Extend SRE Agent with MCP: Build an Agentic Workflow to Triage Customer Issues
Your inbox is full. GitHub issues piling up. "App not working." "How do I configure alerts?" "Please add dark mode." You open each one, figure out what it is, ask for more info, add labels, route to the right team. An hour later, you're still sorting issues. Sound familiar? The Triage Tax Every L1 support engineer, PM, and on-call developer who's handled customer issues knows this pain. When tickets come in, you're not solving problems, you're sorting them. Read the issue. Is it a bug or a question? Check the docs. Does this feature exist? Ask for more info. Wait two days. Re-triage. Add labels. Route to engineering. It's tedious. It requires judgment, you need to understand the product, know what info is needed, check documentation. And honestly? It's work that nobody volunteers for but someone has to do. In large organizations, it gets even more complex. The issue doesn't just need to be triaged, it needs to be routed to the right engineering team. Is this an auth issue? Frontend? Backend? Infrastructure? A wrong routing decision means delays, re-assignments, and frustrated customers. What if an AI agent could do this for you? Enter Azure SRE Agent + MCP Here's what I built: I gave SRE Agent access to my GitHub and PagerDuty accounts via MCP, uploaded my triage rubric as a markdown file, and set it to run twice a day. No more reading every ticket manually. No more asking the same "please provide more info" questions. No more morning triage sessions. What My Setup Looks Like My app's customer issues come in through GitHub. My team uses PagerDuty to track bugs and incidents. So I connected both via MCP to the SRE Agent. I also uploaded my triage logic as a .md file on how to classify issues, what info is required for each category, which labels to use, which team handles what. And since I didn't want to run this workflow manually, I set up a scheduled task to trigger it twice a day. Now it just runs. I verify its work if I want to. What the Agent Does Fetches all open, unlabeled GitHub issues Reads each issue and classifies it (bug, doc question, feature request) Checks if required info is present Posts a comment asking for details if needed, or acknowledges the issue Adds appropriate labels Creates a PagerDuty incident for bugs ready for engineering Moves to the next issue How I Built It: Step by Step Let me walk you through exactly how I set this up inside SRE Agent. Step 1: Create an SRE Agent I created a new SRE Agent in the Azure portal. Since this workflow triages GitHub issues and not Azure resources, I didn't need to configure any Azure resource groups or subscriptions. Just an agent. Step 2: Connect MCP Servers I added two MCP servers to give the agent access to my tools: GitHub MCP– Fetch issues, post comments, add labels PagerDuty MCP – Create incidents for bugs that need dev team's attention MCP (Model Context Protocol) lets you bring any API into the agent. If your tool has an API, you can connect it. Step 3: Create Subagents I created two focused subagents, each with a specific job and only the tools it needs: GitHub Issue Triager "You are expert in triaging GitHub issues, classifying them into categories such as user needs to supply additional information, bug, documentation question, or feature request. Use the knowledge base to search for the right document that helps you with performing this triaging. Perform all actions autonomously without waiting for user input. Hand off to Incident Creator for the issues you classified as bugs." Tools: GitHub MCP (issues, labels, comments) Incident Creator Here "You are expert in managing incidents in PagerDuty, listing services, incidents, creating incidents with all details. Once done, hand off back to GitHub Issue Triager." Tools: PagerDuty MCP (services, incidents) The handoff between them creates a workflow. They collaborate without human involvement. Step 4: Add Your Knowledge I uploaded my triage logic as a .md file to the agent's knowledge base. This is my rubric - my mental model for how to triage issues: How do I classify bugs vs. doc questions vs. feature requests? What info is required for each category? What labels do I use? When should an incident be created? Which team handles which type of issue? I wrote it down the way I'd explain it to a new teammate. The agent searches and follows it. Step 5: Add a Scheduled Task I didn't want to trigger this workflow manually every time. SRE Agent supports scheduled tasks, workflows that run automatically on a cadence. I set up a trigger to run twice a day: morning and evening. Now the workflow is fully automated. Here is the end to end automated agentic workflow to triage customer tickets. Why MCP Matters Every team uses different tools. Maybe your customer issues live in Zendesk, incidents go to ServiceNow and you use Jira or Azure DevOps. SRE Agent doesn't lock you in. With MCP, you connect to whatever tools you already use. The agent orchestrates across them. That's the extensibility model: your tools, your workflow, orchestrated by the agent. The Result Before: 2 hours every morning sorting tickets. After: By the time anyone logs in, issues are labeled, missing-info requests are posted, urgent bugs have incidents, and feature requests are acknowledged. Your team can finally focus on the complex stuff not sorting tickets. Why This Matters Faster response times. Issues get acknowledged in minutes, not days. Consistent classification. No "this should have been a P1" moments. No tickets bouncing between teams. Happier customers. They get a response immediately even if it's just "we're looking into it." Focus on what matters. Your team should be solving problems, not sorting them. The Bottom Line Triage isn't the job, it's the tax on the job. It quietly eats the hours your team could spend building, debugging, and shipping. You don't need to build a custom triage bot. You don't need to wire up webhooks and write glue code. You give the SRE agent your tools, your logic, and a schedule and it handles the sorting. Use GitHub? Connect GitHub. Use Zendesk? Connect Zendesk. PagerDuty, ServiceNow, Jira - whatever your team runs on, the agent meets you there. Stop sorting tickets. Start shipping. A Few Tips Test MCP endpoints before configuring them in the SRE agent Give each subagent only the tools it needs, don't enable everything Start read-only until you trust the classification, then enable comments Do You Still Want to Triage Issues Manually? What tools does your team use to track customer-reported issues and incidents? Let us know in the comments, we'd love to hear how you'd use this workflow with your stack. Is triage your most toilsome workflow or is there something even worse eating your team's time? Let us know in the comments.
Fix It Before They Feel It: Higher Reliability with Proactive Mitigation
What if your infrastructure could detect performance issues and fix them automatically—before your users even notice? This blog brings that vision to life using Azure SRE Agent, an AI-powered autonomous agent that monitors, detects, and remediates production issues in real-time. 💡 The magic: Zero human intervention required. The agent handles detection, diagnosis, remediation, and reporting—all autonomously. 📺 Watch the Demo This content was presented at .NET Day 2025. Watch the full session to see Azure SRE Agent in action: 🎬 Fix it before they feel it - .NET Day 2025 🎯 What You'll See in This Demo Watch as we intentionally deploy "bad" code to production and observe how the SRE Agent: Detects the degradation — Compares live response times against learned baselines Takes autonomous action — Executes a slot swap to roll back to healthy code Communicates the incident — Posts to Teams and creates a GitHub issue Generates reports — Summarizes deployment metrics for stakeholders 🚀 Key Capabilities Capability What It Shows Proactive Baseline Learning Agent learns normal response times and stores them in a knowledge base Real-time Anomaly Detection Instant comparison of current vs. baseline metrics Autonomous Remediation Agent executes Azure CLI commands to swap slots without human approval Cross-platform Communication Automatic Teams posts and GitHub issue creation Incident Reporting End-of-day email summaries with deployment health metrics Architecture Overview The solution uses Azure SRE Agent with three specialized sub-agents working together: Components Application Layer: .NET 9 Web API running on Azure App Service Application Insights for telemetry collection Azure Monitor Alerts for incident triggers Azure SRE Agent: AvgResponseTime Sub-Agent: Captures baseline metrics every 15 minutes, stores in Knowledge Store DeploymentHealthCheck Sub-Agent: Triggered by deployment alerts, compares metrics to baseline, auto-remediates DeploymentReporter Sub-Agent: Generates daily summary emails from Teams activity External Integrations: GitHub (issue creation, semantic code search, Copilot assignment) Microsoft Teams (deployment summaries) Outlook (summary reports) What the SRE Agent Does When a deployment occurs, the SRE Agent autonomously performs the following actions: 1. Health Check (DeploymentHealthCheck Sub-Agent) When a slot swap alert fires, the agent: Queries App Insights for current response times Retrieves the baseline from the Knowledge Store Compares current performance against baseline If degradation > 20%: Executes rollback and creates GitHub issue If healthy: Posts confirmation to Teams Healthy Deployment - No Action Needed (Teams Post): The agent confirms the deployment is healthy — response time (22ms) is 80% faster than baseline (116ms). Degraded Deployment - Automatic Rollback (Teams Post): The agent detects +332% latency regression (212ms vs 116ms baseline), executes a slot swap to rollback, and creates GitHub Issue. 2. Daily Summary (DeploymentReporter Sub-Agent) Every 24 hours, the reporter agent: Reads all Teams deployment posts from the last 24 hours Aggregates deployment metrics Sends an executive summary email Daily Summary (Outlook Email): The daily report shows 9 deployments, 6 healthy, 3 rollbacks, and 3 GitHub issues created — complete with response time details and issue links. Demo Flow View Step-by-Step Instructions → Step Action Step 1 Deploy Infrastructure + Applications Step 2 Create Sub-Agents, Triggers & Schedules Step 3 Swap bad code, watch agent remediate Setting Up the Demo Prerequisites Azure subscription with Contributor access Azure CLI installed and logged in (az login) .NET 9.0 SDK PowerShell 7.0+ Step 1: Deploy Infrastructure cd scripts .\1-setup-demo.ps1 -ResourceGroupName "sre-demo-rg" -AppServiceName "sre-demo-app-12345" This script will: Prompt for Azure subscription selection Deploy Azure infrastructure (App Service, App Insights, Alerts) Build and deploy healthy code to production Build and deploy problematic code to staging Full Setup Instructions → Step 2: Configure Azure SRE Agent Navigate to Azure SRE Agents Portal Sub Agent builder tab and create three sub-agents: Sub-Agent Purpose Tools Used AvgResponseTime Captures baseline response time metrics QueryAppInsightsByAppId, UploadKnowledgeDocument DeploymentHealthCheck Detects degradation and executes remediation SearchMemory, QueryAppInsights, PostTeamsMessage, CreateGithubIssue, Az CLI commands DeploymentReporter Generates deployment summary reports GetTeamsMessages, SendOutlookEmail Creating Each Sub-Agent In the Github links below you can find gif images that capture the creation flow AvgResponseTime + Baseline Task: Detailed Instructions → DeploymentHealthCheck + Swap Alert: Detailed Instructions → DeploymentReporter + Reporter Task: Detailed Instructions → Step 3: Run the Demo .\2-run-demo.ps1 This triggers the following flow: Slot Swap Occurs (demo script) ▼ Activity Log Alert Fires ▼ Incident Trigger Activated ▼ DeploymentHealthCheck Agent Runs ─ Queries current response time from App Insights ─ Retrieves baseline from knowledge store ─ Compares (if >20% degradation) ─ Executes: az webapp deployment slot swap ─ Creates GitHub issue (if degraded) ─ Posts to Teams channel Full Demo Instructions → Demo Timeline Time Event 0:00 Run 2-run-demo.ps1 0:30 Swap staging → production (bad code deployed) 1:00 Production now slow (~1500ms vs ~50ms baseline) ~5:00 Slot Swap Alert fires ~5:04 Agent executes slot swap (rollback) ~5:30 Production restored to healthy state ~6:00 Agent posts to Teams, creates GitHub issue How the Performance Toggle Works The app has a compile-time toggle in ProductsController.cs: private const bool EnableSlowEndpoints = false; // false = fast, true = slow The setup script creates two versions: Production: EnableSlowEndpoints = false → ~50ms responses Staging: EnableSlowEndpoints = true → ~1500ms responses (artificial delay) Get Started 🔗 Full source code and instructions: github.com/microsoft/sre-agent/samples/proactive-reliability 🔗 Azure SRE Agent documentation: https://learn.microsoft.com/en-us/azure/sre-agent/ Technology Stack Framework: ASP.NET Core 9.0 Infrastructure: Azure Bicep Monitoring: Application Insights + Log Analytics Automation: Azure SRE Agent Scripts: PowerShell 7.0+ Tags: Azure, SRE Agent, DevOps, Reliability, .NET, App Service, Application Insights, Autonomous RemediationAnnouncing 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!Stop Running Runbooks at 3 am: Let Azure SRE Agent Do Your On-Call Grunt Work
Your pager goes off. It's 2:47am. Production is throwing 500 errors. You know the drill - SSH into this, query that, check these metrics, correlate those logs. Twenty minutes later, you're still piecing together what went wrong. Sound familiar? The On-Call Reality Nobody Talks About Every SRE, DevOps engineer, and developer who's carried a pager knows this pain. When incidents hit, you're not solving problems - you're executing runbooks. Copy-paste this query. Check that dashboard. Run these az commands. Connect the dots between five different tools. It's tedious. It's error-prone at 3am. And honestly? It's work that doesn't require human creativity but requires human time. What if an AI agent could do this for you? Enter Azure SRE Agent + Runbook Automation Here's what I built: I gave SRE Agent a simple markdown runbook containing the same diagnostic steps I'd run manually during an incident. The agent executes those steps, collects evidence, and sends me an email with everything I need to take action. No more bouncing between terminals. No more forgetting a step because it's 3am and your brain is foggy. What My Runbook Contains Just the basics any on-call would run: az monitor metrics – CPU, memory, request rates Log Analytics queries – Error patterns, exception details, dependency failures App Insights data – Failed requests, stack traces, correlation IDs az containerapp logs – Revision logs, app configuration That's it. Plain markdown with KQL queries and CLI commands. Nothing fancy. What the Agent Does Reads the runbook from its knowledge base Executes each diagnostic step Collects results and evidence Sends me an email with analysis and findings I wake up to an email that says: "CPU spiked to 92% at 2:45am, triggering connection pool exhaustion. Top exception: SqlException (1,832 occurrences). Errors correlate with traffic spike. Recommend scaling to 5 replicas." All the evidence. All the queries used. All the timestamps. Ready for me to act. How to Set This Up (6 Steps) Here's how you can build this yourself: Step 1: Create SRE Agent Create a new SRE Agent in the Azure portal. No Azure resource groups to configure. If your apps run on Azure, the agent pulls context from the incident itself. If your apps run elsewhere, you don't need Azure resource configuration at all. Step 2: Grant Reader Permission (Optional) If your runbooks execute against Azure resources, assign Reader role to the SRE Agent's managed identity on your subscription. This allows the agent to run az commands and query metrics. Skip this if your runbooks target non-Azure apps. Step 3: Add Your Runbook to SRE Agent's Knowledge base You already have runbooks, they're in your wiki, Confluence, or team docs. Just add them as .md files to the agent's knowledge base. To learn about other ways to link your runbooks to the agent, read this Step 4: Connect Outlook Connect the agent to your Outlook so it can send you the analysis email with findings. Step 5: Create a Subagent Create a subagent with simple instructions like: "You are an expert in triaging and diagnosing incidents. When triggered, search the knowledge base for the relevant runbook, execute the diagnostic steps, collect evidence, and send an email summary with your findings." Assign the tools the agent needs: RunAzCliReadCommands – for az monitor, az containerapp commands QueryLogAnalyticsByWorkspaceId – for KQL queries against Log Analytics QueryAppInsightsByResourceId – for App Insights data SearchMemory – to find the right runbook SendOutlookEmail – to deliver the analysis Step 6: Set Up Incident Trigger Connect your incident management tool - PagerDuty, ServiceNow, or Azure Monitor alerts and setup the incident trigger to the subagent. When an incident fires, the agent kicks off automatically. That's it. Your agentic workflow now looks like this: This Works for Any App, Not Just Azure Here's the thing: SRE Agent is platform agnostic. It's executing your runbooks, whatever they contain. On-prem databases? Add your diagnostic SQL. Custom monitoring stack? Add those API calls. The agent doesn't care where your app runs. It cares about following your runbook and getting you answers. Why This Matters Lower MTTR. By the time you're awake and coherent, the analysis is done. Consistent execution. No missed steps. No "I forgot to check the dependencies" at 4am. Evidence for postmortems. Every query, every result, timestamped and documented. Focus on what matters. Your brain should be deciding what to do not gathering data. The Bottom Line On-call runbook execution is the most common, most tedious, and most automatable part of incident response. It's grunt work that pulls engineers away from the creative problem-solving they were hired for. SRE Agent offloads that work from your plate. You write the runbook once, and the agent executes it every time, faster and more consistently than any human at 3am. Stop running runbooks. Start reviewing results. Try it yourself: Create a markdown runbook with your diagnostic queries and commands, add it to your SRE Agent's knowledge base, and let the agent handle your next incident. Your 3am self will thank you.Build Long-Running AI Agents on Azure App Service with Microsoft Agent Framework
UPDATE 10/22/2025: An alternative implementation of this sample app has been added to this blog post. The alternate version uses a WebJob for background processing instead of an in-process hosted service. WebJobs are a great alternative for background processing in App Service, providing better separation of concerns, independent restarts, and dedicated logging. To learn more about WebJobs on App Service, see the Azure App Service WebJobs documentation. The AI landscape is evolving rapidly, and with the introduction of Microsoft Agent Framework, developers now have a powerful platform for building sophisticated AI agents that go far beyond simple chat completions. These agents can execute complex, multi-step workflows with persistent state, conversation threads, and structured execution—capabilities that are essential for production AI applications. Today, we're excited to share how Azure App Service provides an excellent platform for running Agent Framework workloads, especially those involving long-running operations. Let's explore why App Service is a great choice and walk through a practical example. 🔗 Quick link to sample app GitHub repo: https://github.com/Azure-Samples/app-service-agent-framework-travel-agent-dotnet 🔗 Quick link to WebJob sample app GitHub repo: https://github.com/Azure-Samples/app-service-agent-framework-travel-agent-dotnet-webjob The Challenge: Long-Running Agent Framework Flows Agent Framework enables AI agents to perform complex tasks that can take significant time to complete: Multi-turn reasoning: Iterative calls to large language models (LLMs) where each response informs the next prompt Tool integration: Function calling and external API interactions for real-time data Complex processing: Budget calculations, content optimization, multi-phase generation Persistent context: Maintaining conversation state across multiple interactions These workflows often take 30 seconds to several minutes to complete—far too long for synchronous HTTP request handling. Traditional web applications run into several constraints: ⏱️ Timeout Limitations: HTTP requests have timeout constraints (typically 30-230 seconds) ⚠️ Connection Issues: Clients may disconnect due to network interruptions or browser navigation 📈 Scalability Concerns: Long-running requests block worker threads and don't survive app restarts 🎯 Poor User Experience: Users see endless loading spinners with no progress feedback The Solution: Async Pattern with App Service Azure App Service provides a robust solution through the asynchronous request-reply pattern combined with background processing: API immediately returns (202 Accepted) with a task ID Background worker processes the Agent Framework workflow Client polls for status with real-time progress updates Durable state storage (Cosmos DB) maintains task status and results This pattern ensures: ✅ No HTTP timeouts—API responds in milliseconds ✅ Resilient to restarts—state survives deployments and scale events ✅ Progress tracking—users see real-time updates (10%, 45%, 100%) ✅ Better scalability—background workers process independently NOTE! This pattern can be implemented with either an in-process BackgroundService or as a separate WebJob process. Deployment Patterns: BackgroundService vs WebJob The following compares the two deployment options you have for this implementation. BackgroundService Pattern: ✅ Simpler deployment (single project) ✅ Shared process and memory ✅ Good for moderate workloads ⚠️ API and worker restart together WebJob Pattern (alternative): ✅ Separate processes (API + WebJob) ✅ Independent restart without API downtime ✅ Dedicated WebJob monitoring in portal ✅ Better for production operations ⚠️ Slightly more complex deployment (manual WebJob upload) Either of these options are a great way to help you get started with implementing long-running processes on App Service. To learn more about WebJobs on App Service, see the Azure App Service WebJobs documentation. Rapid Innovation Support The AI landscape is changing at an unprecedented pace. New models, frameworks, and capabilities are released constantly. Azure App Service's managed platform ensures your applications can adapt quickly without infrastructure rewrites: Framework Updates: Deploy new Agent Framework SDK versions like any application update Model Upgrades: Switch between GPT-4, GPT-4o, or future models with configuration changes Scaling Patterns: Start with combined API+worker, split into separate apps as needs grow New Capabilities: Integrate emerging AI services without changing hosting infrastructure App Service handles the platform complexity so you can focus on building great AI experiences. Sample Application: AI Travel Planner To demonstrate this pattern, we've built a Travel Planner application that uses Agent Framework to generate detailed, multi-day travel itineraries. The agent performs complex reasoning including: Researching destination attractions and activities Optimizing daily schedules based on location proximity Calculating detailed budget breakdowns Generating personalized travel tips and recommendations The entire application runs on a single P0v4 App Service with both the API and background worker combined—showcasing App Service's flexibility for hosting diverse workload patterns in one deployment. Key Architecture Components Azure App Service (P0v4 Premium) Hosts both REST API and background worker in a single app "Always On" feature keeps background worker running continuously Managed identity for secure, credential-less authentication Azure Service Bus Decouples API from long-running Agent Framework processing Reliable message delivery with automatic retries Dead letter queue for error handling Azure Cosmos DB Stores task status with real-time progress updates Automatic 24-hour TTL for cleanup Rich query capabilities for complex itinerary data Azure AI Foundry Hosts persistent agents with conversation threads Structured execution with Agent Framework runtime GPT-4o model for intelligent travel planning One of the powerful features of using Azure AI Foundry with Agent Framework is the ability to inspect agents and conversation threads directly in the Azure portal. This provides valuable visibility into what's happening during execution. Viewing Agents and Threads in Azure AI Foundry When you submit a travel plan request, the application creates an agent in Azure AI Foundry. You can navigate to your AI Foundry project in the Azure portal to see: Agents The application creates an agent for each request Important: Agents are **automatically deleted** after the itinerary is generated to keep your project clean Tip: You'll need to be quick! Navigate to Azure AI Foundry right after submitting a request to see the agent in action Once processing completes, the agent is removed as part of the cleanup process Conversation Threads Unlike agents, threads persist even after the agent completes You can view the complete conversation history at any time See the exact prompts sent to the model and the responses generated Useful for debugging, understanding agent behavior, and improving prompts The ephemeral nature of agents (created per request, deleted after completion) keeps your Azure AI Foundry project clean while the persistent threads give you full traceability of every interaction. Alternative Architecture: WebJob Pattern The alternate version of this app uses a WebJob for background processing instead of an in-process hosted service. However, just a single App Service is still required. WebJobs are a great alternative for background processing in App Service, providing better separation of concerns, independent restarts, and dedicated logging. To learn more about WebJobs on App Service, see the Azure App Service WebJobs documentation. Get Started Today The complete Travel Planner application is available as a reference implementation so you can quickly get started building your own apps with Agent Framework on App Service. Try one or both of these today! 🔗 GitHub Repository for background process version: https://github.com/Azure-Samples/app-service-agent-framework-travel-agent-dotnet 🔗 GitHub Repository for WebJob version: https://github.com/Azure-Samples/app-service-agent-framework-travel-agent-dotnet-webjob The repo includes: Complete .NET 9 source code with Agent Framework integration Infrastructure as Code (Bicep) for automated deployment Web UI with real-time progress tracking Comprehensive README with deployment instructions Deploy in minutes: git clone https://github.com/Azure-Samples/app-service-agent-framework-travel-agent-dotnet.git cd app-service-agent-framework-travel-agent-dotnet azd auth login azd up IMPORTANT! For the WebJob version, you will also need to manually deploy the WebJob. See the instructions in the README to learn how to do this. Key Takeaways ✅ Agent Framework enables sophisticated AI agents beyond simple chat completions ✅ Long-running workflows (30s-minutes) require async patterns to avoid timeouts ✅ App Service provides a simple, cost-effective platform for these workloads ✅ Async request-reply pattern with Service Bus + Cosmos DB ensures reliability ✅ Rapid innovation in AI is supported by App Service's adaptable platform Whether you're building travel planners, document processors, research assistants, or other AI-powered applications, Azure App Service gives you the flexibility and reliability you need—without the complexity of container orchestration or function programming models. What's Next? Build on This Foundation This Travel Planner is just the starting point—a foundation to help you understand the patterns and architecture. Agent Framework is designed to grow with your needs, making it easy to add sophisticated capabilities with minimal effort: 🛠️ Add Tool Calling Connect your agent to real-time APIs for weather, flight prices, hotel availability, and actual booking systems. Agent Framework's built-in tool calling makes this straightforward. 🤝 Implement Multi-Agent Systems Create specialized agents (flight expert, hotel specialist, activity planner) that collaborate to build comprehensive travel plans. Agent Framework handles the orchestration. 🧠 Enhance with RAG Add retrieval-augmented generation to give your agent deep knowledge of destinations, local customs, and insider tips from your own content library. 📊 Expand Functionality Real-time pricing and availability Interactive refinement based on user feedback Personalized recommendations from past trips Multi-language support for global users The beauty of Agent Framework is that these advanced features integrate seamlessly into the pattern we've built. Start with this sample, explore the Agent Framework documentation, and unlock powerful AI capabilities for your applications! Learn More Microsoft Agent Framework Documentation Azure App Service Documentation Async Request-Reply Pattern Azure App Service WebJobs documentation Have you built AI agents on App Service? We'd love to hear about your experience! Share your thoughts in the comments below. Questions about Agent Framework on App Service? Drop a comment and our team will help you get started.Call Function App from Azure Data Factory with Managed Identity Authentication
Integrating Azure Function Apps into your Azure Data Factory (ADF) workflows is a common practice. To enhance security beyond the use of function API keys, leveraging managed identity authentication is strongly recommended. Given the fact that many existing guides were outdated with recent updates to Azure services, this article provides a comprehensive, up-to-date walkthrough on configuring managed identity in ADF to securely call Function Apps. The provided methods can also be adapted to other Azure services that need to call Function Apps with managed identity authentication. The high level process is: Enable Managed Identity on Data Factory Configure Microsoft Entra Sign-in on Azure Function App Configure Linked Service in Data Factory Assign Permissions to the Data Factory in Azure Function Step 1: Enable Managed Identity on Data Factory On the Data Factory’s portal, go to Managed Identities, and enable a system assigned managed identity. Step 2: Configure Microsoft Entra Sign-in on Azure Function App 1. Go to Function App portal and enable Authentication. Choose "Microsoft" as the identity provider. 2. Add an app registration to the app, it could be an existing one or you can choose to let the platform create a new app registration. 3. Next, allow the ADF as a client application to authenticate to the function app. This step is a new requirement from previous guides. If these settings are not correctly set, the 403 response will be returned: Add the Application ID of the ADF managed identity in Allowed client application and Object ID of the ADF managed identity in the Allowed identities. If the requests are only allowed from specific tenants, add the Tenant ID of the managed identity in the last box. 4. This part sets the response from function app for the unauthenticated requests. We should set the response as "HTTP 401 Unauthorized: recommended for APIs" as sign-in page is not feasible for API calls from ADF. 5. Then, click next and use the default permission option. 6. After everything is set, click "Add" to complete the configuration. Copy the generated App (client) id, as this is used in data factory to handle authorization. Step 3: Configure Linked Service in Data Factory 1. To use an Azure Function activity in a pipeline, follow the steps here: Create an Azure Function activity with UI 2. Then Edit or New a Azure Function Linked Service. 3. Change authentication method to System Assigned Managed Identity, and paste the copied client ID of function app identity provider from Step 2 into Resource ID. This step is necessary as authorization does not work without this. Step 4: Assign Permissions to the Data Factory in Azure Function 1. On the function app portal, go to Access control (IAM), and Add a new role assignment. 2. Assign reader role. 3. Assign the Data Factory’s Managed Identity to that role. After everything is set, test that the function app can be called from Azure Data Factory successfully. Reference: https://prodata.ie/2022/06/16/enabling-managed-identity-authentication-on-azure-functions-in-data-factory/ https://learn.microsoft.com/en-us/azure/data-factory/control-flow-azure-function-activity https://docs.azure.cn/en-us/app-service/overview-authentication-authorizationAnnouncing 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.Industry-Wide Certificate Changes Impacting Azure App Service Certificates
Executive Summary In early 2026, industry-wide changes mandated by browser applications and the CA/B Forum will affect both how TLS certificates are issued as well as their validity period. The CA/B Forum is a vendor body that establishes standards for securing websites and online communications through SSL/TLS certificates. Azure App Service is aligning with these standards for both App Service Managed Certificates (ASMC, free, DigiCert-issued) and App Service Certificates (ASC, paid, GoDaddy-issued). Most customers will experience no disruption. Action is required only if you pin certificates or use them for client authentication (mTLS). Who Should Read This? App Service administrators Security and compliance teams Anyone responsible for certificate management or application security Quick Reference: What’s Changing & What To Do Topic ASMC (Managed, free) ASC (GoDaddy, paid) Required Action New Cert Chain New chain (no action unless pinned) New chain (no action unless pinned) Remove certificate pinning Client Auth EKU Not supported (no action unless cert is used for mTLS) Not supported (no action unless cert is used for mTLS) Transition from mTLS Validity No change (already compliant) Two overlapping certs issued for the full year None (automated) If you do not pin certificates or use them for mTLS, no action is required. Timeline of Key Dates Date Change Action Required Mid-Jan 2026 and after ASMC migrates to new chain ASMC stops supporting client auth EKU Remove certificate pinning if used Transition to alternative authentication if the certificate is used for mTLS Mar 2026 and after ASC validity shortened ASC migrates to new chain ASC stops supporting client auth EKU Remove certificate pinning if used Transition to alternative authentication if the certificate is used for mTLS Actions Checklist For All Users Review your use of App Service certificates. If you do not pin these certificates and do not use them for mTLS, no action is required. If You Pin Certificates (ASMC or ASC) Remove all certificate or chain pinning before their respective key change dates to avoid service disruption. See Best Practices: Certificate Pinning. If You Use Certificates for Client Authentication (mTLS) Switch to an alternative authentication method before their respective key change dates to avoid service disruption, as client authentication EKU will no longer be supported for these certificates. See Sunsetting the client authentication EKU from DigiCert public TLS certificates. See Set Up TLS Mutual Authentication - Azure App Service Details & Rationale Why Are These Changes Happening? These updates are required by major browser programs (e.g., Chrome) and apply to all public CAs. They are designed to enhance security and compliance across the industry. Azure App Service is automating updates to minimize customer impact. What’s Changing? New Certificate Chain Certificates will be issued from a new chain to maintain browser trust. Impact: Remove any certificate pinning to avoid disruption. Removal of Client Authentication EKU Newly issued certificates will not support client authentication EKU. This change aligns with Google Chrome’s root program requirements to enhance security. Impact: If you use these certificates for mTLS, transition to an alternate authentication method. Shortening of Certificate Validity Certificate validity is now limited to a maximum of 200 days. Impact: ASMC is already compliant; ASC will automatically issue two overlapping certificates to cover one year. No billing impact. Frequently Asked Questions (FAQs) Will I lose coverage due to shorter validity? No. For App Service Certificate, App Service will issue two certificates to span the full year you purchased. Is this unique to DigiCert and GoDaddy? No. This is an industry-wide change. Do these changes impact certificates from other CAs? Yes. These changes are an industry-wide change. We recommend you reach out to your certificates’ CA for more information. Do I need to act today? If you do not pin or use these certs for mTLS, no action is required. Glossary ASMC: App Service Managed Certificate (free, DigiCert-issued) ASC: App Service Certificate (paid, GoDaddy-issued) EKU: Extended Key Usage mTLS: Mutual TLS (client certificate authentication) CA/B Forum: Certification Authority/Browser Forum Additional Resources Changes to the Managed TLS Feature Set Up TLS Mutual Authentication Azure App Service Best Practices – Certificate pinning DigiCert Root and Intermediate CA Certificate Updates 2023 Sunsetting the client authentication EKU from DigiCert public TLS certificates Feedback & Support If you have questions or need help, please visit our official support channels or the Microsoft Q&A, where our team and the community can assist you.Announcing Public Preview of Managed Instance on Azure App Service
Today at Ignite 2025, we announced the Public Preview of a fantastic new capability which will enable customers to move applications to Azure App Service faster, and with minimal, if any, code changes! Azure App Service is a fully managed PaaS platform for hosting web applications, APIs, and mobile backends, enabling customers to deploy and scale applications securely without managing infrastructure. Azure App Service offers built-in compliance, identity and DevOps integration, making it ideal for cloud-native and modernization scenarios where agility, scalability, and operational efficiency are critical. Managed Instance on App Service builds on and extends these capabilities to solve many of the challenges customers have with migration and modernizing legacy and complex enterprise applications. Challenges with Migration and Modernization We have been listening intently to our customers and working on solutions to address their needs when migrating and modernizing applications, particularly .NET Framework applications, to Azure and specifically Azure App Service. Customers face clear challenges when migrating and modernizing applications Application Dependencies – Many apps rely on components that can’t easily migrate to App Service, such as libraries installed on the web worker, GAC entries, Windows Services, or OS-level features. Configuration Systems – Some apps heavily depend on reading/writing settings in the Windows Registry. File I/O – Legacy apps often require local disk access or network storage via mapped drives. Reduced Access & Tooling – Migration limits direct infrastructure access and familiar troubleshooting tools. Lengthy Migration & ROI Challenges – Complex code changes, testing, and issue resolution can make projects take months, delaying return on investment. How Managed Instance on Azure App Service addresses these challenges Managed Instance on Azure App Service addresses these challenges by providing a host of new functionality: - Configuration scripts – Provide a zip file containing all your dependencies with an accompanying PowerShell script to install and configure your dependencies. Store this in Azure Storage and securely access and retrieve using Managed Identity. - Registry adapters – Write to the App Service Plan instance’s windows registry, providing values using secrets stored and secured in Key Vault using Managed Identity. - Storage mounts – Map Azure Files, SMB File shares in your network and local temporary storage volumes using drive letter or drive letter and folder mappings, any credentials or storage connection strings are securely retrieved via Managed Identity from Key Vault secrets. - RDP to instances using Azure Bastion – for the first time ever, open a remote desktop session directly to your App Service Plan instances securely using Azure Bastion and use tools you’re familiar with such as IIS Manager, Event Viewer and Windows Feature MMC Snap-in tools. - Shortens time to migrate and modernize – Reduces the amount of cases where code changes might be needed in order to successfully migrate and modernize, shortening the time and cost to realize return on investment moving to the cloud. All of these features expand on top of the already rich set of capabilities within Azure App Service which enable rapid scale, network integration and security, combined with the new Premium v4 (Announcing General Availability of Premium v4 for Azure App Service | Microsoft Community Hub) series of pricing plans offering enhanced performance, scalability and cost efficiency. Key Scenarios: Technical and Business Perspectives 1. Lift-and-Improve Legacy Applications Technical: Migrate legacy .NET apps with hardcoded file paths, COM dependencies, or registry access—no major code rewrites required. Install custom components directly on the managed instance. Business: Accelerate cloud adoption, reduce migration friction, and preserve business continuity by avoiding costly re-platforming projects. Realize Azure App Service benefits (scaling, patching, high availability) with minimal disruption. 2. Re-platforming Hard-to-Modernize Apps Technical: Move applications with unavailable or hard-to-modify source code, or those tightly coupled to infrastructure (e.g., SMTP servers, MSMQ, legacy middleware). Managed Instance removes blockers by supporting custom installers and advanced networking. Business: Unlock value from legacy systems, extend their useful life, and enable phased modernization. Reduce risk and cost by avoiding “big bang” transformations. 3. Hybrid and Regulated Workloads Technical: Integrate securely with on-premises resources using VNETs and private endpoints. Enforce data residency and access controls with Bring Your Own Storage and Managed Identity. Business: Meet compliance and regulatory requirements for industries like finance, healthcare, and government. Streamline audits and reduce operational overhead for sensitive workloads. 4. Incremental Modernization Technical: Start with “lift-and-shift,” then incrementally adopt PaaS features—DevOps automation, dynamic scaling, centralized configuration—at your own pace. Business: Future-proof your application portfolio, drive ongoing innovation, and maximize ROI by continuously improving applications without major disruptions. Next Steps We’re delighted to be able to announce Managed Instance on Azure App Service and are eager to see it speed up and solve problems in your modernization journey. Moving your workloads to Managed Instance on Azure App Service open up new opportunities for you to add business value and securely integrate with other Azure services. Get started with Managed Instance on Azure App Service with our documentation and check out our Technical Deep Dive on Managed Instance on Azure App Service at Ignite 2025
