From Local MCP Server to Hosted Web Agent: App Service Observability, Part 2
In Part 1, we introduced the App Service Observability MCP Server — a proof-of-concept that lets GitHub Copilot (and other AI assistants) query your App Service logs, analyze errors, and help debug issues through natural language. That version runs locally alongside your IDE, and it's great for individual developers who want to investigate their apps without leaving VS Code. A local MCP server is powerful, but it's personal. Your teammate has to clone the repo, configure their IDE, and run it themselves. What if your on-call engineer could just open a browser and start asking questions? What if your whole team had a shared observability assistant — no setup required? In this post, we'll show how we took the same set of MCP tools and wrapped them in a hosted web application — deployed to Azure App Service with a chat UI and a built-in Azure OpenAI agent. We'll cover what changed, what stayed the same, and why this pattern opens the door to far more than just a web app. Quick Recap: The Local MCP Server If you haven't read Part 1, here's the short version: We built an MCP (Model Context Protocol) server that exposes ~15 observability tools for App Service — things like querying Log Analytics, fetching Kudu container logs, analyzing HTTP errors, correlating deployments with failures, and checking logging configurations. You point your AI assistant (GitHub Copilot, Claude, etc.) at the server, and it calls those tools on your behalf to answer questions about your apps. That version: Runs locally on your machine via node Uses stdio transport (your IDE spawns the process) Relies on your Azure credentials ( az login ) — the AI operates with your exact permissions Requires no additional Azure resources It works. It's fast. And for a developer investigating their own apps, it's the simplest path. This is still a perfectly valid way to use the project — nothing about the hosted version replaces it. The Problem: Sharing Is Hard The local MCP server has a limitation: it's tied to one developer's machine and IDE. In practice, this means: On-call engineers need to clone the repo and configure their environment before they can use it Team leads can't point someone at a URL and say "go investigate" Non-IDE users (PMs, support engineers) are left out entirely Consistent configuration (which subscription, which resource group) has to be managed per-person We wanted to keep the same tools and the same observability capabilities, but make them accessible to anyone with a browser. The Solution: Host It on App Service The answer turned out to be straightforward: deploy the MCP server itself to Azure App Service, give it a web frontend, and bring its own AI agent along for the ride. Here's what the hosted version adds on top of the local MCP server: Local MCP Server Hosted Web Agent How it works Runs locally, your IDE's AI calls the tools Deployed to Azure App Service with its own AI agent Interface VS Code, Claude Desktop, or any MCP client Browser-based chat UI Agent Your existing AI assistant (Copilot, Claude, etc.) Built-in Azure OpenAI (GPT-5-mini) Azure resources needed None beyond az login App Service, Azure OpenAI, VNet Best for Individual developers in their IDE Teams who want a shared, centralized tool Authentication Your local az login credentials Managed identity + Easy Auth (Entra ID) Deploy npm install && npm run build azd up The key insight: the MCP tools are identical. Both versions use the exact same set of observability tools — the only difference is who's calling them (your IDE's AI vs. the built-in Azure OpenAI agent) and where the server runs (your laptop vs. App Service). What We Built Architecture ┌─────────────────────────────────────────────────────────────────────────────┐ │ Web Browser │ │ React Chat UI — resource selectors, tool steps, markdown responses │ └──────────────────────────────────┬──────────────────────────────────────────┘ │ HTTP (REST API) ▼ ┌─────────────────────────────────────────────────────────────────────────────┐ │ Azure App Service (Node.js 20) │ │ ┌──────────────────────────────────────────────────────────────────────┐ │ │ │ Express Server │ │ │ │ ├── /api/chat → Agent loop (OpenAI → tool calls → respond) │ │ │ │ ├── /api/set-context → Set target app for investigation │ │ │ │ ├── /api/resource-groups, /api/apps → Resource discovery │ │ │ │ ├── /mcp → MCP protocol endpoint (Streamable HTTP) │ │ │ │ └── / → Static SPA (React chat UI) │ │ │ └──────────────────────────────────────────────────────────────────────┘ │ │ VNet Integration (snet-app) │ └─────────────────────────────────────────────────────────────────────────────┘ │ │ │ ▼ ▼ ▼ ┌──────────────┐ ┌───────────────────┐ ┌────────────────────┐ │ Azure OpenAI │ │ Log Analytics / │ │ ARM API / Kudu │ │ (GPT-5-mini) │ │ KQL Queries │ │ (app metadata, │ │ Private EP │ └───────────────────┘ │ container logs) │ └──────────────┘ └────────────────────┘ The Express server does double duty: it serves the React chat UI as static files and exposes the MCP endpoint for remote IDE connections. The agent loop is simple — when a user sends a message, the server calls Azure OpenAI, which may request tool calls, the server executes those tools, and the loop continues until the AI has a final answer. Demo The following screenshots show how this app can be used. The first screenshot shows what happens when you ask about a functioning app. You can see the agent made 5 tool calls and was able to give a thorough summary of the current app's status, recent deployments, as well as provide some recommendations for how to improve observability of the app itself. I expanded the tools section so you could see exactly what the agent was doing behind the scenes and get a sense of how it was thinking. At this point, you can proceed to ask more questions about your app if there were other pieces of information you wanted to pull from your logs. I then injected a fault into this app by initiating a deployment pointing to a config file that didn't actually exist. The goal here was to prove that the agent could correlate an application issue to a specific deployment event, something that currently involves manual effort and deep investigation into logs and source code. Having an agent that can do this for you in a matter of seconds saves so much time and effort that could be directed to more important activities and ensures that you find the issue the first time. A few minutes after initiating the bad deployment, I saw that my app was no longer responding. Rather than going to the logs and investigating myself, I asked the agent "I'm getting an application error now, what happened?" I obviously know what happened and what the source of the error was, but let's see if the agent can pick that up. The agent was able to see that something was wrong and then point me in the direction to address the issue. It ran a number of tool calls following our investigation steps called out in the skills file and was successfully able to identify the source of the error. And lastly, I wanted to confirm the error was associated with the recent deployment, something that our agent should be able to do because we built in the tools it needs to be able to corrleate these kinds of events with errors. I asked it directly and here was the response, exactly what I expected to see. Infrastructure (one command) Everything is defined in Bicep and deployed with the Azure Developer CLI: azd up This provisions: App Service Plan (P0v3) with App Service (Node.js 20 LTS, VNet-integrated) Azure OpenAI (GPT-5-mini, Global Standard) with a private endpoint and private DNS zone VNet (10.0.0.0/16) with dedicated subnets for the app and private endpoints Managed Identity with RBAC roles: Reader, Website Contributor, Log Analytics Reader, Cognitive Services OpenAI User No API keys anywhere. The App Service authenticates to Azure OpenAI over a private network using its managed identity. The Chat UI The web interface is designed to get out of the way and let you focus on investigating: Resource group and app dropdowns — Browse your subscription, pick the app you want to investigate Tool step visibility — A collapsible panel shows exactly which tools the agent called, what arguments it used, and how long each took Session management — Start fresh conversations, with confirmation dialogs when switching context mid-investigation Markdown responses — The agent's answers are rendered with full formatting, code blocks, and tables When you first open the app, it auto-discovers your subscription and populates the resource group dropdown. Select an app, hit "Tell me about this app," and the agent starts investigating. Security Since this app has subscription-wide read access to your App Services and Log Analytics workspaces, you should definitely enable authentication. After deploying, configure Easy Auth in the Azure Portal: Go to your App Service → Authentication Click Add identity provider → select Microsoft Entra ID Set Unauthenticated requests to "HTTP 401 Unauthorized" This ensures only authorized members of your organization can access the tool. The connection to Azure OpenAI is secured via a private endpoint — traffic never traverses the public internet. The app authenticates using its managed identity with the Cognitive Services OpenAI User role. What Stayed the Same This is the part worth emphasizing: the core tools didn't change at all. Whether you're using the local MCP server or the hosted web agent, you get the same 15 tools. The Agent Skill (SKILL.md) from Part 1 also carries over. The hosted agent has the same domain expertise for App Service debugging baked into its system prompt — the same debugging workflows, common error patterns, KQL templates, and SKU reference that make the local version effective. The Bigger Picture: It's Not Just a Web App Here's what makes this interesting beyond our specific implementation: the pattern is the point. We took a set of domain-specific tools (App Service observability), wrapped them in a standard protocol (MCP), and showed two ways to use them: Local MCP server → Your IDE's AI calls the tools Hosted web agent → A deployed app with its own AI calls the same tools But those are just two examples. The same tools could power: A Microsoft Teams bot — Your on-call channel gets an observability assistant that anyone can mention A Slack integration — Same idea, different platform A CLI agent — A terminal-based chat for engineers who live in the command line An automated monitor — An agent that periodically checks your apps and files alerts An Azure Portal extension — Observability chat embedded directly in the portal experience A mobile app — Check on your apps from your phone during an incident The MCP tools are the foundation. The agent and interface are just the delivery mechanism. Build whatever surface makes sense for your team. This is one of the core ideas behind MCP: write the tools once, use them everywhere. The protocol standardizes how AI assistants discover and call tools, so you're not locked into any single client or agent. Try It Yourself Both versions are open-source: Local MCP server (Part 1): github.com/seligj95/app-service-observability-agent Hosted web agent (Part 2): github.com/seligj95/app-service-observability-agent-hosted To deploy the hosted version: git clone https://github.com/seligj95/app-service-observability-agent-hosted.git cd app-service-observability-agent-hosted azd up To run the local version, see the Getting Started section in Part 1. What's Next? This is still a proof-of-concept, and we're continuing to explore how AI-powered observability can become a first-class part of the App Service platform. Some things we're thinking about: More tools — Resource health, autoscale history, certificate expiration, network diagnostics Multi-app investigations — Correlate issues across multiple apps in a resource group Proactive monitoring — Agents that watch your apps and alert you before users notice Deeper integration — What if every App Service came with a built-in observability endpoint? We'd love your feedback. Try it out, open an issue, or submit a PR if you have ideas for additional tools or debugging patterns. And if you build something interesting on top of these MCP tools — a Teams bot, a CLI agent, anything — we'd love to hear about it.Strapi on App Service: Quick start
In this quick start guide, you will learn how to create and deploy your first Strapi site on Azure App Service Linux, using Azure Database for MySQL or PostgreSQL, along with other necessary Azure resources. This guide utilizes an ARM template to install the required resources for hosting your Strapi application.Chat with Your App Service Logs Using GitHub Copilot
The Problem We know that logs and observability on App Service can be tricky—it's feedback we hear from customers all the time. There are many sources of information: Kudu container logs, Log Analytics tables (AppServiceHTTPLogs, ConsoleLogs, PlatformLogs, AppLogs), deployment logs, metrics, and more. It's not always obvious where to look, especially when you're troubleshooting under pressure. Today, debugging production issues often involves: Opening the Azure Portal Figuring out which blade or log source has the information you need Navigating to Log Analytics and remembering (or searching for) the right KQL syntax Interpreting results and manually correlating across multiple log tables Repeating this process until you find the root cause This proof-of-concept is one of our attempts to simplify this experience, using AI to bridge the gap between your question and the answer—no matter where that answer lives. What if you could just ask: "Why did my app stop?" and get an answer without ever having to leave your IDE or terminal? The Solution: App Service Observability MCP Server We've built a proof-of-concept MCP (Model Context Protocol) server that exposes App Service observability tools directly to AI assistants like GitHub Copilot in VS Code. It can be accessed from your preferred IDE like VS Code, or directly in your CLI such as GitHub Copilot CLI or Claude Code. You now don't even have to leave your coding environment to get answers to your App Service issues. Key capabilities: Query logs from Log Analytics (HTTP logs, Console logs, Platform logs) Fetch container logs directly from Kudu (no setup required!) Analyze HTTP errors grouped by status code and endpoint Find slow requests exceeding latency thresholds Diagnose deployment issues — automatically correlate deploys with startup failures and errors Check logging setup — runtime-specific recommendations (Python, Node.js, .NET, Java) View deployment history and correlate with issues Investigate container restarts and identify root causes Demo To see how the tool works, here are a series of screenshots going over a real-world scenario where a deployment issue breaks an app. The first screenshot is from when the app was functioning with no issues. You can see the tool calls one of MCP tools to get the app info. I then asked if there were any issues. It found a couple issues early on, but they were all transient and after reviewing logs and errors, it determined the app was functional. I then introduced a bug into my app and redeployed. I changed the name of a reference to a config file to one that didn't exist, thereby causing the app to crash because it was trying to load a file that didn't exist. GitHub Copilot was easily able to pick up the issue based on the deployment logs tooling. Also, because GitHub Copliot has direct access to my codebase for the app it was analyzing, it was able to see that the file that I was referencing didn't exist and knew what to change it to to get the app working again. This is one of the benefits of running this tool locally alongside your codebase - in addition to the tooling, it can also keep an eye on your codebase. Now if you've ever used GitHub Copilot to help deploy one of your apps, you may know that it can natively make calls using the Azure CLI for example to pull logs. But in my experience, these actions don't always work, take multiple attempts, and take a significant amount of time to complete. With the tooling and skills here, this operation becomes seamless because the agent knows exactly what to do and how to do it. It takes away the guesswork and multiple attempts that an agent without this tool would have to go through. In the following screenshot, I asked why the deployment was taking so long. Usually a deployment with azd for an app like the demo app here takes under a minute, so I wanted it to help me understand what the delay was caused by. Within a couple seconds, it was able to pickup the bug I introduced. Lastly, I then asked it to correlate the error with a deployment. One of the major problem areas our customers have is determining which deployment led to a specific error. We've built a tool into this feature that can correlate deployements and errors. Here's what the tool found. You can see I did a couple deployments with config file names that didn't exist. The tool was able to pinpoint the exact deployments that caused the issue and also tell me what to change to remediate the issue. This is a major benefit that was only possible with the help of AI and it's reasoning capabilities. How It Works The MCP server sits between your AI assistant and Azure, translating natural language requests into API calls: Important: Some tools require Log Analytics diagnostic settings to be enabled, but `get_recent_logs` and `get_deployments` work out of the box by calling Kudu and ARM directly. Security: Your Credentials, Your Access A common question when connecting AI tools to cloud resources: "What access does this have?" The MCP server here uses `DefaultAzureCredential` from the Azure SDK, which means it leverages your existing Azure identity—typically from `az login`. It can only access resources you already have permission to access. There are no stored secrets, no service principals with elevated privileges, and no additional credentials required. In other words: if you could run the investigation yourself in the portal or via Azure CLI, the MCP server can do it. If you don't have access to a resource, neither does the server. This design ensures: No privilege escalation — The AI operates with your exact permissions Existing RBAC applies — Your organization's access controls are respected Audit trail intact — All API calls use your identity and appear in Azure activity logs Looking ahead: For production scenarios with fully autonomous agents (running unattended or on a schedule), you'd want to apply least-privilege principles—create a dedicated service principal or managed identity with only the specific permissions needed (e.g., Reader on the App Service, Log Analytics Reader on the workspace). This limits blast radius and follows security best practices for any automated system accessing cloud resources. The Agent Skill: Domain Expertise for Debugging Beyond just exposing tools, we've included an Agent Skill file (SKILL.md) that gives the AI domain expertise for App Service debugging. What's an Agent Skill? Agent Skills are markdown files that provide structured knowledge to AI assistants. When GitHub Copilot has access to our SKILL.md, it gains: Debugging workflows — Step-by-step approaches for investigating issues Common error patterns — OOM crashes, Always On issues, HTTP 500/503 errors KQL query templates — Ready-to-use queries for each scenario SKU reference — Which features are available on each pricing tier Best practices — How to present findings with actionable recommendations Tools + Knowledge = Better Debugging The MCP tools and Agent Skill work together: Component Role MCP Tools Fetch real data from your Azure resources Agent Skill Interpret results and guide investigations For example, when investigating a container restart, the Agent Skill teaches Copilot to: Check for OOM patterns in platform logs Look for crash loops vs. graceful terminations Consider Always On settings based on the SKU Provide the right `az` command to fix the issue Example: Investigating a Container Stop Here's a real conversation showing AI-assisted debugging: User: "Show me the recent logs" Copilot: calls get_recent_logs 2026-01-30T19:52:42Z Container start method called. 2026-01-30T19:52:43Z Container is running. 2026-01-30T19:52:57Z Site started. 2026-01-30T19:53:17Z Container is terminating. Grace period: 5 seconds. 2026-01-30T19:53:22Z Site stopped. Copilot: The site started but stopped after 20 seconds. Want me to investigate? User: "Please investigate" Copilot: calls check_diagnostics, get_http_errors, query_logs, get_app_info Root Cause: Your container is stopping because "Always On" is disabled. With low traffic (only 14 requests in 24 hours), App Service terminates idle containers to save resources. Evidence: ✅ No errors in platform or application logs ✅ No HTTP 5xx errors Container terminated gracefully (not a crash) Fix: az webapp config set --name your-app --resource-group your-rg --always-on true Note: Requires Basic tier or higher. No portal. No manual KQL. Just ask and get answers. Getting Started Prerequisites Node.js 20+ Azure CLI (`az login` for authentication) VS Code with GitHub Copilot Installation git clone https://github.com/seligj95/app-service-observability-agent.git cd app-service-observability-agent npm install && npm run build Configure VS Code Create `.vscode/mcp.json` in your workspace: { "servers": { "appservice-logs": { "command": "node", "args": ["/path/to/app-service-observability-agent/dist/index.js"], "type": "stdio", "env": { "AZURE_SUBSCRIPTION_ID": "your-subscription-id", "AZURE_RESOURCE_GROUP": "your-resource-group", "AZURE_APP_NAME": "your-app-name" } } } } Reload VS Code, click "Start" next to the server, and start chatting with Copilot about your App Service! What's Next? This is a proof-of-concept demonstrating what an App Service AI observability tool could look like. We're exploring how this pattern could become a first-class feature of the platform. Imagine a future where every App Service has a built-in MCP endpoint for observability: https://my-app.scm.azurewebsites.net/mcp. Stay tuned for part 2 of this blog where we will show how to host this tool on App Service so that not just you, but you're whole team can leverage this tool for your workloads. Try It Out GitHub Repo: github.com/seligj95/app-service-observability-agent Agent Skill: Check out SKILL.md for the debugging knowledge base We'd love your feedback! Use the comments below or open an issue or PR if you have ideas for additional tools or debugging patterns.
Announcing Conversational Diagnostics (Preview) on Windows App Services
We are pleased to announce Conversational Diagnostics (Preview), a new feature in Windows App Services that leverages the powerful capabilities of OpenAI to take your problem-solving to the next level. With this feature, you can engage in a conversational dialogue to accurately identify the issue with your Windows Web Apps, and receive a clear set of solutions, documentation, and diagnostics to help resolve the issue. How to access Conversational Diagnostics (Preview) Navigate to your Windows Web App on the Azure Portal. Select Diagnose and Solve Problems. Select AI Powered Diagnostics (preview) to open chat. What is the tool capable of? Type a question or select any of the sample questions in the options. Types of questions you can ask include but not limited to: Questions regarding a specific issue that your app is experiencing Questions about how-to instructions Questions about best practices The AI-powered Diagnostics runs relevant diagnostic checks and provides a diagnosis of the issue and a recommended solution. Additionally, it can provide documentation addressing your questions. Select View Details for a deep-dive view on the solution and reference to the suggested insight. Launch recommended solutions directly from the chat. Conversational Diagnostics (Preview) remembers the context of the conversation, so you can ask follow-up questions. Once you are done with troubleshooting, you can create a summary of your troubleshooting session by responding to the chat with the message that the issue has been resolved. If you want to start a new investigation, select New Chat. How to sign up for access To get started, sign up for early access to the Conversational Diagnostics (Preview) feature in the Diagnose and Solve Problems experience. Your access request may take up to 4 weeks to complete. Once access is granted, Conversational Diagnostics (Preview) will be available for all the Windows App Service on your subscription. Navigate to your Windows Web App on the Azure Portal. Select Diagnose and Solve Problems. Select Request Access in the announcement banner. Whether you're a seasoned developer or a newcomer to App Services, Conversational Diagnostics (Preview) provides an intuitive and efficient way to understand and tackle any issue you may encounter. You can easily access this feature whenever you need it without any extra configuration. Say goodbye to frustrating troubleshooting and hello to a smarter, more efficient way of resolving issues with App Services. Preview Terms Of Use | Microsoft Azure Microsoft Privacy Statement – Microsoft privacyAnnouncing Public Preview: ASEv3 Outbound Network Segmentation
🗣️ Update 2/3/2026: As of February 3, 2026, the Outbound Network Segmentation feature is now Generally Available. For more information, refer to the documentation. 🔍 What Is Outbound Network Segmentation? Outbound Network Segmentation allows you to define and control how outbound traffic is routed from your App Service Environment v3 apps. This means you can now segment outbound traffic at an app level, enabling fine-grained egress control that aligns with enterprise security policies and compliance requirements. Previously, all outbound traffic from an App Service Environment v3 originated from the full subnet range hosting the App Service Environment, making it difficult for networking teams to apply per-app restrictions, like what is available with the multi-tenant App Service offering. With this new capability, you can now: For each app, define the subnet all outbound traffic is routed through. Assign dedicated outbound IPs per app via NAT Gateways. Route traffic through custom firewalls or appliances. Apply Network Security Groups (NSGs) with greater precision. Improve auditability and compliance for regulated workloads. In an App Service Environment, each worker is assigned an IP from the subnet, but there is no way to group IPs from various apps/plans to allow for routing/blocking/allowing specific app traffic from a networking perspective. With outbound network segmentation, you can now direct various app traffic to the same subnet/virtual network and gain this level of control. For example, consider the following scenario where you would like to ensure that only App A is able to talk to Database A. To ensure only traffic from App A can reach Database A, you join App A to an alternate subnet (vnet-integration-subnet). The alternate subnet has network access to the private endpoint subnet via NSG. This means that only traffic from the virtual network integration subnet can reach the private endpoint subnet, which then gives access to the database. 🧪 What’s Included in the Public Preview? This feature is currently available in all public Azure regions. If you're interested in trying it out, you will need to create a new App Service Environment and enable the following cluster setting during creation. Cluster settings can be configured using an ARM/Bicep template. For guidance on configuring cluster settings, see Custom configuration settings for App Service Environments. "clusterSettings": [ { "name": "MultipleSubnetJoinEnabled", "value": "true" } ] Once the App Service Environment is created and this cluster setting is enabled, you will have access to join apps to alternate subnets at any time. However, if you don't set the cluster setting during creation, the App Service Environment will not support this feature. Enabling this feature on existing App Service Environments is not supported. Portal support for enabling this cluster setting as well as joining alternate subnets is not available at this time. To configure the cluster setting, use an ARM/Bicep template to create the App Service Environment. To join an alternate subnet, you can use the following Azure CLI command. The alternate subnet must be empty and be delegated to Microsoft.web/serverfarms prior to attempting to join it. Also ensure that application traffic routing is enabled for your app. This is key to ensure all traffic is routed through the alternate subnet and not the default route. az webapp vnet-integration add --resource-group <APP-RESOURCE-GROUP> --name <APP-NAME> --vnet <VNET-NAME> --subnet <ALTERNATE-SUBNET-NAME> If your alternate subnet is in a different resource group than your app, run "az webapp vnet-integration add -h" and see the help text to learn how to specify this resource id. 🔧 Tech Specs If you're familiar with the multi-plan subnet join feature available in the multi-tenant App Service offering, unfortunately, App Service Environments and the alternate subnet join feature are incompatible with multi-plan subnet join. For App Service Environments, each app from a given plan can only integrate with 1 alternate subnet. Similar to regular virtual network integration, however, a given plan can have multiple different connections and apps in the same plan can use either of the connections. For multi-tenant App Service, this is limited to 2 connections per plan. For App Service Environment v3, you can have up to 4 connections. If you need to remove or change the alternate subnet join for a specific app, you can do this at any time. First remove the existing join, and then add a new one following the same process as you did previously. 💡 Why This Feature Matters App Service Environment v3 has always been about isolation, scalability, and control. With outbound segmentation, we’re taking that control to the next level. Whether you're running high-scale web apps, handling sensitive data, or managing complex environments, this feature gives you the tools to secure outbound traffic without compromising performance. 📚 Learn More To dive deeper into App Service Environment v3 networking capabilities, check out the App Service Environment v3 networking overview. Have questions or feedback? Drop them in the comments below.Announcing the Public Preview of the New App Service Quota Self-Service Experience
Update 10/30/2025: The App Service Quota Self-Service experience is back online after a short period where we were incorporating your feedback and making needed updates. As this is public preview, availability and features are subject to change as we receive and incorporate feedback. What’s New? The updated experience introduces a dedicated App Service Quota blade in the Azure portal, offering a streamlined and intuitive interface to: View current usage and limits across the various SKUs Set custom quotas tailored to your App Service plan needs This new experience empowers developers and IT admins to proactively manage resources, avoid service disruptions, and optimize performance. Quick Reference - Start here! If your deployment requires quota for ten or more subscriptions, then file a support ticket with problem type Quota following the instructions at the bottom of this post. If any subscription included in your request requires zone redundancy (note that most Isolated v2 deployments require ZR), then file a support ticket with problem type Quota following the instructions at the bottom of this post. Otherwise, leverage the new self-service experience to increase your quota automatically. Self-service Quota Requests For non-zone-redundant needs, quota alone is sufficient to enable App Service deployment or scale-out. Follow the provided steps to place your request. 1. Navigate to the Quotas resource provider in the Azure portal 2. Select App Service (Pubic Preview) Navigating the primary interface: Each App Service VM size is represented as a separate SKU. If the intention is to be able to scale up or down within a specific offering (e.g., Premium v3), then equivalent number of VMs need to be requested for each applicable size of that offering (e.g., request 5 instances for both P1v3 and P3v3). As with other quotas, you can filter by region, subscription, provider, or usage. Note that your portal will now show "App Service (Public Preview)" for the Provider name. You can also group the results by usage, quota (App Service VM type), or location (region). Current usage is represented as App Service VMs. This allows you to quickly identify which SKUs are nearing their quota limits. Adjustments can be made inline: no need to visit another page. This is covered in detail in the next section. Total Regional VMs: There is a SKU in each region called Total Regional VMs. This SKU summarizes your usage and available quota across all individual SKUs in that region. There are three key points about using Total Regional VMs. You should never request Total Regional VMs quota directly - it will automatically increase in response to your request for individual SKU quota. If you are unable to deploy a given SKU, then you must request more quota for that SKU to unblock deployment. For your deployment to succeed, you must have sufficient quota in the individual SKU as well as Total Regional VMs. If either usage is at its respective limit, then you will be unable to deploy and must request more of that individual SKU's quota to proceed. In some regions, Total Regional VMs appears as "0 of 0" usage and limit and no individual SKU quotas are shown. This is an indication that you should not interact with the portal to resolve any quota-related issues in this region. Instead, you should try the deployment and observe any error messages that arise. If any error messages indicate more quota is needed, then this must be requested by filing a support ticket with problem type Quota following the instructions at the bottom of this post so that App Service can identify and fix any potential quota issues. In most cases, this will not be necessary, and your deployment will work without requesting quota wherever "0 of 0" is shown for Total Regional VMs and no individual SKU quotas are visible. See the example below: 3. Request quota adjustments Clicking the pen icon opens a flyout window to capture the quota request: The quota type (App Service SKU) is already populated, along with current usage. Note that your request is not incremental: you must specify the new limit that you wish to see reflected in the portal. For example, to request two additional instances of P1v2 VMs, you would file the request like this: Click submit to send the request for automatic processing. How quota approvals work: Immediately upon submitting a quota request, you will see a processing dialog like the one shown: If the quota request can be automatically fulfilled, then no support request is needed. You should receive this confirmation within a few minutes of submission: If the request cannot be automatically fulfilled, then you will be given the option to file a support request with the same information. In the example below, the requested new limit exceeds what can be automatically granted for the region: 4. If applicable, create support ticket When creating a support ticket, you will need to repopulate the Region and App Service plan details; the new limit has already been populated for you. If you forget the region or SKU that was requested, you can reference them in your notifications pane: If you choose to create a support ticket, then you will interact with the capacity management team for that region. This is a 24x7 service, so requests may be created at any time. Once you have filed the support request, you can track its status via the Help + support dashboard. Known issues The self-service quota request experience for App Service is in public preview. Here are some caveats worth mentioning while the team finalizes the release for general availability: Closing the quota request flyout window will stop meaningful notifications for that request. You can still view the outcome of your quota requests by checking actual quota, but if you want to rely on notifications for alerts, then we recommend leaving the quota request window open for the few minutes that it is processing. Some SKUs are not yet represented in the quota dashboard. These will be added later in the public preview. The Activity Log does not currently provide a meaningful summary of previous quota requests and their outcomes. This will also be addressed during the public preview. As noted in the walkthrough, the new experience does not enable zone-redundant deployments. Quota is an inherently regional construct, and zone-redundant enablement requires a separate step that can only be taken in response to a support ticket being filed. Quota API documentation is being drafted to enable bulk non-zone redundant quota requests without requiring you to file a support ticket. Filing a Support Ticket If your deployment requires zone redundancy or contains many subscriptions, then we recommend filing a support ticket with issue type "Technical" and problem type "Quota": We want your feedback! If you notice any aspect of the experience that does not work as expected, or you have feedback on how to make it better, please use the comments below to share your thoughts!Announcing the Public Preview of the New Hybrid Connection Manager (HCM)
Update May 28, 2025: The new Hybrid Connection Manager is now Generally Available. The download links shared in this post will give you the latest Generally Available version. Learn more Key Features and Improvements The new version of HCM introduces several enhancements aimed at improving usability, performance, and security: Cross-Platform Compatibility: The new HCM is now supported on both Windows and Linux clients, allowing for seamless management of hybrid connections across different platforms, providing users with greater flexibility and control. Enhanced User Interface: We have redesigned the GUI to offer a more intuitive and efficient user experience. In addition to a new and more accessible GUI, we have also introduced a CLI that includes all the functionality needed to manage connections, especially for our Linux customers who may solely use a CLI to manage their workloads. Improved Visibility: The new version offers enhanced logging and connection testing, which provides greater insight into connections and simplifies debugging. Getting Started To get started with the new Hybrid Connection Manager, follow these steps: Requirements: Windows clients must have ports 4999-5001 available Linux clients must have port 5001 available Download and Install: The new HCM can be downloaded from the following links. Ensure you download the version that corresponds to your client. If you are new to the HCM, check out the existing documentation to learn more about the product and how to get started. If you are an existing Windows user, installing the new Windows version will automatically upgrade your existing version to the new version, and all your existing connections will be automatically ported over. There is no automated migration path from the Windows to the Linux version at this time. Windows download Download the MSI package and follow the installation instructions Linux download From your terminal running as administrator, follow these steps: sudo apt update sudo apt install tar gzip build-essential sudo wget "https://download.microsoft.com/download/HybridConnectionManager-Linux.tar.gz" sudo tar -xf HybridConnectionManager-Linux.tar.gz cd HybridConnectionManager/ sudo chmod 755 setup.sh sudo ./setup.sh Once that is finished, your HCM is ready to be used Run `hcm help` to see the available commands For interactive mode, you will need to install and login to the Azure CLI. Authentication from the HCM to Azure is done using this credential. Install the Azure CLI with: `install azure cli: curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash` Run `az login` and follow the prompts Add your first connection by running `hcm add` Configure Your Connections: Use the GUI or the CLI to add hybrid connections to your local machine. Manage Your Connections: Use the GUI or the CLI with the `hcm list` and `hcm remove` commands to manage your hybrid connections efficiently. Detailed help texts are available for each command to assist you. Join the Preview We invite you to join the public preview and provide your valuable feedback. Your insights will help us refine and improve the Hybrid Connections Manager to better meet your needs. Feedback and Support If you encounter any issues or have suggestions, please reach out to hcmsupport@service.microsoft.com or leave a comment on this post. We are committed to ensuring a smooth and productive experience with the new HCM. Detailed documentation and guidance will be available in the coming weeks as we get closer to General Availability (GA). Thank you for your continued support and collaboration. We look forward to hearing your thoughts and feedback on this exciting new release.Exciting Updates Coming to Conversational Diagnostics (Public Preview)
Last year, at Ignite 2023, we unveiled Conversational Diagnostics (Preview), a revolutionary tool integrated with AI-powered capabilities to enhance problem-solving for Windows Web Apps. This year, we're thrilled to share what’s new and forthcoming for Conversational Diagnostics (Preview). Get ready to experience a broader range of functionalities and expanded support across various Azure Products, making your troubleshooting journey even more seamless and intuitive.Proactive Cloud Ops with SRE Agent: Scheduled Checks for Cloud Optimization
The Cloud Optimization Challenge Your cloud environment is always changing: New features ship weekly Traffic patterns shift seasonally Costs creep up quietly Security best practices evolve Teams spin up resources and forget them It's Monday morning. You open the Azure portal. Everything looks... fine. But "fine" isn't great. That VM has been at 8% CPU for weeks. A Key Vault secret expires in 12 days. Nothing's broken. But security is drifting, costs are creeping, and capacity gaps are growing silently. The question isn't "is something broken?" it's "could this be better?" Four Pillars of Cloud Optimization Pillar What Teams Want The Challenge Security Stay compliant, reduce risk Config drift, legacy settings, expiring creds Cost Spend efficiently, justify budget Hard to spot waste across 100s of resources Performance Meet SLOs, handle growth Know when to scale before demand hits Availability Maximize uptime, build resilience Hidden dependencies, single points of failure Most teams check these sometimes. SRE Agent checks them continuously. Enter SRE Agent + Scheduled tasks SRE Agent can pull data from Azure Monitor, resource configurations, metrics, logs, traces, errors, cost data and analyze it on a schedule. If you use tools outside Azure (Datadog, PagerDuty, Splunk), you can connect those via MCP servers so the agent sees your full observability stack. My setup uses Azure-native sources. Here's how I wired it up. How I Set It Up: Step by Step Step 1: Create SRE Agent with Subscription Access I created an SRE Agent without attaching it to any specific resource group. Instead, I gave it Reader access at the subscription level. This lets the agent scan across all my resource groups for optimization opportunities. No resource group configuration needed. The agent builds a knowledge graph of everything VMs, storage accounts, Key Vaults, NSGs, web apps across the subscription. Step 2: Create and Upload My Organization Practices I created an org-practices.md file that defines what "good" looks like for my team: I uploaded this to SRE Agent's knowledge base. Now the agent knows our bar, not just Azure defaults. 👉 See my full org-practices.md Source repos for this demo: security-demoapp - App with intentional security misconfigurations costoptimizationapp - App with cost optimization opportunities Step 3: Connect to Teams Channel I connected SRE Agent to my team's Teams channel so findings land where we already work. Critical findings get immediate notifications. Warnings go into a daily digest. No more logging into separate dashboards. The insights come to us. Step 4: Connect Resource Groups to GitHub Repos Add the two resource groups to the SRE Agent and link the apps to their corresponding GitHub repos: Resource Group GitHub Repository rg-security-opt-demo security-demoapp rg-cost-opt-sreademo costoptimizationapp This enables the agent to create GitHub issues for findings linking violations directly to the repo responsible for that infrastructure. Step 5: Test with Prompts Before setting up automation, I tested the agent with manual prompts to make sure it was finding the right issues. The agent ran the checks, compared against my org-practices.md, and identified the issues. Security Check: Scan resource group "rg-security-opt-demo" for any violations of our security practices defined in org-practices.md in your knowledge base. list violations with severity and remediation steps. Make sure to check against all critical requirements and send message in teams channel with your findings and create an issue in the github repo https://github.com/dm-chelupati/security-demoapp.git Cost Check: Scan resource group "rg-cost-opt-sreademo" for any violations of our costpractices defined in org-practices.md in your knowledge base. list violations with severity and remediation steps. Make sure to check against all critical requirements and send message in teams channel with your findings and create an issue in the github repo https://github.com/dm-chelupati/costoptimizationapp.git Step 6: Check Output via GitHub Issues After running prompts, I checked GitHub. The agent had created issues. Each issue has the root cause, impact, and fix ready for the team to action or for Coding Agent to pick up and create a PR. 👉 See the actual issues created: Security findings issue Cost findings issue Step 7: Set Up Scheduled Triggers This is where it gets powerful. I configured recurring schedules: Weekly Security Check (Wednesdays 8 AM): Create a scheduled trigger that performs security practices checks against the org practices in knowledge base org-practices.md, creates github issue and send teams message on a weekly basis Wednesdays at 8 am UTC Weekly Cost Review (Mondays 8 AM): Create a scheduled trigger that performs cost practices checks against the org practices in knowledge base org-practices.md, creates github issue and send teams message on a weekly basis on Mondays at 8 am UTC Now optimization runs automatically. Every week, fresh findings land in GitHub Issues and Teams. Why Context Makes the SRE Agent Powerful Think about hiring a new SRE. They're excellent at their craft—they know Kubernetes, networking, Azure inside out. But on day one, they can't solve problems in your environment yet. Why? They don't have context: What are your SLOs? What's "acceptable" latency for your app? When do you rotate secrets? Monthly? Quarterly? Before each release? Which resources are production-critical vs. dev experiments? What's your tagging policy? Who owns what? How do you deploy? GitOps? Pipelines? Manual approvals? A great engineer becomes your great engineer once they learn how your team operates. SRE Agent works the same way. Out of the box, it knows Azure resource types, networking, best practices. But it doesn't know your bar. Is 20% CPU utilization acceptable or wasteful? Should secrets expire in 30 days or 90? Are public endpoints ever okay, or never? The more context you give the agent, your SLOs, your runbooks, your policies, the more it reasons like a team member who understands your environment, not just Azure in general. That's why Step 2 matters so much. When I uploaded our standards, the agent stopped checking generic Azure best practices and started checking our best practices. Bring your existing knowledge: You don't have to start from scratch. If your team's documentation already lives in Atlassian Confluence, SharePoint, or other tools, you can connect those via MCP servers. The agent pulls context from where your team already works, no need to duplicate content. Why This Matters Before this setup, optimization was a quarterly thing. Now it happens automatically: Before After Check security when audit requests it Daily automated posture check Find waste when finance complains Weekly savings report in Teams Discover capacity issues during incidents Scheduled headroom analysis Expire credentials and debug at 2 AM 30-day warning with exact secret names Optimization isn't a project anymore. It's a practice. Try It Yourself Create an SRE Agent with access to your subscription Upload your team's standards (security policies, cost thresholds, tagging rules) Set up a scheduled trigger, start with a daily security check Watch the first report land in Teams See what you've been missing while everything looked "fine." Learn More Azure SRE Agent documentation Azure SRE Agent blogs Azure SRE Agent community Azure SRE Agent home page Azure SRE Agent pricing Azure SRE Agent is currently in preview. Get StartedAI Transcription & Text Analytics for Health
Industry Challenge Healthcare organizations depend on qualitative research, patient interviews, and clinical documentation to improve care delivery. Traditional transcription services often create bottlenecks: Manual Processes: Require manual uploads and lack automation. Delayed Turnaround: Transcripts can take days, slowing research and decision-making. Limited Integration: Minimal interoperability with EMR systems or analytics platforms. Cost Inefficiencies: Pricing models that scale poorly for large volumes. The need for real-time, HIPAA-compliant transcription and integrated analytics has never been greater. Azure AI Solution Overview Azure provides a comprehensive, cloud-native transcription and analytics pipeline that addresses these challenges head-on. By leveraging Azure AI Services, organizations can: Transcribe audio/video recordings in real time. Process PDFs and text documents for structured data extraction. Apply Text Analytics for Health to identify medical entities and structure data into FHIR format. Generate summaries and insights using cutting edge LLMs including Azure OpenAI. This approach accelerates workflows, improves compliance, and reduces costs compared to traditional transcription vendors. Azure Speech Service Options Azure Speech Service offers multiple transcription modes to fit different scenarios: Real-Time Transcription: Converts live audio streams into text instantly for telehealth sessions and interviews. Batch Transcription: Processes large volumes of pre-recorded audio asynchronously for research studies. Fast Transcription: Optimized for quick turnaround on short recordings for rapid documentation needs. Azure Text Analytics for Health One of the most powerful components of this solution is Azure AI Language – Text Analytics for Health, which transforms raw text into structured clinical insights. Key capabilities include: Named Entity Recognition (NER): Automatically identifies clinical entities such as symptoms, diagnoses, medications, procedures, and anatomy from transcripts and documents. Relation Extraction: Detects relationships between entities (e.g., linking a medication to its dosage or a condition to its treatment), enabling richer context for clinical decision-making. Entity Linking to UMLS Codes: Maps recognized entities to Unified Medical Language System (UMLS) concepts, ensuring interoperability and standardization across healthcare systems. Assertion Detection: Determines the status of an entity (e.g., present, absent, conditional, or hypothetical), which is critical for accurate interpretation of patient data. These features allow healthcare organizations to move beyond simple transcription and unlock structured, actionable insights that can feed downstream analytics and reporting. Other Azure Resources Azure AI Document Intelligence – Extracts structured data from PDFs and scanned documents. Azure OpenAI Service – Summarizes transcripts and generates clinical insights. Azure Storage & Functions – Securely stores raw and processed data; orchestrates workflows for transcription and analytics. Integration with Microsoft Fabric OneLake Once FHIR JSON output is generated from Text Analytics for Health, it can be stored in Microsoft Fabric OneLake. This unlocks powerful downstream capabilities: Unified Data Lake: Centralized storage for structured healthcare data. Analytics & Reporting: Use Fabric’s Lakehouse and Power BI to build dashboards for clinical research trends, patient outcomes, and operational metrics. AI-Driven Insights: Combine transcription data with other datasets for predictive modeling and advanced analytics. This integration ensures that transcription and clinical insights are not siloed—they become part of a broader data ecosystem for research and decision-making. Why Azure Stands Out Compared to other transcription solutions in the market, Azure offers: Real-Time Processing: Immediate access to transcripts versus multi-day turnaround. Integrated Analytics: Built-in medical entity recognition and AI summarization. Compliance & Security: HIPAA-ready architecture with enterprise-grade governance. Cost Efficiency: Pay-as-you-go pricing with elastic scaling for large datasets. End-to-End Data Flow: From transcription to Fabric OneLake for analytics. Step-by-Step Deployment Guide As part of the Azure Field team working in the Healthcare and Life Sciences industry, this challenge has emerged as a common theme among organizations seeking to modernize transcription and analytics workflows. To assist organizations exploring Azure AI solutions to address these challenges, the following demo application was developed by Solution Engineer Samuel Tauil and Cloud & AI Platform Specialist Hannah Abbott. This application is intended to allow organizations to quickly stand up and test these Azure services for their needs and is not intended as a production-ready solution. This Azure-powered web application demonstrates how organizations can modernize transcription and clinical insights using cloud-native AI services. Users can upload audio files in multiple formats, which are stored in Azure Storage and trigger an Azure Function to perform speech-to-text transcription with speaker diarization. The transcript is then enriched through Azure Text Analytics for Health, applying advanced capabilities like named entity recognition, relation extraction, UMLS-based entity linking, and assertion detection to deliver structured clinical insights. Finally, Azure OpenAI generates a concise summary and a downloadable clinical report, while FHIR-compliant JSON output seamlessly integrates with Microsoft Fabric OneLake for downstream analytics and reporting—unlocking a complete, scalable, and secure solution for healthcare data workflows. The following video clip uses AI-generated dialog for a fictitious scenario to demonstrate the capabilities of the sample application. Sample application developed by Samuel Tauil Microsoft Solution Engineer (25) Samuel Tauil | LinkedIn Prerequisites Azure Subscription GitHub account Azure CLI installed locally (optional, for manual deployment) 1. Fork the Repository GitHub - samueltauil/transcription-services-demo: Azure Healthcare Transcription Services Demo - Speech-to-text with Text Analytics for Health for HIPAA-compliant medical transcription 2. Create Azure Service Principal for GitHub Actions Copy the JSON output. 3. Add GitHub Secrets (Settings → Secrets and variables → Actions): AZURE_CREDENTIALS: Paste the service principal JSON from step 2 4. Run the deployment workflow: Go to Actions tab → "0. Deploy All (Complete)" Click "Run workflow" Enter your resource group name and Azure region Click "Run workflow" 5. After infrastructure deploys, add these additional secrets: AZURE_FUNCTIONAPP_NAME: The function app name (shown in workflow output) AZURE_STATIC_WEB_APPS_API_TOKEN: Get from Azure Portal → Static Web App → Manage deployment token Benefits Accelerated Research: Reduce transcription time from days to minutes. Enhanced Accuracy: AI-driven entity recognition for clinical terms. Scalable & Secure: Built on Azure’s compliance-ready infrastructure. Analytics-Ready: Seamless integration with Fabric for reporting and insights. Reference Links: Transcription Service: Speech to text overview - Speech service - Foundry Tools | Microsoft Learn Batch transcription overview - Speech service - Foundry Tools | Microsoft Learn Speech to text quickstart - Foundry Tools | Microsoft Learn Real-time diarization quickstart - Speech service - Foundry Tools | Microsoft Learn Text Analytics: Watch this: Embedded Video | Microsoft Learn What is the Text Analytics for health in Azure Language in Foundry Tools? - Foundry Tools | Microso… Fast Healthcare Interoperability Resources (FHIR) structuring in Text Analytics for health - Foundr… azure-ai-docs/articles/ai-services/language-service/text-analytics-for-health/quickstart.md at main… AI Foundry: Model catalog - Azure AI Foundry
