Tag Archives: Cloud Computing

Anatomy of an Agent Loop in Azure Logic Apps

Posted on by
1

Part 2 of 7 in the Logic Apps Agent Loop series

Part 1 explained why the Azure Logic Apps agent loop is a different design paradigm from conventional workflow automation. This post gets hands-on with the anatomy of that loop. We will look at the four building blocks that make up every agent loop trigger, instructions, connected model, and tools, and walk through how to wire them together in a Standard logic app.

By the end of this post you will have a working autonomous agent that accepts a prompt from a trigger, reasons over it using Azure OpenAI, invokes a connector action as a tool, and returns a result. The run history will show you exactly how the loop iterated.

The Azure Logic Apps agent loop: four building blocks

Before opening the designer, it helps to have a clear mental model of what you are assembling. Every Azure Logic Apps agent loop consists of four parts.

Trigger

The trigger starts the workflow, exactly as it does in any nonagentic Logic Apps workflow. For an autonomous agent, this can be any supported trigger an HTTP request, a timer, a Service Bus message, a new email, or anything else in the connector library. The trigger’s output becomes the initial input to the agent: the prompt or data the model will reason over.

Instructions

Instructions are the system prompt for the agent. You provide them as a block of natural language text in the agent action’s configuration pane. They define the agent’s role, what it can and cannot do, how it should respond, and any constraints it should observe. A well-written instructions block is the single most important factor in how well the agent performs. Think of it as the job description you hand to the model at the start of every run.

Connected model

The agent needs a language model to reason with. In Standard Logic Apps, you connect the agent to an Azure OpenAI Service resource and specify the model deployment to use — typically a GPT-4o deployment. The agent sends the instructions, the trigger input, and the results of any tool calls to the model at each iteration of the loop. The model’s response tells the agent what to do next.

Tools

A tool is a sequence of one or more connector actions that the agent can choose to invoke. You build tools directly in the Logic Apps designer by adding actions from the connector gallery inside the agent action. Each tool gets a name and a description — the model uses these to decide which tool to call and when. A single agent can have multiple tools. An agent with no tools can still respond to prompts using the model’s built-in knowledge, but it cannot take action on external systems.

The diagram below shows how these four parts fit together inside a single agent loop execution.

Anatomy of an Azure Logic Apps agent loop — trigger, instructions, model, and tools
Figure 1 — Every Azure Logic Apps agent loop consists of four building blocks: a trigger that starts the workflow, instructions that define the agent’s role, a connected model (Azure OpenAI / GPT-4o) that reasons over each iteration, and tools built from connector actions. The loop cycles through Think, Act, and Observe until the model determines the task is complete.

Building your first agent loop in Azure Logic Apps

The demo for this post is deliberately simple: an agent that receives a topic via an HTTP trigger, uses Azure OpenAI to generate a summary, and returns the result to the caller. One trigger, one model, one tool is enough to see all four building blocks in action and to read a meaningful run history.

Prerequisites

  • A Standard logic app resource deployed in Azure
  • An Azure OpenAI Service resource with a GPT-4o model deployment
  • Contributor access to both resources

Step 1: Create the workflow

In the Azure portal, open your Standard logic app and select Workflows from the sidebar. Choose Add, then select Autonomous Agents as the workflow type. Give the workflow a name and select Stateful. Logic Apps creates a new workflow with an empty agent action already in place.

Step 2: Configure the trigger

The autonomous agent workflow template starts with a When a HTTP request is received trigger by default. Leave the method as POST. In the request body JSON schema, add a single property: topic of type string. This is the input the agent will work with.

Step 3: Write the instructions

Select the agent action in the designer to open its configuration pane. On the Parameters tab, find the Instructions field. Enter something like the following:

You are a research assistant. When given a topic, use the available tools to retrieve relevant information and return a concise summary of no more than three sentences. Always cite your source.

Keep instructions specific and bounded. Vague instructions produce unpredictable behaviour. The model will take the instructions literally, so precision matters.

Step 4: Connect the model

Still on the Parameters tab, select Add connection under the model configuration section. Choose Azure OpenAI Service, select your resource, and choose your GPT-4o deployment. Logic Apps establishes the connection and stores it against the workflow.

Step 5: Add a tool

Inside the agent action, select Add a tool. This opens the connector gallery filtered to actions that can be used as tools. For this demo, add the HTTP action as a tool — name it search_web, give it the description “Retrieves content from a given URL”, and configure it to accept a URL as input. In a production scenario you would use Azure AI Search or a more capable connector here; the HTTP action keeps the demo self-contained.

Step 6: Save and run

Save the workflow. Use a REST client to POST a JSON body like {"topic": "Azure Logic Apps agent loop"} to the workflow’s trigger URL. The agent fires, the model reasons over the instructions and the topic, invokes the search tool, and returns a summary.

Logic Apps designer view of an autonomous agent workflow. The canvas shows an HTTP request trigger connected to an Agent action containing a Tool with an HTTP action inside. The right pane shows the Agent parameters: AI model set to GPT-4o via Foundry Models, instructions for the research assistant role, and the topic dynamic value wired as user instructions item 1.
Figure 2 — The completed agent configuration in the Logic Apps designer. The Agent action is connected to GPT-4o via Foundry Models, the instructions define the research assistant role and output format, and the topic value from the HTTP trigger is passed in as the user instruction. The Tool contains a single HTTP action that the agent can invoke to retrieve content from a given URL.

Reading the run history

he run history is where the Azure Logic Apps agent loop becomes visible. Open the workflow’s Run history and select the latest run. You will see the trigger, followed by the agent action. Expand the agent action and you will find each iteration of the loop shown as a numbered step: the model’s reasoning output, the tool call with its inputs and outputs, and the model’s decision on whether to loop again or return a final answer.

This is the key difference from a nonagentic run history. In a conventional workflow, the run history shows a flat list of actions. In an agent loop, it shows a nested, iterative structure the model’s chain of thought made visible.

Run history of a Logic Apps autonomous agent workflow completed in 9.21 seconds, showing the HTTP trigger, a first agent iteration that invoked the HTTP tool in 3.7 seconds, and a second agent iteration that sent the final chat message.
Figure 3 — The run history of the minimal autonomous agent from this post. The loop ran two iterations: the first agent step (3.9s) reasoned over the topic prompt and invoked the HTTP tool (0.6s); the second agent step (3.2s) observed the result and composed the final response. The canvas shows iteration 1 of 3 steps — trigger, tool, and HTTP action — all succeeded in 9.21 seconds total.

For a simple prompt, you may see a single iteration. For a more complex task involving multiple tool calls, you will see the loop unfold across three, five, or more steps. Each step shows exactly what the model decided and why.

Standard versus Consumption: model connections

In Standard logic apps, you configure the model connection yourself — selecting an Azure OpenAI Service resource and specifying the deployment. This gives you full control over which model version you use, where it is hosted, and how it is secured via Managed Identity.

In Consumption logic apps (currently in public preview), the model connection is handled via Microsoft Foundry and the configuration is more constrained. For any production workload, Standard remains the right choice.

What comes next

The agent in this post is autonomous it runs without human interaction, triggered by an HTTP call and returning a result when done. That covers a wide range of integration scenarios, but not all of them. Some tasks require a back-and-forth with a user: a support conversation, a guided data-entry flow, a multi-turn research session.

The next part will cover exactly that distinction, autonomous versus conversational agentic workflows, and walk through when to choose each pattern and what changes in the designer when you do.

Why the Agent Loop Changes Everything in Azure Logic Apps

Posted on by
1

Part 1 of 7 in the Logic Apps Agent Loop series

The Azure Logic Apps agent loop introduces a fundamentally different way to design workflows on the platform. While conventional Logic Apps workflows follow a fixed sequence of steps defined at design time, the agent loop delegates reasoning to a large language model at runtime, looping through think, act, and observe cycles until a task is complete. This post opens a seven-part series on building agentic workflows in Logic Apps. It starts with the question that matters most: why does this change anything?

For years, Azure Logic Apps has been the platform of choice for integration architects who need to orchestrate business processes across cloud services and on-premises systems. You build a workflow, wire up triggers and actions, define your conditions, handle your errors, deploy, and move on. The flow is predictable (deterministic): given the same inputs, it does the same thing every time. That predictability is the point.

The agent loop breaks that contract, deliberately and usefully.

With the introduction of agentic workflows in Azure Logic Apps, Microsoft has extended the platform from a fixed automation engine into something that can reason, adapt, and decide. At its core, the agent loop drives this shift. It is a repeating process: the connected language model thinks through a problem, selects a tool, acts on the result, and decides whether the task is done.Unlike a conventional workflow, there is no hardcoded sequence of steps. Instead, the model determines the path based on the task.

This post is the opening of a seven-part series on building agentic workflows in Azure Logic Apps. Before going hands-on with triggers, connectors, and multi-agent patterns in later posts, this one makes the case for why the agent loop matters and what it fundamentally changes about how you think about workflow design.

How the Azure Logic Apps agent loop differs from nonagentic workflows

Nonagentic Logic Apps workflows are excellent at exactly the kind of work they were designed for: stable, predictable, repeatable processes. An approval workflow, an ETL pipeline, and a B2B message exchange are all scenarios where the path through the workflow is known in advance. The trigger fires, the conditions evaluate, the actions execute in sequence, and the run history tells you exactly what happened and why.

The challenge arises when the environment you are integrating with is unstable or unpredictable. When incoming data is unstructured. Or when the right action depends on context that cannot be captured in a condition expression. Or when you need to handle a customer query that could go a dozen different directions depending on what the customer actually says.

These are the cases where deterministic workflows buckle. You end up building sprawling switch-case structures, hardcoding edge cases as branches, and constantly patching the workflow every time a new variation appears. The workflow becomes a maintenance problem rather than a solution.

Agentic workflows excel in dynamic environments where unexpected events occur, the choice of the right tool relies on the input, and the system must manage unstructured data without specific instructions for each variant.

The agent loop: Think, Act, Learn

How the agent loop works: Think, Act, Learn

The Azure Logic Apps agent loop follows a three-step process.

Think. The agent collects available information: task instructions, prior inputs, and previous tool results. It then passes all of this to the connected language model.The model reasons over the context and decides what to do next: invoke a tool, ask a follow-up question, or return a final answer.

Act. In Logic Apps, tools are actions drawn from 400+ connectors. These include Azure OpenAI, Azure AI Search, Office 365, and custom APIs. Once the action runs, the result feeds back into the next cycle.

Optionally, the loop adapts. The agent can use feedback or external signals to adjust its behaviour over time, though this is the most advanced capability and not required for most workflows.

Iterations, not instructions

This loop continues think, act, observe, decide until the model determines the task is complete. You can change the number of iterations as needed. A simple query might resolve in one loop. A complex multi-step task might require five or ten.

The diagram below shows the difference between a conventional non-agentic workflow, which follows a linear sequence of predetermined steps, and the agent loop, which dynamically iterates until the model determines that the task is complete.

Figure 1 — A conventional nonagentic workflow follows a fixed path defined at design time (left). The agent loop iterates dynamically at runtime: the LLM thinks, acts, observes the result, and decides whether to loop again or return a final answer (right).

Agent versus nonagentic: a structural comparison

The difference is not just philosophical. It shows up in how you design, deploy, and maintain the workflow.

In a nonagentic workflow, the logic architect owns the decision tree. Every branch, every condition, every action path is explicitly modelled. This is powerful for known, bounded scenarios, but it places all the reasoning burden on the architect at design time.

In an agentic workflow, the reasoning is delegated to the model at runtime. The architect’s job shifts: instead of modelling every path, you define the agent’s instructions, give it the right tools, and trust the model to navigate the task. This is a different skill and a different mindset closer to prompt engineering and system design than to traditional workflow modelling.

The Microsoft documentation puts it plainly: agentic workflows can adapt to environments where unexpected events happen, choose which tools to use based on prompts and available data, and handle unstructured data at a level of flexibility that nonagentic workflows simply cannot match. Moreover, nonagentic workflows function best in stable environments with static, predictable, repetitive tasks.

Neither is universally better. They address different problems. But for integration architects, the arrival of the agent loop means Logic Apps can now cover territory that previously required a custom-coded application or a fully separate agent framework.

Standard versus Consumption: what you need to know now

Azure Logic Apps offers two hosting models: Standard (single-tenant, runs on Azure Functions runtime) and Consumption (multitenant, pay-per-execution). Agentic workflows are fully available in Standard. Consumption support is in public preview as of early 2026 and carries some restrictions.

For production agentic workloads, Standard is the right choice today. The rest of this series will use Standard throughout, with notes where the Consumption behaviour differs.

What this series covers

The seven posts in this series move from concept to production:

  1. Why the agent loop changes everything — this post
  2. Anatomy of an agent loop — instructions, the connected model, tool calls, and how the loop iterates
  3. Autonomous versus conversational workflows — choosing between unattended execution and human-in-the-loop patterns
  4. Building tools for the agent — connectors, custom connectors, and MCP servers as tool providers
  5. Multi-agent patterns — handoffs, orchestrators, and sequential agent loops
  6. Securing agentic workflows — authentication, the expanded caller surface, and Easy Auth
  7. Observability, pricing, and running in production — Application Insights, agent loop pricing, and DevOps deployment

The next post gets hands-on: we will look at the anatomy of a single agent loop in the Logic Apps designer, walk through the instructions pane, wire up Azure OpenAI as the model, and watch the run history to see how the iterations unfold.

AWS European Sovereign Cloud Launches—But Does It Solve the Real Problem?

Posted on by
Reply

Earlier, AWS officially launched its European Sovereign Cloud, backed by a €7.8 billion investment in Brandenburg, Germany. The infrastructure is physically and logically separated from AWS global regions, managed by a new German parent company (AWS European Sovereign Cloud GmbH), and staffed exclusively by EU residents. On paper, it checks every compliance box for data residency and operational sovereignty. AWS CEO Matt Garman called it “a big bet” for the company, and it is. The question is whether it’s the right bet for Europe.

European Sovereign Cloud: Real Isolation, Real Trade-offs

The technical separation is genuine. An AWS engineer who deployed services to the European Sovereign Cloud confirmed on Hacker News that proper boundaries exist—U.S.-based engineers can’t see anything happening in the sovereign cloud. To fix issues there, they play “telephone” with EU-based engineers. The infrastructure uses the partition name *aws-eusc* and the region name *eusc-de-east-1*, which are completely separate from AWS’s global regions. All components, IAM, billing systems, and Route 53 name servers using European Top-Level Domains—remain within EU borders.

But this isolation comes with costs. As that same engineer warned, “it really slows down debugging issues. Problems that would be fixed in a day or two can take a month.” This is the sovereignty trade-off in practice: more control, less velocity. The service launches with approximately 90 AWS services, not the full catalog. Plans exist to expand into sovereign Local Zones in Belgium, the Netherlands, and Portugal, but this remains a subset of AWS’s offerings globally.

For some workloads, this trade-off makes sense. For others, it’s a deal-breaker.

Why the European Sovereign Cloud Can’t Escape U.S. Jurisdiction

Here’s the uncomfortable truth that AWS’s marketing carefully sidesteps: technical isolation doesn’t create legal isolation. AWS, headquartered in America, remains subject to U.S. jurisdiction. The CLOUD Act allows U.S. authorities to compel U.S.-based technology companies to provide data, regardless of where it is stored globally. Courts can require parent companies to produce data held by subsidiaries.

This isn’t theoretical hand-wraving. Microsoft had to admit in a French court that it cannot guarantee data sovereignty for EU customers. When Airbus executive Catherine Jestin discussed AWS’s sovereignty claims with lawyers late last year, she said: “I still don’t understand how it is possible” for AWS to be immune to extraterritorial laws.

Cristina Caffarra, founder of the Eurostack Foundation and competition economist, puts it bluntly:

A company subject to the extraterritorial laws of the United States cannot be considered sovereign for Europe. That simply doesn’t work.

The AWS response focuses on technical controls—encryption, the Nitro System preventing employee access, and hardware security modules. These are important safeguards, but they don’t address the core legal issue. If a U.S. court orders Amazon.com Inc. to produce data, technical barriers become legal obstacles the parent company must overcome, not protections.

Europe’s European Sovereign Cloud Strategy: The Cloud and AI Development Act

AWS’s launch comes as Europe finalizes its own legislative response. The EU Cloud and AI Development Act, expected in Q1 2026, aims to strengthen Europe’s autonomy over cloud infrastructure and data. As Christoph Strnadl, CTO of Gaia-X, explains:

For critical data, you will never, ever use a US company. Sovereignty means having strategic options — not doing everything yourself.

The Act is part of the EU’s Competitiveness Compass and addresses a fundamental problem: Europe’s 90% dependency on non-EU cloud infrastructure, predominantly American companies. This dependency isn’t just about data residency—it’s about strategic autonomy. When essential services depend on infrastructure governed by foreign law, questions arise about jurisdiction, resilience, and what happens during geopolitical disruption.

Current estimates indicate that AWS, Microsoft Azure, and Google Cloud collectively control over 60% of the European cloud market. European providers account for only a small share of revenues. The Cloud and AI Development Act aims to establish minimum criteria for cloud services in Europe, mobilize public and private initiatives for AI infrastructure, and create a single EU-wide cloud policy for public administrations and procurement.

Importantly, Brussels isn’t seeking to ban non-EU providers. As Strnadl notes:

Sovereignty does not mean you have to do everything yourself. Sovereignty means that for critical things, you have strategic options.

Gaia-X and the European Sovereign Cloud: A Lesson in Sovereignty Washing

Europe has been down this path before. Gaia-X, launched in 2019, intended to create a trustworthy European data infrastructure. Then American companies lobbied to be included. Once Microsoft, Google, and AWS were inside, critics argue, Gaia-X lost its purpose. The fear now is that AWS’s European Sovereign Cloud represents sophisticated “sovereignty washing”—placing datacenters on European soil without resolving the fundamental legal issue.

Recent European actions suggest growing awareness of this problem. Austria, Germany, France, and the International Criminal Court in The Hague are taking concrete steps toward genuine digital independence. These aren’t just policy statements—they’re actual migrations away from U.S. hyperscalers toward European alternatives.

European Sovereign Cloud Adoption: No Full Migration in 2026

Forrester predicts that no European enterprise will fully shift away from U.S. hyperscalers in 2026, citing geopolitical tensions, volatility, and new legislation, such as the EU AI Act, as barriers. The scale of dependency is too deep, the feature gap too wide, and the migration costs too high for rapid change.

Gartner forecasts European IT spending will grow 11% in 2026 to $1.4 trillion, with 61% of European CIOs and tech leaders wanting to increase their use of local cloud providers. Around half (53%) said geopolitical factors would limit their use of global providers in the future. The direction is clear, even if the pace remains uncertain.

This creates a transitional period where organizations must make pragmatic choices. For non-critical workloads, AWS’s European Sovereign Cloud may be sufficient. For truly sensitive data—government communications, defense systems, critical infrastructure—organizations need genuinely European alternatives: Hetzner, Scaleway, OVHCloud, StackIT by Schwarz Digits.

What AWS’s European Sovereign Cloud Actually Delivers

Let’s be precise about what AWS European Sovereign Cloud achieves. It provides:

  • Data residency within the EU
  • Operational control by EU residents  
  • Governance through EU-based legal entities
  • Technical isolation from the global AWS infrastructure
  • An advisory board of EU citizens with independent oversight

What it doesn’t provide is independence from U.S. legal jurisdiction. For compliance requirements focused purely on data residency and operational transparency, this may be sufficient. For organizations requiring protection from U.S. government data requests, it fundamentally isn’t.

As Eric Swanson from CarMax noted in a LinkedIn post:

Sovereign cloud offerings do not override the Patriot Act. They mainly reduce overlap across other contexts: data location, operational control, employee access, and customer jurisdiction.

European Sovereign Cloud and Strategic Autonomy: Not Autarky

Europe’s path forward isn’t about digital isolationism. As Strnadl emphasizes, technology adoption that involves a paradigm shift doesn’t happen in two years. The challenge is adoption, not frameworks. “Cooperation needs trust,” he says, “and trust needs a trust framework.”

The Cloud and AI Development Act, expected this quarter, will provide that framework. It will set minimum criteria, promote interoperability, and establish procurement rules that favor sovereignty for critical workloads. The question for organizations is: what constitutes critical?

For email, public administration, political communication, and defense systems, the answer should be obvious. These require European alternatives. For other workloads, AWS’s European Sovereign Cloud may strike an acceptable balance between capability and control.

The Bottom Line

AWS’s €7.8 billion investment is real. The technical isolation is real. The economic contribution to Germany’s GDP (€17.2 billion over 20 years) is real. What’s also real is that Amazon.com Inc., a U.S. company, ultimately controls this infrastructure and remains subject to U.S. law.

For organizations seeking compliance checkboxes and data residency guarantees, AWS European Sovereign Cloud delivers. For organizations requiring genuine independence from U.S. legal jurisdiction, it remains fundamentally insufficient. That’s not a criticism of AWS’s engineering—it’s a statement of legal reality.

The sovereignty question Europe faces isn’t technical. It’s strategic: do we accept managed dependency or build genuine autonomy? AWS offers the former. Only European alternatives can provide the latter.

The market will decide which answer matters more.

Agentic Orchestration: The Evolution of SOA

Posted on by
1

For decades, integration professionals have shaped the digital backbone of enterprises from EAI to SOA to microservices. Today, agentic orchestration marks the next step in that evolution: transforming how we compose, coordinate, and reason across enterprise services. This isn’t a replacement for what we know; it’s an intelligent upgrade to it.

We built the bridges, the highways, and the intricate railway networks of the digital world. Yet, let’s be honest—for all our sophistication, our orchestrations often felt like a meticulous, rigid dance.

Enter Agentic Orchestration. This isn’t just another buzzword. It’s a profound shift, an evolution that takes the core principles of SOA and infuses them with intelligence, dynamism, and a remarkable degree of autonomy. For the seasoned integration architect and engineer, this isn’t about replacing what we know—it’s about enhancing it, elevating it to a new plane of capability.

How SOA Composites Differ from Agentic Orchestration

Cast your mind back to the golden age of SOA. For those of us in the Microsoft ecosystem, this meant nearly two and a half decades with BizTalk Server as our workhorse, our battleground, our canvas. We diligently crafted composite services using orchestration designers, adapters, and pipelines. Others wielded BPEL and ESBs, but the principle was the same. Our logic was clear, explicit, and, crucially, deterministic.

If a business process required validating a customer, then checking inventory, and finally processing an order, we laid out that sequence with unwavering precision—whether in BizTalk’s visual orchestration designer or in BPEL code:

XML

<bpel:sequence name="OrderFulfillmentProcess">
  <bpel:invoke operation="validateCustomer" partnerLink="CustomerService"/>
  <bpel:invoke operation="checkInventory" partnerLink="InventoryService"/>
  <bpel:invoke operation="processPayment" partnerLink="PaymentService"/>
</bpel:sequence>

Those of us who spent years with BizTalk know this dance intimately: the Receive shapes, the Decision shapes, the carefully constructed correlation sets, the Scope shapes wrapped around every potentially fragile operation. We debugged orchestrations at 2 AM, optimized dehydration points, and became masters of the Box-Line-Polygon visual language.

This approach delivered immense value. It brought order to chaos, reused services, and provided a clear, auditable trail. However, its strength was also its weakness: rigidity. Any deviation or unforeseen circumstance required a developer to step in, modify the orchestration, and redeploy. The system couldn’t “think” its way around a problem it merely executed a predefined script a well-choreographed ballet, beautiful but utterly inflexible to improvisation.

Agentic Orchestration: From Fixed Scripts to Intelligent Collaboration

Now, imagine an orchestration that doesn’t just execute a script, but reasons. An orchestration where the “participants” are not passive services waiting for an instruction, but intelligent agents equipped with goals, memory, and a suite of “tools”—which, for us, are often our existing services and APIs.

This is the essence of agentic orchestration. It shifts from a predefined, top-down command structure to a more collaborative, goal-driven paradigm. Instead of meticulously charting every step, we define the desired outcome and empower intelligent agents to find the best path to it.

Think of it as moving from a detailed project plan (SOA) to giving a highly skilled project manager (the Orchestrator Agent) a clear objective and a team of specialists (worker agents, each with specific skills/tools).

Key Differences that Matter

From Fixed Sequence to Dynamic Planning:

Traditional SOA executes a predetermined sequence: Step A, then Step B, then Step C. Agentic orchestration takes a different approach — agents dynamically construct their plan based on current context and available resources, asking: “What tools do I have, and which best serve this step?”

From Explicit Error Handling to Self-Correction:

In SOA, elaborate try-catch blocks covered every potential failure. BizTalk veterans will remember wrapping Scope shapes inside Scope shapes, each carrying its own exception handler. With agentic systems, a failing tool triggers reasoning rather than a halt — the agent may retry with a different tool, consult another agent, or revise its plan entirely.

From API Contracts to Intent-Based Communication:

Traditional SOA services communicate via strict, often verbose XML or JSON contracts — schema design and message transformation consumed countless engineering hours. Agentic systems shift to intent-based communication instead. An “Order Fulfillment Agent” can instruct a “Shipping Agent” with a clear goal: “Ship this package to customer X by date Y.” The Shipping Agent then determines which underlying tools, FedEx API, DHL API, best achieve that outcome, abstracting away the complexity of individual service calls.

From Static Connectors to Smart Tools:

Connectors and adapters in SOA are fixed pathways, each requiring explicit configuration per integration point. BizTalk veterans know this well from hours spent configuring adapters for every specific endpoint. In agentic architectures, existing APIs, databases, message queues, and even legacy systems are reframed as tools that agents can discover and wield intelligently. A Logic App connector to SAP is no longer just a connector; it becomes a capable SAP tool that an agent can invoke when the situation calls for it. The Model Context Protocol (MCP) is making this kind of dynamic tool discovery increasingly seamless.

A Concrete Example

Consider an order that fails the inventory check in our traditional BPEL or BizTalk orchestration. In SOA: hard stop, send error notification, await human intervention, and process redesign.

In an agentic system, the orchestrator agent might dynamically query alternate suppliers, adjust delivery timelines based on customer priority, suggest product substitutions, or even negotiate partial fulfillment—all without hardcoded logic for each scenario. The agent reasons about the business goal (fulfill the customer order) and uses available tools to achieve it, adapting to circumstances we never explicitly programmed for.

Azure Logic Apps: The Bridge to the Agentic Future

Azure Logic Apps demonstrates this evolution in practice, and it’s particularly compelling for integration professionals. For those of us coming from the BizTalk world, Logic Apps already felt familiar—the visual designer, the connectors, the enterprise reliability. Now, we’re not throwing away our decades of experience with these patterns. Instead, we’re adding an “intelligence layer” on top.

The Agent Loop within Logic Apps, with its “Think-Act-Reflect” cycle, transforms our familiar integration canvas into a dynamic decision-making engine. We can build multi-agent patterns—agent “handoffs” in which one agent completes a task and passes it to another, or “evaluator-optimizer” setups in which one agent generates a solution and another critiques and refines it.

All this, while leveraging the robust, enterprise-ready connectors we already depend on. Our existing investments in integration infrastructure don’t become obsolete; they become more powerful. The knowledge we gained from debugging BizTalk orchestrations, understanding message flows, and designing for reliability? All of that remains valuable. Microsoft is simply upgrading our toolkit.

Adopting Agentic Orchestration: The Path Forward for Integration Architects

For integration engineers and architects, this is not a threat but an immense opportunity. We are uniquely positioned to lead this charge. We understand the nuances of enterprise systems, the criticality of data integrity, and the challenges of connecting disparate technologies. Those of us who survived the BizTalk years are battle-tested, we know what real-world integration demands.

Agentic orchestration frees us from the burden of explicit, step-by-step programming for every conceivable scenario. It allows us to design systems that are more resilient, more adaptive, and ultimately, more intelligent. It enables us to build solutions that not only execute business processes but also actively contribute to achieving business outcomes.

Start small: Identify one rigid orchestration in your current architecture that would benefit from adaptive decision-making. Perhaps it’s an order-fulfillment process with too many exception handlers, or a customer-onboarding workflow that breaks when regional requirements change. That’s your first candidate for agentic enhancement.

Let’s cast aside the notion of purely deterministic choreography. Let us instead embrace the era of intelligent collaboration, where our meticulously crafted services become the powerful tools in the hands of autonomous, reasoning agents.

The evolution is here. It’s time to orchestrate a smarter future.

Europe’s Sovereignty Challenge: A Framework for Cloud Control

Posted on by
1

Europe’s sovereignty challenge has moved from political debate to concrete policy. With the EU’s new Cloud Sovereignty Framework now in place, the continent is redefining how it procures and governs cloud infrastructure, shifting from dependency on foreign providers to measurable, auditable control over its digital destiny.

Today, Europe and the Netherlands find themselves at a crucial junction, navigating the complex landscape of digital autonomy. The recent introduction of the EU’s new Cloud Sovereignty Framework is the clearest signal yet that the continent is ready to take back control of its digital destiny.

This isn’t just about setting principles; it’s about introducing a standardized, measurable scorecard that will fundamentally redefine cloud procurement.

Europe’s Sovereignty Challenge: Why Digital Independence Is Non-Negotiable

The digital revolution has brought immense benefits, yet it has also positioned Europe in a state of significant dependency. Approximately 80% of our digital infrastructure relies on foreign companies, primarily American cloud providers. This dependence is not merely a matter of convenience; it’s a profound strategic vulnerability.

The core threat stems from U.S. legislation such as the CLOUD Act, which grants American law enforcement the power to request data from U.S. cloud service providers, even if that data is stored abroad. Moreover, this directly clashes with Europe’s stringent privacy regulations (GDPR) and exposes critical European data to external legal and geopolitical risk.

As we’ve seen with incidents like the Microsoft-ICC blockade, foreign political pressures can impact essential digital services. The possibility of geopolitical shifts, such as a “Trump II” presidency, only amplifies this collective awareness: we cannot afford to depend on foreign legislation for our critical infrastructure. The risk is present, and we must build resilience against it.

The Sovereignty Scorecard: From Principles to SEAL Rankings

The new Cloud Sovereignty Framework is the EU’s proactive response. It shifts the discussion from abstract aspirations to concrete, auditable metrics by evaluating cloud services against eight Sovereignty Objectives (SOVs) that cover legal, strategic, supply chain, and technological aspects.

The result is a rigorous “scorecard.” A provider’s weighted score determines its SEAL ranking (from SEAL-0 to SEAL-4, with SEAL-4 indicating full digital sovereignty). Crucially, this ranking is intended to serve as the definitive minimum assurance factor in government and public sector cloud procurement tenders. The Commission wants to create a level playing field where providers must tangibly demonstrate their sovereignty strengths.

Hyperscalers vs. European Providers: The Cloud Sovereignty Challenge

The framework has accelerated a critical duality in the market: massive, centralized investments by US hyperscalers versus strategic, federated growth by European alternatives.

Hyperscalers Adapt: Deepening European Ties

Global providers are making sovereignty a mandatory architectural and legal prerequisite by localizing their operations and governance.

  • AWS explicitly responded by announcing its EU Sovereign Cloud unit. This service is structured to ensure data residency and operational autonomy within Europe, explicitly targeting the SOV-3 (Data & AI Sovereignty: The degree of control customers have over their data and AI models, including where data is processed) criteria through physically and logically separated infrastructure and governance.
  • Google Cloud has also made significant moves, approaching digital sovereignty across three distinct pillars:
    • Data Sovereignty (focusing on control over data storage, processing, and access with features like the Data Boundary and External Key Management, EKM, where keys can be held outside Google Cloud’s infrastructure);
    • Operational Sovereignty (ensuring local partner oversight, such as the partnership with T-Systems in Germany); and
    • Software Sovereignty (providing tools to reduce lock-in and enable workload portability).To help organizations navigate these complex choices, Google introduced the Digital Sovereignty Explorer, an interactive online tool that clarifies terms, explains trade-offs, and guides European organizations in developing a tailored cloud strategy across these three domains. Furthermore, Google has developed highly specialized options, including Air-Gapped solutions for the defense and intelligence sectors, demonstrating a commitment to the highest levels of security and residency.
  • Microsoft has demonstrated a profound deepening of its commitment, outlining five comprehensive digital commitments designed to address sovereignty concerns:
    • Massive Infrastructure Investment: Pledging a 40% increase in European datacenter capacity, doubling its footprint by 2027.
    • Governance and Resilience: Instituting a “European cloud for Europe” overseen by a dedicated European board of directors (composed exclusively of European nationals) and backed by a “Digital Resilience Commitment” to contest any government order to suspend European operations legally.
    • Data Control: Completing the EU Data Boundary project to ensure European customers can store and process core cloud service data within the EU/EFTA.

European Contenders Scale Up

Strategic, open-source European initiatives powerfully mirror this regulatory push:

  • Virt8ra Expands: The Virt8ra sovereign cloud, which positions itself as a significant European alternative, recently announced a substantial expansion of its federated infrastructure. The platform, coordinated by OpenNebula Systems, added six new cloud service providers, including OVHcloud and Scaleway, significantly broadening its reach and capacity across the continent.
  • IPCEI Funding: This initiative, leveraging the open-source OpenNebula technology, is part of the Important Project of Common European Interest (IPCEI) on Next Generation Cloud Infrastructure and Services, backed by over €3 billion in public and private funding. This is a clear indicator that the vision for a robust, distributed European cloud ecosystem is gaining significant traction.

Redefining European Cloud Sovereignty: Resilience Over Isolation

Industry experts emphasize that the framework embodies a more mature understanding of digital sovereignty. It’s not about isolation (autarky), but about resilience and governance.

Sovereignty is about how an organization is “resilient against specific scenarios.” True sovereignty, in this view, lies in the proven, auditable ability to govern your own digital estate. For developers, this means separating cloud-specific infrastructure code from core business logic to maximize portability, allowing the use of necessary hyper-scale features while preserving architectural flexibility.

The Challenge: Balancing Features with Control

Despite the massive investments and public commitments from all major players, the framework faces two key hurdles:

  • The Feature Gap: European providers often lack the “huge software suite” and “deep feature integration” of US hyperscalers, which can slow down rapid development. Advanced analytics platforms, serverless computing, and tightly integrated security services often lack direct equivalents at smaller providers. This creates a complex chicken-and-egg problem: large enterprises won’t migrate to European providers because they lack features, but local providers struggle to develop those capabilities without enterprise revenue.
  • Skepticism and Compliance Complexity: Some analysts fear the framework’s complexity will inadvertently favor the global giants with larger compliance teams. Furthermore, deep-seated apprehension in the community remains, with some expressing the fundamental desire for purely European technological solutions: “I don’t want a Microsoft cloud or AI solutions in Europe. I want European ones.” Some experts suggest that European providers should focus on building something different by innovating with European privacy and control values baked in, rather than trying to catch up with US providers’ feature sets.

My perspective on this situation is that achieving true digital sovereignty for Europe is a complex and multifaceted endeavor. While the commitments from global hyperscalers are significant, the underlying desire for independent, European-led solutions remains strong. It’s about strategic autonomy, ensuring that we, as Europeans, maintain ultimate control over our digital destiny and critical data, irrespective of where the technology originates.

The race is now on. The challenge for the cloud industry is to translate the high-level, technical criteria of the SOVs into auditable, real-world reality to achieve that elusive top SEAL-4 ranking. The battle for the future of Europe’s cloud is officially underway.

Walking Skeleton & Pipes and Filters for Enterprise Integration

Posted on by
Reply

In enterprise integration, a solid architectural foundation is what separates projects that scale from those that collapse under their own complexity. Two patterns I keep returning to are the Walking Skeleton and Pipes and Filters, which I didn´t realize at first. In this post, I’ll show how they work together when building or rebuilding an integration platform.

An example is that my experience in retail showed me that, and I was involved in rebuilding an integration platform. In the world of integration, where you’re constantly juggling disparate systems, multiple data formats, and unpredictable volumes, a solid architecture is paramount. Thus, I always try to build the best solution based on experience rather than on what’s written in the literature.

What is funny to me is that when I built the integration platform, I realized I was applying patterns such as the Walking Skeleton for architectural validation and the Pipes and Filters pattern for resilient, flexible integration flows.

The Walking Skeleton caught my attention when a fellow architect at my current workplace brought it to my attention. And I realized that this is what I actually did with my team at the retailer. Hence, I should read some literature from time to time!

Why the Walking Skeleton Is Your Integration Architecture First Step

Before you write a line of business logic, you need to prove your stack works from end to end. The Walking Skeleton is precisely that: a minimal, fully functional implementation of your system’s architecture.

It’s not an MVP (Minimum Viable Product), which is a business concept focused on features; the Skeleton is a technical proof of concept focused on connectivity.

Why Build the Skeleton First?

  • Risk Mitigation: You validate your major components—UI, API Gateway, Backend Services, Database, Message Broker—can communicate and operate correctly before you invest heavily in complex features.
  • CI/CD Foundation: By its nature, the Skeleton must run end-to-end. This forces you to set up your CI/CD pipelines early, giving you a working deployment mechanism from day one.
  • Team Alignment: A running system is the best documentation. Everyone on the team gets a shared, tangible understanding of how data flows through the architecture.

Suppose you’re building an integration platform in the cloud (like with Azure). In that case, the Walking Skeleton confirms your service choices, such as Azure Functions and Logic Apps, which integrate with your storage, networking, and security layers. Guess what I am going to do again in the near future, I hope.

Applying Pipes and Filters Within the Walking Skeleton

Now, let’s look at what that “minimal, end-to-end functionality” should look like, especially for data and process flow. The Pipes and Filters pattern is ideally suited for building the first functional slice of your integration Skeleton.

The pattern works by breaking down a complex process into a sequence of independent, reusable processing units (Filters) connected by communication channels (Pipes).

How They Map to Integration:

  1. Filters = Single Responsibility: Each Filter performs one specific, discrete action on the data stream, such as:
    • Schema Validation
    • Data Mapping (XML to JSON)
    • Business Rule Enrichment
    • Auditing/Logging
  2. Pipes = Decoupled Flow: The Pipes ensure data flows reliably between Filters, typically via a message broker or an orchestration layer.

In a serverless environment (e.g., using Azure Functions for the Filters and Azure Service Bus/Event Grid for the Pipes), this pattern delivers immense value:

  • Composability: Need to change a validation rule? You only update one small, isolated Filter. Need a new output format? You add a new mapping Filter at the end of the pipe.
  • Resilience: If one Filter fails, the data is typically held in the Pipe (queue/topic), preventing the loss of the entire transaction and allowing for easy retries.
  • Observability: Each Filter is a dedicated unit of execution. This makes monitoring, logging, and troubleshooting exact no more “black box” failures.

Walking Skeleton and Pipes and Filters: The Synergy

The real power comes from using the pattern within the process of building and expanding your Walking Skeleton:

  1. Initial Validation (The Skeleton): Select the absolute simplest, non-critical domain (e.g., an Article Data Distribution pipeline, as I have done with my team for retailers). Implement this single, end-to-end flow using the Pipes and Filters pattern. This proves that your architectural blueprint and your chosen integration pattern work together.
  2. Iterative Expansion: Once the Article Pipe is proven, validating the architectural choice, deployment, monitoring, and scaling, you have a template.
    • At the retailer, we subsequently built the integration for the Pricing domain, and by creating a new Pipe that reuses common Filters (e.g., the logging or basic validation Filters).
    • Next, we picked another domain by cloning the proven pipeline architecture and swapping in the domain-specific Filters.

You don’t start from scratch; you reapply a proven, validated template across domains. This approach dramatically reduces time-to-market and ensures that every new domain is built on a resilient, transparent, and scalable foundation.

My advice, based on what I know now and my experience, is not to skip the Skeleton. And don’t build a monolith inside it. Start with Pipes and Filters and Skeleton for a future-proof, durable architecture for enterprise integration when rebuilding an integration platform in Azure.

What architectural pattern do you find most useful when kicking off a new integration project? Drop a comment!

AWS Free Tier Goes Credit-Based: How It Compares to Azure and GCP

Posted on by
Reply

AWS is officially moving away from its long-standing 12-month free tier for new accounts. The new standard, called the Free Account Plan, is a credit-based model designed to eliminate the risk of unexpected bills for new users.

Free Account Plan

With this new plan, you get:

  • A risk-free environment for experimenting and building proofs of concept for up to six months.
  • A starting credit of $100, with the potential to earn another $100 by completing specific exploration activities, such as launching an EC2 instance. This means you can get up to $200 in credits to use across eligible services.
  • The plan ends after six months or once your credits are entirely spent, whichever comes first. After that, you have a 90-day window to upgrade to a paid plan and restore access to your account and data.

This shift, as Principal Developer Advocate Channy Yun explains, allows new users to get hands-on experience without cost commitments. However, it’s worth noting that some services typically used by large enterprises won’t be available on this free plan.

While some may see this as a step back, I tend to agree with Corey Quinn’s perspective. He writes that this is “a return to product-led growth rather than focusing on enterprise revenue to the exclusion of all else.” Let’s face it: big companies aren’t concerned with the free tier. But for students and hobbyists, who can be seen as the next generation of cloud builders, a credit-based, risk-free sandbox is a much more attractive proposition. The new notifications for credit usage and expiration dates are a smart addition that provides peace of mind.

How the New Plan Compares to Other Hyperscalers

A helpful plan for those who like to experiment on AWS, I think. Yet, other hyperscalers like Azure and GCP offer similar plans too. Microsoft Azure and Google Cloud Platform (GCP) have long operated on credit-based models.

  • Azure offers a different model: $200 in credits for the first 30 days, supplemented by over 25 “always free” services and a selection of services available for free for 12 months.
  • GCP provides a 90-day, $300 Free Trial for new customers, which can be applied to most products, along with an “Always Free” tier that gives ongoing access to core services like Compute Engine and Cloud Storage up to specific monthly limits.

This alignment among the major cloud providers highlights a consensus on the best way to attract and onboard new developers.

Microsoft also offers $100 in Azure credits through Azure for students. Note that the MSDN credits are typically a monthly allowance tied to a specific Visual Studio subscription, and the student credits are a lump sum for a particular period (e.g., 12 months), as I believe these different models can be confusing.

Speaking of other cloud providers, my own experience with Azure is an excellent example of how these credit models can be beneficial. I enjoy credits for Azure because of my MVP benefits, and through MSDN subscriptions, one has a monthly $150 in credits. These are different options from the general one I mentioned earlier. Anyway, there are ways to access services provided by the three big hyperscalers that allow you to get hands-on experience in combination with their documentation and what you can find in public repos.

In general, when you like to learn more about Azure, AWS, or GCP, the following table shows the most straightforward options:

Cloud HyperscalerFree CreditsDocumentationRepo (samples)
AzureAzure Free AccountMicrosoft LearnAzure Samples · GitHub  
AWSAWS Free TierAWS DocumentationAWS Samples · GitHub
GCPGCP Free TrialGoogle Cloud DocumentationGoogle Cloud Platform · GitHub

Figma AWS Costs Explained: Beyond the Hype and Panic

Posted on by
Reply

Figma’s recent IPO filing revealed that its Figma AWS costs amount to roughly $300,000 per day, approximately $109 million annually, or 12% of its reported revenue of $821 million. The company is also committed to a minimum spend of $545 million with AWS over the next five years. Cue the online meltdown. “Figma is doomed!” “Fire the CTO!” The internet, in its infinite wisdom, declared. I wrote a news item on it for InfoQ and thought, let’s put things into perspective.

(Source: Figma.com)

But let’s inject a dose of reality, shall we? As Corey Quinn from The Duckbill Group, who probably sees more AWS invoices than you’ve seen Marvel movies, rightly points out, this kind of spending for a company like Figma is boringly normal.

As Quinn extensively details in his blog post, Figma isn’t running a simple blog. It’s a compute-intensive, real-time collaborative platform serving 13 million monthly active users and 450,000 paying customers. It renders complex designs with sub-100ms latency. This isn’t just about spinning up a few virtual machines; it’s about providing a seamless, high-performance experience on a global scale.

The Numbers Game: What the Armchair Experts Missed About Figma AWS Costs

The initial panic conveniently ignored a few crucial realities, according to Quinn:

  • Ramping Spend: Most large AWS contracts increase year-over-year. A $109 million annual average over five years likely starts lower (e.g., $80 million) and gradually increases to a higher figure (e.g., $150 million in year five) as the company expands.
  • Post-Discount Figures: These spend targets are post-discount. At Figma’s scale, they’re likely getting a significant discount (think 30% effective discount) on their cloud spend. So, their “retail” spend would be closer to $785 million over five years, not $545 million.

When you factor these in, Figma AWS costs fall squarely within industry benchmarks for its type of business:

  • Compute-lite SaaS: around 5% of revenue
  • Compute-heavy platforms (like Figma): 10–15% of revenue
  • AI/ML-intensive companies: often exceeding 15%

At 12% of revenue, Figma’s AWS costs are exactly where you’d expect them to be for a platform delivering real-time collaborative experiences at a global scale.

Furthermore, the increasing adoption of AI and Machine Learning in application development is introducing a new dimension to cloud costs. AI workloads, particularly for training and continuous inference, are incredibly resource-intensive, pushing the boundaries of compute, storage, and specialized hardware (like GPUs), which naturally translates to higher cloud bills. This makes effective FinOps and cost optimization strategies even more crucial for companies that leverage AI at scale.

So, while the internet was busy getting its math wrong and forecasting doom, Figma was operating within a completely reasonable range for its business model and scale.

The “Risky Dependency” Non-Story

Another popular narrative was the “risky dependency” on AWS. Figma’s S-1 filing includes standard boilerplate language about vendor dependencies, a common feature found in virtually every cloud-dependent company’s SEC filings. It’s the legal equivalent of saying, “If the sky falls, our business might be affected.”

Breaking news: a SaaS company that uses a cloud provider might be affected by outages. In related news, restaurants depend on food suppliers. This isn’t groundbreaking insight; it’s just common business risk disclosure. Figma’s “deep entanglement” with AWS, as described by Hacker News commenter nevon, illustrates the complexity of modern cloud architectures. Every aspect, from permissions to disaster recovery, is seamlessly integrated. That makes a quick migration akin to open-heart surgery. Not something you do on a whim.

Cloud Repatriation: A Valid Strategy, But Not a Universal Panacea

Figma’s costs reignited the cloud repatriation debate. The most vocal advocate is 37signals CTO David Heinemeier Hansson, who famously exited the cloud to save millions. And he’s not wrong for some companies; repatriating workloads delivers significant savings. But it’s not a one-size-fits-all solution.

Every company’s needs are different. Scrimba, for example, runs on dedicated servers and spends less than 1% of revenue on infrastructure. For them, repatriation is a perfect fit. Figma is a different story. Its real-time collaborative demands and massive user base require agility, scalability, and managed services at a global scale. A hyperscale provider like AWS isn’t optional; it’s central to the business model.

This brings us to a broader conversation, especially relevant in Europe: digital sovereignty. As I’ve discussed in my blog post, “Digital Destiny: Navigating Europe’s Sovereignty Challenge,” deep integration with a single hyperscaler isn’t just a cost question. It also affects the control an organization retains over its data and operations. Vendor lock-in carries real strategic implications. Data governance, regulatory compliance, and negotiating power can all be compromised. The extraterritorial reach of foreign laws adds another layer of concern. Many organizations are responding by exploring multi-cloud strategies or hybrid models. The goal: mitigate risk and assert greater control over their digital destiny.

My Cloud Anecdote: Costs vs. Value

This whole debate reminds me of a scenario I encountered back in 2017. I was working on a proof of concept for a customer, building a future-proof knowledge base using Cosmos DB, the Graph Model, and Search. The operating cost, primarily driven by Cosmos DB, was approximately 1,000 euros per month. Some developers immediately flagged it as “too expensive,” as I can recall, or even thought I was selling Cosmos DB. The reception, however, wasn’t universally positive. In fact, one attendee later wrote in their blog:

The most uninteresting talk of the day came from Steef-Jan Wiggers, who, in my opinion, delivered an hour-long marketing pitch for CosmosDB. I think it’s expensive for what it currently offers, and many developers could architect something with just as much performance without needing CosmosDB.

However, the proposed solution was for a knowledge base that customers could leverage via a subscription model. The crucial point was that the costs were negligible compared to the potential revenue the subscription model would net for the customer. It was an investment in a revenue-generating asset, not just a pure expense.

The Bottom Line: Putting Figma AWS Costs in Perspective

Thanks to Quinn, I understand that Figma is actively optimizing its infrastructure, transitioning from Ruby to C++ pipelines, migrating workloads, and implementing dynamic cluster scaling. He concluded:

They’re doing the work. More importantly, they’re growing at 46% year-over-year with a 91% gross margin. If you’re losing sleep over their AWS bill while they’re printing money like this, you might need to reconsider your priorities.

The “innovation <-> optimization continuum” is always at play. Companies often prioritize rapid innovation and speed to market, leveraging the cloud for its agility and flexibility. As they scale, they can then focus on optimizing those costs, and Figma AWS costs are no exception to that pattern.

This increasing complexity underscores the growing importance of FinOps (Cloud Financial Operations), a cultural practice that brings financial accountability to the variable-spend model of cloud computing, empowering teams to make data-driven decisions about cloud usage and optimize costs without sacrificing innovation.

Figma’s transparency in disclosing its cloud costs is actually a good thing. It forces a much-needed conversation about the true cost of running enterprise-scale infrastructure in 2025. The hyperbolic reactions, however, expose a fundamental misunderstanding of these realities. Which I also encountered with my Cosmos DB project in 2017.

So, the next time someone tells you that a company spending 12% of its revenue on infrastructure that literally runs its entire business is “doomed,” perhaps ask them how much they think it should cost to serve real-time collaborative experiences to 13 million users across the globe. When you understand what drives Figma AWS costs, the answer might surprise you.

Lastly, as the cloud landscape continues to evolve, with new services, AI integration, and shifting geopolitical considerations, the core lesson remains: smart cloud investment isn’t about avoiding the bill, but understanding its true value in driving business outcomes and strategic advantage. The dialogue about cloud costs is far from over, but it’s time we grounded it in reality.

Digital Destiny: Navigating Europe’s Sovereignty Challenge

Posted on by
Reply

During my extensive career in IT, I’ve often seen how technology can both empower and entangle us. Today, Europe and the Netherlands find themselves at a crucial junction, navigating the complex landscape of digital sovereignty. Recent geopolitical shifts and the looming possibility of a “Trump II” presidency have only amplified our collective awareness: we cannot afford to be dependent on foreign legislation when it comes to our critical infrastructure.

In this post, I will delve into the threats and strategic risks that underpin this challenge. We’ll explore the initiatives underway at both the European and Dutch levels, and, crucially, what the major U.S. Hyperscalers are now bringing to the table in response.

The Digital Predicament: Threats to Our Autonomy

The digital revolution has certainly brought unprecedented benefits, not least through innovative Cloud Services that are transforming our economy and society. However, this advancement has also positioned Europe in a state of significant dependency. Approximately 80% of our digital infrastructure relies on foreign companies, primarily American cloud providers, including Amazon Web Services (AWS), Microsoft Azure, and Google Cloud. This reliance isn’t just a matter of convenience; it’s a strategic vulnerability.

The Legal Undercurrent: U.S. Legislation

One of the most persistent threats to European digital sovereignty stems from American legislation. The CLOUD Act (2018), an addition to the Freedom Act (2015) that replaced the Patriot Act (2001), grants American law enforcement and security services the power to request data from American cloud service providers, even if that data is stored abroad.

Think about it: if U.S. intelligence agencies can request data from powerhouses like AWS, Microsoft, or Google without your knowledge, what does this mean for European organizations that have placed their crown jewels there? This directly clashes with Europe’s stringent privacy regulations, the General Data Protection Regulation (GDPR), which sets strict requirements for the protection of personal data of individuals in the EU.

While the Dutch National Cyber Security Centre (NCSC) has stated that, in practice, the chance of the U.S. government requesting European data via the CLOUD Act has historically been minimal, they also acknowledge that this could change with recent geopolitical developments. The risk is present, even though it has rarely materialized thus far.

Geopolitics: The Digital Chessboard

Beyond legal frameworks, geopolitical developments pose a very real threat to our digital autonomy. Foreign governments may impose trade barriers and sanctions on Cloud Services. Imagine scenarios where tensions between major powers lead to access restrictions for essential Cloud Services. The European Union or even my country cannot afford to be a digital pawn in such a high-stakes game.

We’ve already seen these dynamics play out. In negotiations for a minerals deal with Ukraine, the White House reportedly made a phone call to stop the delivery of satellite images from Maxar Technologies, an American space company. These images were crucial for monitoring Russian troop movements and documenting war crimes.

Another stark example is the Microsoft-ICC incident, where Microsoft blocked access to email and Office 365 services for the chief prosecutor of the International Criminal Court in The Hague due to American sanctions. These incidents serve as powerful reminders of how critical external political pressures can be in impacting digital services.

Europe’s Response: A Collaborative Push for Sovereignty

Recognizing these challenges, both Europe and the Netherlands are actively pursuing initiatives to bolster digital autonomy. It’s also worth noting how major cloud providers are responding to these evolving demands.

European Ambitions:

The European Union has been a driving force behind initiatives to reinforce its digital independence:

  • Gaia-X: This ambitious European project aims to create a trustworthy and secure data infrastructure, fostering a federated system that connects existing European cloud providers and ensures compliance with European regulations, such as the General Data Protection Regulation (GDPR). It’s about creating a transparent and controlled framework.
  • Digital Markets Act (DMA) & Digital Services Act (DSA): These legislative acts aim to regulate the digital economy, fostering fairer competition and greater accountability from large online platforms.
  • Cloud and AI Development Act (proposed): This upcoming legislation seeks to ensure that strategic EU use cases can rely on sovereign cloud solutions, with the public sector acting as a crucial “anchor client.”
  • EuroStack: This broader initiative envisions Europe as a leader in digital sovereignty, building a comprehensive digital ecosystem from semiconductors to AI systems.

Crucially, we’re seeing tangible progress here. Virt8ra, a significant European initiative positioning itself as a major alternative to US-based cloud vendors, recently announced a substantial expansion of its federated infrastructure. The platform, which initially included Arsys, BIT, Gdańsk University of Technology, Infobip, IONOS, Kontron, MONDRAGON Corporation, and Oktawave, all coordinated by OpenNebula Systems, has now been joined by six new cloud service providers: ADI Data Center Euskadi, Clever Cloud, CloudFerro, OVHcloud, Scaleway, and Stackscale. This expansion is a clear indicator that the vision for a robust, distributed European cloud ecosystem is gaining significant traction.

Dutch Determination:

The Netherlands is equally committed to this journey:

  • Strategic Digital Autonomy and Government-Wide Cloud Policy: A coalition of Dutch organizations has developed a roadmap, proposing a three-layer model for government cloud policy that advocates for local storage of state secret data and autonomy requirements for sensitive government data.
  • Cloud Kootwijk: This initiative brings together local providers to develop viable alternatives to hyperscaler clouds, fostering homegrown digital infrastructure.
  • “Reprogram the Government” Initiative: This initiative advocates for a more robust and self-reliant digital government, pushing for IT procurement reforms and in-house expertise.
  • GPT-NL: A project to develop a Dutch language model, strengthening national strategic autonomy in AI and ensuring alignment with Dutch values.

Hyperscalers and the Sovereignty Landscape:

The growing demand for digital sovereignty has prompted significant responses from major cloud providers, demonstrating a recognition of European concerns:

  • AWS European Sovereign Cloud: AWS has announced key components of its independent European governance for the AWS European Sovereign Cloud.
  • Microsoft’s Five Digital Commitments: Microsoft recently outlined five significant digital commitments to deepen its investment and support for Europe’s technological landscape.

These efforts from hyperscalers highlight a critical balance. As industry analyst David Linthicum noted, while Europe’s drive for homegrown solutions is vital for data control, it also prompts questions about access to cutting-edge innovations. He stresses the importance of “striking the right balance” to ensure sovereignty efforts don’t inadvertently limit access to crucial capabilities that drive innovation.

However, despite these significant investments, skepticism persists. There is an ongoing debate within Europe regarding digital sovereignty and reliance on technology providers headquartered outside the European Union. Some in the community express doubts about how such companies can truly operate independently and prioritize European interests, with comments like, “Microsoft is going to do exactly what the US government tells them to do. Their proclamations are meaningless.” Others echo the sentiment that “European money should not flow to American pockets in such a way. Europe needs to become independent from American tech giants as a way forward.” This collective feedback highlights Europe’s ongoing effort to develop its own technological capabilities and reduce its reliance on non-European entities for critical digital infrastructure.

My perspective on this situation is that achieving true digital sovereignty for Europe is a complex and multifaceted endeavor, marked by both opportunities and challenges. While the commitments from global hyperscalers are significant and demonstrate a clear response to European demands, the underlying desire for independent, European-led solutions remains strong. It’s not about outright rejection of external providers, but about strategic autonomy – ensuring that we, as Europeans, maintain ultimate control over our digital destiny and critical data, irrespective of where the technology originates.

New Pricing Plan and Enhanced Networking for Azure Container Apps in Preview

Posted on by
Reply

Microsoft recently announced a new pricing plan and enhanced networking for Azure Container Apps in public preview.

Azure Container Apps is a fully managed environment that enables developers to run microservices and containerized applications on a serverless platform. It is flexible and can execute application code packaged in any container without runtime or programming model restrictions.

Earlier Azure Container Apps had a consumption plan featuring a serverless architecture that allows applications to scale in and out on demand. Applications can scale to zero, and users only pay for running apps.

In addition to the consumption plan, Azure Container Apps now supports a dedicated plan, which guarantees single tenancy and specialized compute options, including memory-optimized choices. It runs in the same Azure Container Apps environment as the serverless Consumption plan and is referred to as the Consumption + Dedicated plan structure. This structure is in preview.

Mike Morton, a Senior Program Manager at Microsoft, explains in a Tech Community blog post the benefit of the new plan:

It allows apps or microservice components that may have different resource requirements depending on component purpose or development stack to run in the same Azure Container Apps environment. An Azure Container Apps environment provides an execution, isolation, and observability boundary that allows apps within it to easily call other apps in the environment, as well as provide a single place to view logs from all apps.

At the Azure Container Apps environment scope, compute options are workload profiles. The default workload profile for each environment is a serverless, general-purpose profile available as part of the Consumption plan. For the dedicated workload profile, users can select type and size, deploy multiple apps into the profile, use autoscaling to add and remove nodes and limit the scaling of the profile.

Source: https://techcommunity.microsoft.com/t5/apps-on-azure-blog/azure-container-apps-announces-new-pricing-plan-and-enhanced/ba-p/3790723

With Container Apps, one architect has another compute option in Azure besides App Service and Virtual Machines. Edwin Michiels, a Tech Customer Success Manager at Microsoft, answered in a LinkedIn post the difference between Azure Container Apps and Azure Apps Service, which offer similar capabilities:

In terms of cost, Azure App Service has a pricing model based on the number of instances and resources used, while Azure Container Instances and Azure Kubernetes Service are billed based on the number of containers and nodes used, respectively. For small to medium-sized APIs, Azure App Service may be a more cost-effective option, while for larger or more complex APIs, Azure Container Instances or Azure Kubernetes Service may offer more flexibility and cost savings.

The Consumption + Dedicated plan structure also includes optimized network architecture and security features that offer reduced subnet size requirements with a new /27 minimum, support for Azure Container Apps environments on subnets with locked-down network security groups and user-defined routes (UDR), and support on subnets configured with Azure Firewall or third-party network appliances.

The new pricing plan and enhanced networking for Azure Container Apps are available in the North Central US, North Europe, West Europe, and East US regions. Billing for Consumption and Dedicated plans is detailed on the Azure Container Apps pricing page.

Lastly, the new price plan and network enhancements are discussed and demoed in the latest Azure Container Apps Community Standup.