Data & AI on Cyril's Cloud & AI Daily

Browser automation tool in Microsoft Foundry is now GA

Mon, 19 Oct 2026 00:00:00 +0000

There’s been an important development in the GitHub Copilot space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

AI agents can reason over data, invoke APIs, and coordinate complex workflows. Yet many business processes still depend on websites, including internal portals, administrative consoles, vendor systems, dashboards, and applications without complete API coverage.

What’s new in Microsoft Foundry | September 2026

Fri, 16 Oct 2026 00:00:00 +0000

What’s New

September’s updates help you run agents on a schedule, load tool definitions on demand, and investigate behavior from traces. Routines and Tool Search are now GA; Insights enters public preview, and Model Router gains preview controls. We also expanded the GPT-6 lineup and introduced GPT-6.1 Sol.

Azure MCP Server 3.0 stable release: More tools. More possibilities

Wed, 14 Oct 2026 00:00:00 +0000

What’s New

We’re excited to share the stable release of Azure MCP Server 3.0, released on October 12, 2026. From reviewing backup protection to evaluating infrastructure changes, this release brings more everyday Azure operations into your agent workflows. It also introduces clearer tool contracts and security-focused defaults for new resources.

From extraction to action: Using grounding and confidence to build reliable document workflows

Wed, 14 Oct 2026 00:00:00 +0000

There’s been an important development in the Microsoft Foundry space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

“Civilization advances by extending the number of important operations which we can perform without thinking about them.” — Alfred North Whitehead

“Civilization advances by extending the number of important operations which we can perform without thinking about them.” — Alfred North Whitehead

Azure Content Understanding Prebuilt Analyzers: packaging domain knowledge for document AI

Tue, 13 Oct 2026 00:00:00 +0000

There’s been an important development in the AI Agents space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

For many intelligent document processing and emerging agentic workflows, extracting text is only the starting point. Applications increasingly need to capture a document’s structure and implicit business meaning in a form that agents and downstream systems can interpret accurately and act on.

GitHub Copilot app for Beginners: How to teach Copilot about your codebase

Mon, 12 Oct 2026 00:00:00 +0000

What’s New

Context matters when you’re working with AI. Every codebase has its own house rules: how components are structured, which scripts to run, and which conventions apply to different frameworks and file types.

Dynamic Workflows in Azure Functions Hosted Skills: Durable, AI-Led Work for Event-Driven Apps

Thu, 08 Oct 2026 00:00:00 +0000

What’s New

Azure Functions is the event-driven application platform in Azure. Your code runs when a queue message, a blob upload, a database change, or an HTTP request arrives.Azure Functions Hosted Skillsadds AI reasoning to these apps. When an event arrives, an LLM reads it, applies your instructions, skills, and tools, and decides what to do.

Azure Document Intelligence and Azure Content Understanding: a practical guide

Wed, 07 Oct 2026 00:00:00 +0000

There’s been an important development in the Agentic RAG & Foundry IQ space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

Document-processing tools can appear straightforward when every input follows a predictable format. Production workloads are rarely that tidy. Invoices arrive in different layouts, contracts hide important facts in prose, and a single business process can span PDFs, Office documents, images, audio, and video.

Bring agentic reasoning to Python function apps with Azure Functions Agent bindings (preview)

Tue, 06 Oct 2026 00:00:00 +0000

There’s been an important development in the Microsoft Agent Framework space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

Azure Functions applications already have a strong model for event-driven work: a trigger starts the function, bindings connect it to other services, and application code validates input and controls the result. AI reasoning doesn’t need to replace that model.

How we found 24 Android vulnerabilities using our open source AI security agent

Mon, 28 Sep 2026 00:00:00 +0000

What’s New

With the rise of AI in the security space, our team created theGitHub Security Lab Taskflow Agentas a way for security researchers to easily automate, package, and share the AI prompts and workflows that they find effective for their work. In this blog post, I’ll share how I created auditing taskflows to find vulnerabilities in Android applications.

AI-powered fuzzing with the GitHub Security Lab Taskflow Agent

Thu, 24 Sep 2026 00:00:00 +0000

What’s New

If you’re new to fuzzing and want to learn the fundamentals first, check out our Fuzzing 101 course atgh.io/fuzzing101.

Continuous fuzzing is not a magic solution that solves all your problems . Even projects that have been enrolled in OSS-Fuzz for years can still hide critical bugs, and the reason is almost always the same: someone needs to keep an eye on coverage, write new harnesses for the code that nobody is reaching, and triage the crashes that come out the other end. In other words, fuzzing still needs a human in the loop.

From Chatbots to Automated Assistants: Routines in Microsoft Foundry Are Now Generally Available

Thu, 24 Sep 2026 00:00:00 +0000

What’s New

Agents are rapidly evolving beyond chat. The first generation of agents waited for a person to send a message. Today, organizations want agents that can monitor work, respond to business events, and continue tasks over time. An agent might triage a newly opened GitHub issue, respond when a message appears in a Microsoft Teams channel, prepare a report every morning, or check back on a long-running process until it finishes.

Rendering huge pull requests in the GitHub Copilot app

Wed, 23 Sep 2026 00:00:00 +0000

What’s New

Broad refactors and migrations often have to land as one change.

Stacked pull requestsare a great way to split work into smaller changes, which makes reviews easier and helps teams ship with less risk. But some changes, like this one, can’t be split cleanly. That leaves you with a single pull request that can get very large, and the review conversation causes it to grow.

Using Azure Blob Storage as a durable filesystem for LangChain Deep Agents

Tue, 22 Sep 2026 00:00:00 +0000

There’s been an important development in the Azure OpenAI & GPT Models space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

LangChain Deep Agentsis an open-source agent harness with built-in capabilities for building LLM-powered agents and applications, including complex, multi-step workflows.

A model can reason and generate responses, but it needs a harness to do useful work over time. The harness provides the tools and runtime that let the model retrieve the right context, take actions, and manage work across multiple steps. Deep Agents supplies that structure through planning, context management, a virtual filesystem, memory and skills, specialized subagents, and human approval points.

Should you read the code, is RAG dead, and did Skills kill MCP?

Fri, 18 Sep 2026 00:00:00 +0000

What’s New

Hot takes turn complicated topics into one confident sentence. That makes them great for engagement, but not necessarily for understanding.

At the surface level, they do not matter much. You agree, disagree, repost, argue for a few minutes, and move on. Sometimes the take is directionally right. Sometimes it is complete nonsense.

Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my!

Wed, 02 Sep 2026 00:00:00 +0000

What’s New

It might be overwhelming to see all of the new vocabulary popping up in software development these days thanks to AI tools introducing them… all the time.

Some of this new vocab describes useful patterns that people are newly pursuing, others are just fancy names on top of things that already exist, and some are still actively being defined as we speak.

Power Azure SRE Agent with the tools it needs

Mon, 31 Aug 2026 00:00:00 +0000

What’s New

This blog post shows how to expand the capabilities of Azure SRE Agent by giving it access to MCP servers hosted on Azure Connector Namespace. Connector Namespace is a managed MCP hosting platform that removes the operational and management overhead of self-hosting MCP servers. It entered public preview at Microsoft Build in June, with general availability estimated for the end of 2026.

How to evaluate LLMs before production

Tue, 25 Aug 2026 00:00:00 +0000

There’s been an important development in the Cloud & AI space that caught my attention, and I wanted to break it down — not just what was announced, but why it matters and how it fits into the bigger picture.

What’s New

A language model can perform well on a clean benchmark and still struggle with the cases that matter in production.

Benchmarks and curated datasets are useful when prototyping an LLM-based system. They help teams compare models, test an initial prompt, and determine whether an idea is technically plausible.

From single call to agents: five new Claude capabilities now available in Microsoft Foundry

Mon, 17 Aug 2026 00:00:00 +0000

What’s New

From single call to agents: five new Claude capabilities now available in Microsoft Foundry

Structured outputs, Web search, Web fetch, MCP connector, and Tool search are now available for Claude models in Microsoft Foundry hosted on Azure, the building blocks that turn a model endpoint into a production agent platform.

What 50 open source projects taught us about security in the AI era

Thu, 13 Aug 2026 00:00:00 +0000

What’s New

AI is changing the pace of open source development and the security challenges that come with it. Maintainers are reviewing unfamiliar contributions, managing new attack surfaces, and responding to vulnerabilities with limited time and resources.

Azure Content Understanding GPT-5 Series Guide: Model Selection, Grounding Improvements, and Confidence Enhancements

Wed, 12 Aug 2026 00:00:00 +0000

What’s New

Enterprise content is no longer just something people consume. As organizations increasingly rely on AI to extract and act on information from documents, images, audio, and video, Azure Content Understanding is expanding support for the GPT-5 series and improving grounding and confidence to deliver greater flexibility, efficiency, and quality.

From Sync APIs to support for the GPT-5 model series and agentic workflows: What’s new in Azure Content Understanding – August 2026

Wed, 12 Aug 2026 00:00:00 +0000

What’s New

Enterprise content is no longer just something people read. AI apps and agents are only as useful as the information they can understand, yet much of the world’s enterprise knowledge is locked in documents, forms, tables, images, audio, and video. The latest Azure Content Understanding updates help developers turn that content into structured, grounded data with less custom processing. This release brings broader support for the GPT-5 model series, lower token usage, improved confidence scoring, new synchronous APIs for Read and Layout, advanced contextualization for higher-quality extraction, new tax-focused prebuilt analyzers, semantic chunking for retrieval workflows, and agentic document reasoning for more complex extraction scenarios.

How the GitHub legal team used Copilot CLI to streamline their workflows

Tue, 04 Aug 2026 00:00:00 +0000

What’s New

Whether you are just starting out or are not in a technical role at all, you likely already have the skills you need to build your own tools. If you have ever thought “I’m not technical enough to build that,” this post is for you.

Turn one giant AI-generated pull request to a reviewable stack

Tue, 04 Aug 2026 00:00:00 +0000

What’s New

Think about the last big feature you shipped. Be honest. Did you cram it into one giant pull request, or did you split it into smaller scoped pull requests? For years, you have silently had to decide between watching a pull request grow so large that reviewing it becomes a nightmare or breaking it into a chain of smaller pull requests that you have to babysit, sync by hand, and untangle conflicts every time a change is introduced below.

The harness is all you need (mostly)

Mon, 27 Jul 2026 00:00:00 +0000

What’s New

If you’re feeling overwhelmed by AI right now, you’re not alone.

Every day it seems there is a new tool, new MCP, new model, new skill, new workflow, new feature, new social post that is some form of “Hey look! I have completely figured out AI with this one weird prompt.”

Building Agents that Act on Your Behalf with Toolboxes in Foundry

Wed, 22 Jul 2026 00:00:00 +0000

What’s New

How Toolboxes in Foundry simplify user delegation

At some point, many agents move from answering questions to taking action. And when it does, the question becomes:whose identity is it acting with? Imagine you are building an internal employee agent. It needs to call a private, Entra-protected MCP server for orders, and it also needs to use Microsoft’s managed Work IQ MCP server to reason over the employee’s Microsoft 365 context. In both cases, the agent can’t run as a managed identity or service account. It has to act as thereal signed-in user— with that user’s permissions, access boundaries, and data protections. That’s where identity gets hard: exchanging tokens on behalf of the user, keeping each user’s tokens isolated, and handling consent and refreshing.

Copilot vs. raw API access: What are you actually paying for?

Wed, 22 Jul 2026 00:00:00 +0000

What’s New

I keep seeing this question: “Why would I pay for GitHub Copilot when I can call the same models through an API?”

It’s a fair question. The answer depends on what work you need to own.

The cost of saying yes has changed

Fri, 17 Jul 2026 00:00:00 +0000

What’s New

The most expensive part of a small feature request used to be writing the code. Now it’s usually the meeting about whether or not to write the code.

What’s New in Microsoft Foundry | June 2026

Tue, 07 Jul 2026 00:00:00 +0000

What’s New

Here’s what shipped in Microsoft Foundry in June 2026 — Claude reached general availability, Foundry agents started publishing straight into Microsoft 365 Copilot and Teams, and Toolboxes, Routines, and Memory all got meaningfully more capable.

Evaluating performance and efficiency of the GitHub Copilot agentic harness across models and tasks

Thu, 25 Jun 2026 00:00:00 +0000

What’s New

While the model provides the raw intelligence, the harness shapes how effectively that intelligence is applied. The GitHub Copilot agentic harness is a single shared component of theGitHub Copilot SDK, which powers theGitHub Copilot CLI,GitHub Copilot app, andCopilot code review, along with a wide variety of experiences across GitHub and Microsoft. Improve the harness, and every surface benefits.

How we built an internal data analytics agent

Fri, 19 Jun 2026 00:00:00 +0000

What’s New

Large data and analytics organizations often struggle to make access to data and insights truly self-serve. The industry tried to solve this problem, quite unsuccessfully, for decades, but now AI is giving us a credible way to do just that.

Outcome-driven learning systems: Enterprise RL with OpenEnv and Foundry

Thu, 18 Jun 2026 00:00:00 +0000

What’s New

We shipped a lot atBuild 2026: hosted agents, Toolboxes, Foundry IQ, Memory, Managed Compute, fine‑tuning, Frontier Tuning, and a new evaluation and optimization stack. Read as a feature list, it is a lot to hold in your head. So here is a simpler way to see it: these are the parts you need to build alearning system, with agents that get measurably better at your work over time, not a chatbot that answers once and forgets. This post is about assembling those parts into one loop you own, and the science that makes a small, owned model worth training.

Accelerating researchers and developers building multilingual AI with a new open dataset

Mon, 15 Jun 2026 00:00:00 +0000

What’s New

Software may be written in programming languages, but human language is at the heart of developer collaboration. Developers explain how projects work in READMEs. They ask for help in issues. They review, debate, and improve code in pull requests. That collaboration often happens in English—but not always. As AI becomes a bigger part of how developers build software, multilingual developer content matters more than ever.

Making secret scanning more trustworthy: Reducing false positives at scale

Thu, 11 Jun 2026 00:00:00 +0000

What’s New

Secret scanning plays a critical role in protecting developers and organizations. It helps catch exposed credentials early and prevents small mistakes from turning into real incidents.

At GitHub’s scale, even small inefficiencies create real friction. Too many false positives make alerts harder to trust.

Give GitHub Copilot CLI real code intelligence with language servers

Wed, 10 Jun 2026 00:00:00 +0000

What’s New

Ever watched GitHub Copilot CLI extract a JAR file to a temporary directory, grep through.classfiles, and piece together an API signature from raw bytecode? The agent is resourceful, but without a language server, that’s the best it can do.

Accelerate Edge AI Development with Foundry Local

Thu, 04 Jun 2026 00:00:00 +0000

What’s New

AI is no longer confined to cloud experiments. Developers are increasingly expected to deliver AI inside apps, devices, and edge systems where responsiveness, privacy, resilience, and local control are essential. But building those experiences for production is still difficult.

Announcing Foundry Managed Compute: Run open models in Microsoft Foundry