For the last week or two, reports have been circulating that recent Windows 11 updates (specifically KB5063878 and KB5062660) were causing some SSDs using Phison controllers to fail. Tech influencers on YouTube and TikTok were quick to jump on the reports of corrupted data and disappearing drives, laying the blame squarely at Microsoft’s feet. We’re not saying any company is above lying to the public, and Microsoft has a history of rockyupdaterollouts, but both Microsoft and Phison claim they’ve been unable to recreate the issue.
Phison said it was made aware of reports that the Windows update was causing drives to fail on August 18th and began investigating the issue. Then it issued a statement on August 27th saying that after running over 2,200 test cycles totaling more than 4,500 hours it was, “unable to reproduce the reported issue, and no partners or customers have reported that the issue affected their drives at this time.”
Microsoft followed up just a few days later by saying that, “After thorough investigation, Microsoft has found no connection between the August 2025 Windows security update and the types of hard drive failures reported on social media.”
This isn’t terribly surprising since the reports were fairly limited. A Japanese user on Twitter appears to be the first to suggest the Windows update was bricking SSDs and there were some in the comments claiming that they had experienced similar issues. But, there was little evidence to suggest it was widespread and it’s entirely possible that this is a localized problem related to a bad batch of drives. So it seems there’s little reason to believe the August 2025 Windows security update is going to fry your hard drive, no matter what some dude on TikTok says.
Our Leader position in the Gartner Magic Quadrant™ for Desktop as a Service for three consecutive years reflects our commitment to deliver a platform for business agility, resilience, and human-centric innovation.
Flutter 3.35 was released on Aug. 16 with updates that include the stable release of stateful hot reload on the web and the Dart and Flutter MCP Server. It also includes the experimental release of Widget Previews.
Developer productivity was a key aspect of this release, according to a Flutter blog post by Kevin Chisholm, a technical program manager for Dart and Flutter at Google.
Stateful hot reload on the web is now enabled by default, Chisholm wrote. The feature means a developer can edit their web application’s code and see the changes instantly in the browser without losing the application’s current state.
Hot reload is a process that enables the development server to automatically inject new code into a running application after a file is saved, avoiding a full page refresh. The “stateful” part means the application’s current state — like data in a form, a user’s position in a game, or a toggle that’s been flipped — is preserved during the hot reload.
“Our goal is to provide a seamless and consistent hot reload experience across all platforms,” Chisholm wrote. “While you can still disable this feature using a flag, we plan to remove that ability in a future release.”
Also, The Dart and Flutter MCP Server is now available in the stable channel of the Dart SDK.
“The Dart and Flutter MCP Server acts as a bridge, giving AI coding assistants access to even more of your project’s context via the Dart and Flutter toolchain,” Chisholm wrote. “Instead of just suggesting code, your AI assistant can now understand your project deeply and take action on your behalf. This allows you to stay focused on your goals while the AI handles the mechanics.”
The release also includes Widget Previews, a new experimental feature that allows developers to view and iterate on a single widget in isolation, directly within their IDE, without having to run the entire application.
It complements the stateful hot reload, Chisholm said.
“Widget previews complements this by allowing you to visualize and test your widgets in a sandboxed environment, completely separate from a full app,” he wrote. “This is invaluable when building out a design system or testing a component across a matrix of different configurations, such as various screen sizes, themes, and text scales, all at once and side-by-side.”
It speeds up the development process by allowing developers to focus on a specific UI component for fine-tuning the widget’s design and behavior, but without needing to build and run the full app.
Also noteworthy in this release is WebAssembly dry runs.
“In anticipation of enabling WebAssembly (Wasm) as the default web build target, every JS build now performs a ‘dry run’ compilation to Wasm,” Chisholm wrote. “A series of checks determines the Wasm-readiness of your application, and any findings are emitted to the console as warnings.”
Google Changes Android App Installation
Google has changed the Android app installation process: App installation on certified devices will require verified developers starting in March 2026.
That means developers will need to register and prove their identity regardless of how they’re distributing their app — even through third-party app sources, according to a report by Techgig.
Image via Google
Google said this new requirement provides an added layer of security.
“Following recent attacks, including those targeting people’s financial data on their phones, we’ve worked to increase developer accountability to prevent abuse,” Suzanne Frey, the vice president of Product, Trust & Growth for Android, wrote on the Android blog. “We’ve seen how malicious actors hide behind anonymity to harm users by impersonating developers and using their brand image to create convincing fake apps.”
It’s a significant problem, she added. Recent analysis by Google found over 50 times more malware from internet-sideloaded sources than on apps available through Google Play, she stated.
Cloud infrastructure developer DigitalOcean is now offering an MCP (Model Context Protocol) server that allows developers to manage cloud resources with natural language prompts through AI-enabled tools.
The server can currently access nine services: Accounts, App Platform, Databases, DOKS, Droplets, Insights, Marketplace, Networking, and Spaces Storage.
“Instead of juggling multiple dashboards or tools, you can manage common cloud operations right inside your favorite MCP-compatible tools,” the team wrote.
It also allows developers to “turn plain English into real API actions.” That means developers can:
Deploy and manage apps: Run commands like deploy a Ruby on Rails app from a GitHub repo or check which apps are on the developer’s account.
Create and manage databases: Provision a new PostgreSQL database or create a new database.
Work with files: Upload files from a local directory to a Spaces bucket, create a temporary access key, and get public URLs for files.
Check Certificates and Monitoring.
Check the status of an SSL certificate.
Optimize and understand costs: Get visibility on cloud costs, drill down into monthly app spending, or view a billing history for the last 12 months to understand reasons for higher bills in specific months.
In this chapter, we’ll explore the data structure Map (a class) which lets us translate (“map”) from an input value to an output value. We’ll use a Map to display text upside-down in a terminal!
This blog post is the third out of a six-part blog series called Agent Factory which will share best practices, design patterns, and tools to help guide you through adopting and building agentic AI.
Seeing is knowing—the power of agent observability
As agentic AI becomes more central to enterprise workflows, ensuring reliability, safety, and performance is critical. That’s where agent observability comes in. Agent observability empowers teams to:
Detect and resolve issues early in development.
Verify that agents uphold standards of quality, safety, and compliance.
Optimize performance and user experience in production.
Maintain trust and accountability in AI systems.
With the rise of complex, multi-agent and multi-modal systems, observability is essential for delivering AI that is not only effective, but also transparent, safe, and aligned with organizational values. Observability empowers teams to build with confidence and scale responsibly by providing visibility into how agents behave, make decisions, and respond to real-world scenarios across their lifecycle.
Agent observability is the practice of achieving deep, actionable visibility into the internal workings, decisions, and outcomes of AI agents throughout their lifecycle—from development and testing to deployment and ongoing operation. Key aspects of agent observability include:
Continuous monitoring: Tracking agent actions, decisions, and interactions in real time to surface anomalies, unexpected behaviors, or performance drift.
Tracing: Capturing detailed execution flows, including how agents reason through tasks, select tools, and collaborate with other agents or services. This helps answer not just “what happened,” but “why and how did it happen?”
Logging: Records agent decisions, tool calls, and internal state changes to support debugging and behavior analysis in agentic AI workflows.
Evaluation: Systematically assessing agent outputs for quality, safety, compliance, and alignment with user intent—using both automated and human-in-the-loop methods.
Governance: Enforcing policies and standards to ensure agents operate ethically, safely, and in accordance with organizational and regulatory requirements.
Traditional observability vs agent observability
Traditional observability relies on three foundational pillars: metrics, logs, and traces. These provide visibility into system performance, help diagnose failures, and support root-cause analysis. They are well-suited for conventional software systems where the focus is on infrastructure health, latency, and throughput.
However, AI agents are non-deterministic and introduce new dimensions—autonomy, reasoning, and dynamic decision making—that require a more advanced observability framework. Agent observability builds on traditional methods and adds two critical components: evaluations and governance. Evaluations help teams assess how well agents resolve user intent, adhere to tasks, and use tools effectively. Agent governance can ensure agents operate safely, ethically, and in compliance with organizational standards.
This expanded approach enables deeper visibility into agent behavior—not just what agents do, but why and how they do it. It supports continuous monitoring across the agent lifecycle, from development to production, and is essential for building trustworthy, high-performing AI systems at scale.
Azure AI Foundry Observability provides end-to-end agent observability
Azure AI Foundry Observability is a unified solution for evaluating, monitoring, tracing, and governing the quality, performance, and safety of your AI systems end to end in Azure AI Foundry—all built into your AI development loop. From model selection to real-time debugging, Foundry Observability capabilities empower teams to ship production-grade AI with confidence and speed. It’s observability, reimagined for the enterprise AI era.
With built-in capabilities like the Agents Playground evaluations, Azure AI Red Teaming Agent, and Azure Monitor integration, Foundry Observability brings evaluation and safety into every step of the agent lifecycle. Teams can trace each agent flow with full execution context, simulate adversarial scenarios, and monitor live traffic with customizable dashboards. Seamless CI/CD integration enables continuous evaluation on every commit and governance support with Microsoft Purview, Credo AI, and Saidot integration helps enable alignment with regulatory frameworks like the EU AI Act—making it easier to build responsible, production-grade AI at scale.
Five best practices for agent observability
1. Pick the right model using benchmark driven leaderboards
Every agent needs a model and choosing the right model is foundational for agent success. While planning your AI agent, you need to decide which model would be the best for your use case in terms of safety, quality, and cost.
You can pick the best model by either evaluating the model on your own data or use Azure AI Foundry’s model leaderboards to compare foundation models out-of-the-box by quality, cost, and performance—backed by industry benchmarks. With Foundry model leaderboards, you can find model leaders in various selection criteria and scenarios, visualize trade-offs among the criteria (e.g., quality vs cost or safety), and dive into detailed metrics to make confident, data-driven decisions.
Azure AI Foundry’s model leaderboards gave us the confidence to scale client solutions from experimentation to deployment. Comparing models side by side helped customers select the best fit—balancing performance, safety, and cost with confidence.
—Mark Luquire, EY Global Microsoft Alliance Co-Innovation Leader, Managing Director, Ernst & Young, LLP*
2. Evaluate agents continuously in development and production
Agents are powerful productivity assistants. They can plan, make decisions, and execute actions. Agents typically first reason through user intents in conversations, select the correct tools to call and satisfy the user requests, and complete various tasks according to their instructions. Before deploying agents, it’s critical to evaluate their behavior and performance.
Azure AI Foundry makes agent evaluation easier with several agent evaluators supported out-of-the-box, including Intent Resolution (how accurately the agent identifies and addresses user intentions), Task Adherence (how well the agent follows through on identified tasks), Tool Call Accuracy (how effectively the agent selects and uses tools), and Response Completeness (whether the agent’s response includes all necessary information). Beyond agent evaluators, Azure AI Foundry also provides a comprehensive suite of evaluators for broader assessments of AI quality, risk, and safety. These include quality dimensions such as relevance, coherence, and fluency, along with comprehensive risk and safety checks that assess for code vulnerabilities, violence, self-harm, sexual content, hate, unfairness, indirect attacks, and the use of protected materials. The Azure AI Foundry Agents Playground brings these evaluation and tracing tools together in one place, letting you test, debug, and improve agentic AI efficiently.
The robust evaluation tools in Azure AI Foundry help our developers continuously assess the performance and accuracy of our AI models, including meeting standards for coherence, fluency, and groundedness.
3. Integrate evaluations into your CI/CD pipelines
Automated evaluations should be part of your CI/CD pipeline so every code change is tested for quality and safety before release. This approach helps teams catch regressions early and can help ensure agents remain reliable as they evolve.
Azure AI Foundry integrates with your CI/CD workflows using GitHub Actions and Azure DevOps extensions, enabling you to auto-evaluate agents on every commit, compare versions using built-in quality, performance, and safety metrics, and leverage confidence intervals and significance tests to support decisions—helping to ensure that each iteration of your agent is production ready.
We’ve integrated Azure AI Foundry evaluations directly into our GitHub Actions workflow, so every code change to our AI agents is automatically tested before deployment. This setup helps us quickly catch regressions and maintain high quality as we iterate on our models and features.
4. Scan for vulnerabilities with AI red teaming before production
Security and safety are non-negotiable. Before deployment, proactively test agents for security and safety risks by simulating adversarial attacks. Red teaming helps uncover vulnerabilities that could be exploited in real-world scenarios, strengthening agent robustness.
Azure AI Foundry’s AI Red Teaming Agent automates adversarial testing, measuring risk and generating readiness reports. It enables teams to simulate attacks and validate both individual agent responses and complex workflows for production readiness.
Accenture is already testing the Microsoft AI Red Teaming Agent, which simulates adversarial prompts and detects model and application risk posture proactively. This tool will help validate not only individual agent responses, but also full multi-agent workflows in which cascading logic might produce unintended behavior from a single adversarial user. Red teaming lets us simulate worst-case scenarios before they ever hit production. That changes the game.
5. Monitor agents in production with tracing, evaluations, and alerts
Continuous monitoring after deployment is essential to catch issues, performance drift, or regressions in real time. Using evaluations, tracing, and alerts helps maintain agent reliability and compliance throughout its lifecycle.
Azure AI Foundry observability enables continuous agentic AI monitoring through a unified dashboard powered by Azure Monitor Application Insights and Azure Workbooks. This dashboard provides real-time visibility into performance, quality, safety, and resource usage, allowing you to run continuous evaluations on live traffic, set alerts to detect drift or regressions, and trace every evaluation result for full-stack observability. With seamless navigation to Azure Monitor, you can customize dashboards, set up advanced diagnostics, and respond swiftly to incidents—helping to ensure you stay ahead of issues with precision and speed.
Security is paramount for our large enterprise customers, and our collaboration with Microsoft allays any concerns. With Azure AI Foundry, we have the desired observability and control over our infrastructure and can deliver a highly secure environment to our customers.
Get started with Azure AI Foundry for end-to-end agent observability
To summarize, traditional observability includes metrics, logs, and traces. Agent Observability needs metrics, traces, logs, evaluations, and governance for full visibility. Azure AI Foundry Observability is a unified solution for agent governance, evaluation, tracing, and monitoring—all built into your AI development lifecycle. With tools like the Agents Playground, smooth CI/CD, and governance integrations, Azure AI Foundry Observability empowers teams to ensure their AI agents are reliable, safe, and production ready. Learn more about Azure AI Foundry Observability and get full visibility into your agents today!
What’s next
In part four of the Agent Factory series, we’ll focus on how you can go from prototype to production faster with developer tools and rapid agent development.
*The views reflected in this publication are the views of the speaker and do not necessarily reflect the views of the global EY organization or its member firms.
Log in
