<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>OpenAI on Cyril's Cloud &amp; AI Daily</title><link>https://cyrilbouharb.github.io/tags/openai/</link><description>Recent content in OpenAI on Cyril's Cloud &amp; AI Daily</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 16 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://cyrilbouharb.github.io/tags/openai/index.xml" rel="self" type="application/rss+xml"/><item><title>What’s new in Microsoft Foundry | September 2026</title><link>https://cyrilbouharb.github.io/posts/2026-10-16-what-s-new-in-microsoft-foundry-september-2026/</link><pubDate>Fri, 16 Oct 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-10-16-what-s-new-in-microsoft-foundry-september-2026/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>Dynamic Workflows in Azure Functions Hosted Skills: Durable, AI-Led Work for Event-Driven Apps</title><link>https://cyrilbouharb.github.io/posts/2026-10-08-dynamic-workflows-in-azure-functions-hosted-skills-durable-a/</link><pubDate>Thu, 08 Oct 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-10-08-dynamic-workflows-in-azure-functions-hosted-skills-durable-a/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>Using Azure Blob Storage as a durable filesystem for LangChain Deep Agents</title><link>https://cyrilbouharb.github.io/posts/2026-09-22-using-azure-blob-storage-as-a-durable-filesystem-for-langcha/</link><pubDate>Tue, 22 Sep 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-09-22-using-azure-blob-storage-as-a-durable-filesystem-for-langcha/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;LangChain Deep Agentsis an open-source agent harness with built-in capabilities for building LLM-powered agents and applications, including complex, multi-step workflows.&lt;/p&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>What’s new in Microsoft Foundry: July and August 2026</title><link>https://cyrilbouharb.github.io/posts/2026-09-09-what-s-new-in-microsoft-foundry-july-and-august-2026/</link><pubDate>Wed, 09 Sep 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-09-09-what-s-new-in-microsoft-foundry-july-and-august-2026/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Microsoft Foundry’s July and August 2026 updates make Hosted Agents, Voice Live integration, and Toolboxes generally available; expand Claude tools hosted on Azure; update Model Router’s regions and model pool; add Foundry Local capabilities; and advance the Python, JavaScript, Java, and .NET SDKs.&lt;/p&gt;</description></item><item><title>What 50 open source projects taught us about security in the AI era</title><link>https://cyrilbouharb.github.io/posts/2026-08-13-what-50-open-source-projects-taught-us-about-security-in-the/</link><pubDate>Thu, 13 Aug 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-08-13-what-50-open-source-projects-taught-us-about-security-in-the/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>Azure Content Understanding GPT-5 Series Guide: Model Selection, Grounding Improvements, and Confidence Enhancements</title><link>https://cyrilbouharb.github.io/posts/2026-08-12-azure-content-understanding-gpt-5-series-guide-model-selecti/</link><pubDate>Wed, 12 Aug 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-08-12-azure-content-understanding-gpt-5-series-guide-model-selecti/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>From Sync APIs to support for the GPT-5 model series and agentic workflows: What’s new in Azure Content Understanding – August 2026</title><link>https://cyrilbouharb.github.io/posts/2026-08-12-from-sync-apis-to-support-for-the-gpt-5-model-series-and-age/</link><pubDate>Wed, 12 Aug 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-08-12-from-sync-apis-to-support-for-the-gpt-5-model-series-and-age/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>Stacked sessions and pull requests in the GitHub Copilot app</title><link>https://cyrilbouharb.github.io/posts/2026-07-30-stacked-sessions-and-pull-requests-in-the-github-copilot-app/</link><pubDate>Thu, 30 Jul 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-07-30-stacked-sessions-and-pull-requests-in-the-github-copilot-app/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;I want you to look at this screenshot for a moment from theGitHub Copilot app. It’s a small one, it’s got a lot of icons, and it tells the most glorious story that I’m really excited about.&lt;/p&gt;</description></item><item><title>Copilot vs. raw API access: What are you actually paying for?</title><link>https://cyrilbouharb.github.io/posts/2026-07-22-copilot-vs-raw-api-access-what-are-you-actually-paying-for/</link><pubDate>Wed, 22 Jul 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-07-22-copilot-vs-raw-api-access-what-are-you-actually-paying-for/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Microsoft Foundry&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;I keep seeing this question: “Why would I pay for GitHub Copilot when I can call the same models through an API?”&lt;/p&gt;&#10;&lt;p&gt;It’s a fair question. The answer depends on what work you need to own.&lt;/p&gt;</description></item><item><title>Evaluating performance and efficiency of the GitHub Copilot agentic harness across models and tasks</title><link>https://cyrilbouharb.github.io/posts/2026-06-25-evaluating-performance-and-efficiency-of-the-github-copilot-/</link><pubDate>Thu, 25 Jun 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-06-25-evaluating-performance-and-efficiency-of-the-github-copilot-/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>From one-off prompts to workflows: How to use custom agents in GitHub Copilot CLI</title><link>https://cyrilbouharb.github.io/posts/2026-06-09-from-one-off-prompts-to-workflows-how-to-use-custom-agents-i/</link><pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-06-09-from-one-off-prompts-to-workflows-how-to-use-custom-agents-i/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Developers work across many surfaces like the CLI, IDE, and GitHub. The terminal is often where they turn to move fast, automate tasks, or work directly with systems and scripts.&lt;/p&gt;</description></item><item><title>Build 2026: From observability to ROI for AI agents on any framework</title><link>https://cyrilbouharb.github.io/posts/2026-06-03-build-2026-from-observability-to-roi-for-ai-agents-on-any-fr/</link><pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-06-03-build-2026-from-observability-to-roi-for-ai-agents-on-any-fr/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Microsoft Agent Framework&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;9 min read · June 3, 2026 · Sebastian Kohlmeier&lt;/p&gt;&#10;&lt;p&gt;Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck. Agents are non-deterministic. Their behavior shifts as models update, tools change, and traffic patterns evolve and most of that drift happens silently, long after the demo.End-to-end observabilitycovering the full development lifecycle is how you close that gap: See every step an agent takes, evaluate quality and safety against criteria you define, optimize what isn’t working, and prove the business value of what is.&lt;/p&gt;</description></item><item><title>Build smarter document workflows: What’s new in Azure Content Understanding at Build 2026</title><link>https://cyrilbouharb.github.io/posts/2026-06-03-build-smarter-document-workflows-what-s-new-in-azure-content/</link><pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-06-03-build-smarter-document-workflows-what-s-new-in-azure-content/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Azure Content Understanding in Foundry Tools is Microsoft’s comprehensive content AI service. It ingests diverse data types — documents, audio, images, and video — and extracts the most critical information to power well-grounded, reliable generative AI and agentic solutions. Azure Content Understanding brings together Azure Document Intelligence’s proven traditional AI with advanced LLM-based content reasoning, enabling both structured and unstructured content extraction, as well as multimodal understanding to address your full spectrum of processing needs.&lt;/p&gt;</description></item><item><title>Introducing Agent Optimizer in Foundry Agent Service</title><link>https://cyrilbouharb.github.io/posts/2026-06-03-introducing-agent-optimizer-in-foundry-agent-service/</link><pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-06-03-introducing-agent-optimizer-in-foundry-agent-service/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Microsoft Foundry&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Withhosted agents, we made it straightforward to build and deploy agents on Foundry. You write your logic, run azd deploy, and your agent is live. But “live” and “production-ready” aren’t the same thing.&lt;/p&gt;</description></item><item><title>What’s new in Microsoft Foundry | Build Edition</title><link>https://cyrilbouharb.github.io/posts/2026-06-02-what-s-new-in-microsoft-foundry-build-edition/</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-06-02-what-s-new-in-microsoft-foundry-build-edition/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;h3 id="tldr"&gt;TL;DR&lt;/h3&gt;&#10;&lt;p&gt;At Build 2026, Microsoft Foundry added more of the platform pieces developers need for production agents: runtime, tools, memory, grounding, models, observability, and governance. This recap highlights what shipped, what is in preview, and where to start.&lt;/p&gt;</description></item><item><title>What’s new in Microsoft Foundry | May 2026</title><link>https://cyrilbouharb.github.io/posts/2026-05-31-what-s-new-in-microsoft-foundry-may-2026/</link><pubDate>Sun, 31 May 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-05-31-what-s-new-in-microsoft-foundry-may-2026/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;h3 id="tldr"&gt;TL;DR&lt;/h3&gt;&#10;&lt;ul&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;Trace-based evaluation for external and hosted agents:Grade real production traces from Foundry, GCP, AWS, or any framework — no hand-curated datasets required.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;Grok 4.3:xAI’s latest model lands in Foundry for advanced agentic and domain-specific workloads.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;DeepSeek V4:DeepSeek’s newest model family expands open-model choice in the catalog.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;Fireworks AI — May update:DeepSeek V4 Pro and Kimi 2.6 arrive via Fireworks for high-performance open-model inference.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;/ul&gt;</description></item><item><title>How to run evals for the model router</title><link>https://cyrilbouharb.github.io/posts/2026-05-19-how-to-run-evals-for-the-model-router/</link><pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-05-19-how-to-run-evals-for-the-model-router/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;One endpoint. Smarter spend. Model router in Foundry Models picks the optimal LLM for every prompt in real time based on signals like complexity, reasoning, and task type. Now with access to 28 frontier models, the model router makes model selection easier for developers and reduces manual overhead. This article walks you through how to run evaluations using a new open-source GitHub repo designed explicitly for the model router.Access the Eval Repo on GitHub&lt;/p&gt;</description></item><item><title>Governance at the Speed of Agents: Microsoft Agent Framework and Agent Governance Toolkit, Better Together</title><link>https://cyrilbouharb.github.io/posts/2026-05-14-governance-at-the-speed-of-agents-microsoft-agent-framework-/</link><pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-05-14-governance-at-the-speed-of-agents-microsoft-agent-framework-/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Building powerful AI agents is only half the story, running them safely in production is the real challenge. As customers adopt Microsoft Agent Framework for agent orchestration, a clear need has emerged for robust, built-in governance. In this post, Imran Siddique from the AGT team walks through how Agent Governance Toolkit pairs with Agent Framework to enforce policy at runtime, govern agent actions, and provide end-to-end auditability. Turning agentic systems into production-ready platforms.&lt;/p&gt;</description></item><item><title>Foundry Local 1.1: Live Transcription, Embeddings, and Responses API</title><link>https://cyrilbouharb.github.io/posts/2026-05-12-foundry-local-1-1-live-transcription-embeddings-and-response/</link><pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-05-12-foundry-local-1-1-live-transcription-embeddings-and-response/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;RAG (Retrieval Augmented Generation)&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Today we’re announcing the1.1.0 release of Foundry Local— Microsoft’s cross-platform local AI solution that lets developers bringAI directly into their applicationswith no cloud dependency, no network latency, and no per-token costs.&lt;/p&gt;</description></item><item><title>What’s new in Microsoft Foundry | April 2026</title><link>https://cyrilbouharb.github.io/posts/2026-05-12-what-s-new-in-microsoft-foundry-april-2026/</link><pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-05-12-what-s-new-in-microsoft-foundry-april-2026/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;h3 id="tldr"&gt;TL;DR&lt;/h3&gt;&#10;&lt;ul&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;Foundry Local (generally available, GA):Local model inference is production-ready on Windows, macOS on Apple Silicon, and Linux x64.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;GPT-5.5:The latest GPT-5 family model is available in Microsoft Foundry, with default quota for Tier 5 and Tier 6 subscriptions.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;Microsoft Agent Framework tracing (Preview):Agent Framework agents can emit OpenTelemetry traces into Foundry for debugging and production observability.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;li&gt;&#10;&lt;p&gt;Hosted-agent tracing (Preview):Hosted-agent sessions, tool calls, and run steps can now surface in Foundry traces.&lt;/p&gt;&#10;&lt;/li&gt;&#10;&lt;/ul&gt;</description></item><item><title>From Local to Production: Deploy Your Microsoft Agent Framework Agent with Foundry Hosted Agents</title><link>https://cyrilbouharb.github.io/posts/2026-05-06-from-local-to-production-deploy-your-microsoft-agent-framewo/</link><pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-05-06-from-local-to-production-deploy-your-microsoft-agent-framewo/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Microsoft Foundry&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Once you have your Microsoft Agent Framework (MAF) agent or workflow happily running locally on your dev machine, it’s time to decide how to deploy your agent to production, monitor it, evaluate it and version it. These decisions are just as important as getting the agent running.Hosted Agents in Foundry Agent Serviceis the easiest way to deploy Agent Framework agent to the cloud – with built-in identity, automatic scaling, managed session state, observability, and versioning.&lt;/p&gt;</description></item><item><title>Chat History Storage Patterns in Microsoft Agent Framework</title><link>https://cyrilbouharb.github.io/posts/2026-04-24-chat-history-storage-patterns-in-microsoft-agent-framework/</link><pubDate>Fri, 24 Apr 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-04-24-chat-history-storage-patterns-in-microsoft-agent-framework/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;Azure OpenAI &amp;amp; GPT Models&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;When people talk about building AI agents, they usually focus on models, tools, and prompts. In practice, one of the most important architectural decisions is much simpler:where does the conversation history live?&lt;/p&gt;</description></item><item><title>From Local to Production: The Complete Developer Journey for Building, Composing, and Deploying AI Agents</title><link>https://cyrilbouharb.github.io/posts/2026-04-22-from-local-to-production-the-complete-developer-journey-for-/</link><pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-04-22-from-local-to-production-the-complete-developer-journey-for-/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;AI Agents&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;When we launchedMicrosoft Agent Frameworklast October, we made a promise: building production-grade AI agents should feel as natural and structured as building any other software.&lt;/p&gt;&#10;&lt;p&gt;Today, we’re delivering on that promise — with thev1.0 release of Microsoft Agent Frameworkand thegeneral availability ofFoundry Toolkitfor Visual Studio Code(formerly AI Toolkit for VS Code), new capabilities inmemory(preview) in Foundry Agent Service,Toolbox in Foundry(preview) to give your agents the right tools, a faster and more securehostedagentsexperience in Foundry Agent Service (preview), andObservability in Foundry Control Planereaching full GA on core capabilities including end-to-end tracing now in place.&lt;/p&gt;</description></item><item><title>Introducing the new hosted agents in Foundry Agent Service: secure, scalable compute built for agents</title><link>https://cyrilbouharb.github.io/posts/2026-04-22-introducing-the-new-hosted-agents-in-foundry-agent-service-s/</link><pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate><guid>https://cyrilbouharb.github.io/posts/2026-04-22-introducing-the-new-hosted-agents-in-foundry-agent-service-s/</guid><description>&lt;p&gt;There&amp;rsquo;s been an important development in the &lt;strong&gt;GitHub Copilot&lt;/strong&gt; 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.&lt;/p&gt;&#10;&lt;h2 id="whats-new"&gt;What&amp;rsquo;s New&lt;/h2&gt;&#10;&lt;p&gt;Agents are already transforming how developers solve problems. Whether it’s a coding agent that refactors your repo overnight, a research agent that synthesizes hundreds of documents into a brief, or an ops agent that monitors and remediates infrastructure — the pattern is clear. Developers are building agents that don’t just answer questions, they go do things.&lt;/p&gt;</description></item></channel></rss>