations manage and secure their virtual networks in the cloud. With Azure Virtual Network Manager, organizations can establish secure connections between their on-premises and cloud-based resources, create complex multi-tier application architectures, and manage virtual networks across different regions and subscriptions. While there are some limitations and known issues with the tool, Microsoft is continually improving it with updates and new features.

If you have any questions about how to use Azure Virtual Network Manager or want to learn more about how it can support your organization’s networking needs, don’t hesitate to get in touch. Our team of experts is always available to help you navigate the complexities of cloud networking and find the best solutions for your business.

Let’s start with the settings used, I started with these and didn’t change them at all during the process:

engine="35t", (gpt35-turbo)
temperature=0.8,
max_tokens=800,
top_p=0.95,
frequency_penalty=0,
presence_penalty=0

Overall, I think it has the basics nearly correct. However, it has very little personalisation, it obviously speak to no real experience, and is essentially a modified read of the Docs pages. So I am pretty confident that at no point in near future could it be used to write an entire post that I would be happy with publishing. However, where a post calls for something more generic, like known issues, or intros, it could definitely be used as a starting point.

I am interest to see if a GPT4 model would make a huge difference, but for this style of work, I am not sure. Also, I could of course edit the temperature or top p, but I am unsure as to whether that impact again would be noticeable enough.

In conclusion, Azure OpenAI can definitely write a blog post – I am just not sure it’s a blog post I would be happy with!

Azure Migrate – Where to Start?

If you’re thinking about making a move to Azure, it’s important to first understand how to approach it. With the correct approach and sufficient planning, a migration can be straight forward, efficient and void of surprises.

Therefore, the place to start is the Microsoft Cloud Operating Model. This is a detailed white paper that allows you to create a strategy for migration. Covering cloud readiness, people strategy and technical analysis, it’s a comprehensive document. Once you have an understanding of your business strategy, read “Why am I moving to Azure?” and your people strategy, read “Who is moving us to Azure?” you can progress to the technical phase.

The vast majority of initial moves to Azure are often re-host migrations, or “lift and shift”, as these are most common, I will reference this scenario as an example. There are four stages:

The first step of the technical phase is to Assess. This means understanding what it is that you are moving and what the best process will be. This includes everything from involving the business stake holders, to cost calculation to application evaluation. This analysis should give you an output that not only details where the application could go but more importantly, where it can go.

Microsoft offer several tools to help with some of this. First up is Azure TCO. This allows you to estimate the cost savings you could make by migrating to Azure. Next is Azure Migrate, this is an assessment tool that is FREE and allows you to discover, document and assess your workloads and their dependencies. You can then create cost estimates for running them in Azure.

Azure Migrate Dependencies Example

Now that you have your environment discovered, grouped and sized correctly, you can begin to migrate your workloads. Microsoft provide a service for this also, Azure Site Recovery (ASR). This service allows you to replicate your servers from your on-premises environment. For most services it is application aware, meaning it can replicate services like SQL server without any data loss. Before you implement ASR it is important to use your data from Azure Migrate to capacity plan for your replication requirements. Taking this step allows for greater speed and efficiency during replication and migration of workloads.

Microsoft also provide a script repository for migrating large numbers of VMs at once. These can be from VMware, AWS, GCP or physical servers. There are some limitations, most restrictive is lack of support for Managed Disks, but you can always flip these manually later. The scripts and guide can be found here.

How long it takes to migrate your workloads is determined by your business requirements. However, once complete, it is vital that you revisit these workloads for optimisation. Azure Advisor can provide recommendations but the key areas to focus on are:

  • VM sizing – Ensure the VM is running on an appropriate size to gain maximum cost efficiency
  • Storage tier – Ensure the disks associated with the VM are using the correct tier to balance performance requirements against cost.
  • Reserved Instances – Once the VM is sized correctly, purchase Reserved Instances to achieve the maximum discount to run your workload for one to three years.

Now that your workloads are migrated and optimised, your final step is to ensure they’re secure and managed correctly. The best place to start with this process is Azure Security Center. This provides unified security management and allows you to take action to mitigate risk and implement actionable recommendations. This will include common requirements like disk encryption and anti virus. More advanced and platform specific features like Just In Time Access are also available.

So to recap, there is 1 prerequisite then 4 main steps:

  1. Understand and create your Cloud Operating Model
  2. Assess your current environment
  3. Migrate it!
  4. Optimise your utilisation
  5. Secure and Manage it

If all of the above is completed and optimisation and security are reviewed regularly you can be confident in the quality of your environment state. If you have any questions, feel free to tweet me @wedoAzure or leave a comment!