https://cyrilbouharb.github.io/tags/foundry/Recent content in Foundry on Cyril's Cloud & AI DailyHugoen-USMon, 19 Oct 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-10-19-browser-automation-tool-in-microsoft-foundry-is-now-ga/Mon, 19 Oct 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-10-19-browser-automation-tool-in-microsoft-foundry-is-now-ga/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-10-16-what-s-new-in-microsoft-foundry-september-2026/Fri, 16 Oct 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-10-16-what-s-new-in-microsoft-foundry-september-2026/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-10-14-from-extraction-to-action-using-grounding-and-confidence-to-/Wed, 14 Oct 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-10-14-from-extraction-to-action-using-grounding-and-confidence-to-/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <blockquote> <p>“Civilization advances by extending the number of important operations which we can perform without thinking about them.” — Alfred North Whitehead</p> </blockquote> <p>“Civilization advances by extending the number of important operations which we can perform without thinking about them.” — Alfred North Whitehead</p>https://cyrilbouharb.github.io/posts/2026-10-08-dynamic-workflows-in-azure-functions-hosted-skills-durable-a/Thu, 08 Oct 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-10-08-dynamic-workflows-in-azure-functions-hosted-skills-durable-a/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-10-06-bring-agentic-reasoning-to-python-function-apps-with-azure-f/Tue, 06 Oct 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-10-06-bring-agentic-reasoning-to-python-function-apps-with-azure-f/<p>There&rsquo;s been an important development in the <strong>Microsoft Agent Framework</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-09-29-why-content-extraction-still-matters-in-the-genai-era/Tue, 29 Sep 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-09-29-why-content-extraction-still-matters-in-the-genai-era/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>The future of enterprise AI is not determined by the model you choose. It isdetermined by whether your agents can trust the content they act on.</p> <p>Five years into the era of large language models, that thesis still holds. If anything, it is truer today than when we started. The models are stronger. The content is messier. Most of the real engineering lies in turning a raw PDF, image, or audio file into grounded, verifiable information an agent can act on.</p>https://cyrilbouharb.github.io/posts/2026-09-24-control-where-your-hosted-agent-connects-with-network-egress/Thu, 24 Sep 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-09-24-control-where-your-hosted-agent-connects-with-network-egress/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="keep-destination-rules-outside-your-agent-code-observe-real-calls-then-test-an-explicit-outbound-boundary">Keep destination rules outside your agent code. Observe real calls, then test an explicit outbound boundary</h3> <p>Preview.This walkthrough is for development and evaluation. Network egress controls are not GA, have no preview SLA, and are not intended for production use.[1]</p>https://cyrilbouharb.github.io/posts/2026-09-24-from-chatbots-to-automated-assistants-routines-in-microsoft-/Thu, 24 Sep 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-09-24-from-chatbots-to-automated-assistants-routines-in-microsoft-/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-09-15-introducing-foundry-dev-pack-one-command-to-start-building-o/Tue, 15 Sep 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-09-15-introducing-foundry-dev-pack-one-command-to-start-building-o/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="introducing-foundry-dev-pack-one-command-to-start-building-on-microsoft-foundry">Introducing Foundry Dev Pack: One Command to Start Building on Microsoft Foundry</h3> <p>Setting up your Microsoft Foundry environment just got a lot simpler. We launched Foundry Dev Pack to consolidate initial installation steps into a single setup process.</p>https://cyrilbouharb.github.io/posts/2026-09-10-announcing-azure-ai-speech-llm-2607-better-multilingual-accu/Thu, 10 Sep 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-09-10-announcing-azure-ai-speech-llm-2607-better-multilingual-accu/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>Azure AI Speech continues to deliver regular improvements to LLM Speech throughout the year, helping developers build more accurate and capable voice experiences. We’re announcingLLM Speech 2607, our latest model update, which brings improvements in multilingual recognition and mixed-language audio inputs, along with an enhanced experience for the phrase list feature.</p>https://cyrilbouharb.github.io/posts/2026-09-09-what-s-new-in-microsoft-foundry-july-and-august-2026/Wed, 09 Sep 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-09-09-what-s-new-in-microsoft-foundry-july-and-august-2026/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-08-17-from-single-call-to-agents-five-new-claude-capabilities-now-/Mon, 17 Aug 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-08-17-from-single-call-to-agents-five-new-claude-capabilities-now-/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="from-single-call-to-agents-five-new-claude-capabilities-now-available-in-microsoft-foundry">From single call to agents: five new Claude capabilities now available in Microsoft Foundry</h3> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-08-12-from-sync-apis-to-support-for-the-gpt-5-model-series-and-age/Wed, 12 Aug 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-08-12-from-sync-apis-to-support-for-the-gpt-5-model-series-and-age/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-07-22-building-agents-that-act-on-your-behalf-with-toolboxes-in-fo/Wed, 22 Jul 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-07-22-building-agents-that-act-on-your-behalf-with-toolboxes-in-fo/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>How Toolboxes in Foundry simplify user delegation</p> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-07-22-copilot-vs-raw-api-access-what-are-you-actually-paying-for/Wed, 22 Jul 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-07-22-copilot-vs-raw-api-access-what-are-you-actually-paying-for/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>I keep seeing this question: “Why would I pay for GitHub Copilot when I can call the same models through an API?”</p> <p>It’s a fair question. The answer depends on what work you need to own.</p>https://cyrilbouharb.github.io/posts/2026-07-07-what-s-new-in-microsoft-foundry-june-2026/Tue, 07 Jul 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-07-07-what-s-new-in-microsoft-foundry-june-2026/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-06-18-outcome-driven-learning-systems-enterprise-rl-with-openenv-a/Thu, 18 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-18-outcome-driven-learning-systems-enterprise-rl-with-openenv-a/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-06-04-accelerate-edge-ai-development-with-foundry-local/Thu, 04 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-04-accelerate-edge-ai-development-with-foundry-local/<p>There&rsquo;s been an important development in the <strong>Agentic RAG &amp; Foundry IQ</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-06-03-announcing-foundry-managed-compute-run-open-models-in-micros/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-announcing-foundry-managed-compute-run-open-models-in-micros/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="announcing-foundry-managed-compute-run-open-models-in-microsoft-foundry">Announcing Foundry Managed Compute: Run open models in Microsoft Foundry</h3> <p>Today we’re announcingManaged Compute in Microsoft Foundry, a new managed platform for customizing and serving open-source AI models on elastic GPU capacity without the operational burden of running virtual machines, Kubernetes clusters, or model runtimes. Managed Compute pulls together three things into one experience: the Foundry Model Catalog, the runtimes and frameworks that serve those models well, and the GPU capacity underneath. It’s open by design. You get access to thousands of open-source models through our Hugging Face partnership, you can customize them with supervised fine-tuning or reinforcement learning, and you can securely deploy model weights you trained somewhere else.</p>https://cyrilbouharb.github.io/posts/2026-06-03-build-2026-from-observability-to-roi-for-ai-agents-on-any-fr/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-build-2026-from-observability-to-roi-for-ai-agents-on-any-fr/<p>There&rsquo;s been an important development in the <strong>Microsoft Agent Framework</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>9 min read · June 3, 2026 · Sebastian Kohlmeier</p> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-06-03-build-smarter-document-workflows-what-s-new-in-azure-content/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-build-smarter-document-workflows-what-s-new-in-azure-content/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-06-03-discovery-to-execution-scaling-agents-with-toolboxes-and-rou/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-discovery-to-execution-scaling-agents-with-toolboxes-and-rou/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>Tooling doesn’t break at a small scale—it breaks when teams move to production. AI adoption accelerates, so does the number of tools available to them. Discovering, managing and securing the right tools has quickly become one of the biggest challenges in building production-grade agents. Today, we are announcing new capabilities in Toolboxes in Foundry:</p>https://cyrilbouharb.github.io/posts/2026-06-03-expanding-the-reach-of-document-translation-new-capabilities/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-expanding-the-reach-of-document-translation-new-capabilities/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>Our commitment to advancing cross-language communication takes another major step forward at Microsoft Build. Azure Translator in Foundry Tools is expanding Document Translation with a set of new capabilities designed to meet enterprises where their content lives today — across formats, modalities, and languages. From large language model–powered translations to native image translation and expanded structured content support, these updates help organizations translate more of what they produce, with higher fidelity and less friction.</p>https://cyrilbouharb.github.io/posts/2026-06-03-introducing-agent-optimizer-in-foundry-agent-service/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-introducing-agent-optimizer-in-foundry-agent-service/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-06-03-making-agent-memory-more-reliable-transparent-and-production/Wed, 03 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-03-making-agent-memory-more-reliable-transparent-and-production/<p>There&rsquo;s been an important development in the <strong>Microsoft Agent Framework</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>Memory has always mattered for personalization and continuity. But as customers move agents from demos into production, another requirement becomes just as important: reliability.</p> <p>Enterprise teams need agents that not only remember facts, but also apply what they have learned to follow procedures consistently, recover from repeated failure modes, and complete tasks with greater confidence over time. Memory in Foundry Agent Service is built for this shift, with new procedural memory capability, management experiences, and a set of new features such as time-to-live that give developers more visibility and control over what memory stores.</p>https://cyrilbouharb.github.io/posts/2026-06-02-a-developer-s-guide-to-managing-models-cost-and-quality-in-m/Tue, 02 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-02-a-developer-s-guide-to-managing-models-cost-and-quality-in-m/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="a-developers-guide-to-managing-models-cost-and-quality-in-microsoft-foundry">A Developer’s Guide to Managing Models, Cost and Quality in Microsoft Foundry</h3> <p>The hardest part of building AI systems today is no longer getting access to a capable model. It is knowing how to choose, validate, optimize, and operate the right model across the full lifecycle of a real application.</p>https://cyrilbouharb.github.io/posts/2026-06-02-azure-translator-improving-translation-quality-with-adaptive/Tue, 02 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-02-azure-translator-improving-translation-quality-with-adaptive/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>Your healthcare app needs “La médica” not “El médico.” Your legal documents need precise terminology, not generic translations. When domain-specific language matters, generic LLM translation falls short.</p> <p>Azure Translator’s adaptive translation lets you teach the model your terminology with just a handful of examples—no model training required. In this walkthrough, you’ll create an adaptive dataset, compare baseline vs. adapted translations side-by-side, and see exactly how much difference domain context makes.</p>https://cyrilbouharb.github.io/posts/2026-06-02-build-and-run-agents-at-scale-with-microsoft-foundry-at-buil/Tue, 02 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-02-build-and-run-agents-at-scale-with-microsoft-foundry-at-buil/<p>There&rsquo;s been an important development in the <strong>AI Agents</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>Developers are already building agents, and the early productivity gains speak for themselves. Thanks to coding agents like GitHub Copilot, standing up a working prototype is the easy part.</p>https://cyrilbouharb.github.io/posts/2026-06-02-foundry-iq-build-smarter-agents-faster-with-unified-knowledg/Tue, 02 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-02-foundry-iq-build-smarter-agents-faster-with-unified-knowledg/<p>There&rsquo;s been an important development in the <strong>Agentic RAG &amp; Foundry IQ</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="foundry-iq-build-smarter-agents-faster-with-unified-knowledge-and-serverless-retrieval">Foundry IQ: Build smarter agents faster with unified knowledge and serverless retrieval</h3> <p>Developers building agent fleets keep hitting the same pattern: the agent logic is ready, but the knowledge infrastructure underneath is complex to do well. Getting to production means solving for stability, scale, data access, answer quality, security, and content ingestion all at once. Today, we are enabling developers to have faster impact by simplifying the enterprise knowledge platform.</p>https://cyrilbouharb.github.io/posts/2026-06-02-what-s-new-in-microsoft-foundry-build-edition/Tue, 02 Jun 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-06-02-what-s-new-in-microsoft-foundry-build-edition/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="tldr">TL;DR</h3> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-05-31-what-s-new-in-microsoft-foundry-may-2026/Sun, 31 May 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-05-31-what-s-new-in-microsoft-foundry-may-2026/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="tldr">TL;DR</h3> <ul> <li> <p>Trace-based evaluation for external and hosted agents:Grade real production traces from Foundry, GCP, AWS, or any framework — no hand-curated datasets required.</p> </li> <li> <p>Grok 4.3:xAI’s latest model lands in Foundry for advanced agentic and domain-specific workloads.</p> </li> <li> <p>DeepSeek V4:DeepSeek’s newest model family expands open-model choice in the catalog.</p> </li> <li> <p>Fireworks AI — May update:DeepSeek V4 Pro and Kimi 2.6 arrive via Fireworks for high-performance open-model inference.</p> </li> </ul>https://cyrilbouharb.github.io/posts/2026-05-19-how-to-run-evals-for-the-model-router/Tue, 19 May 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-05-19-how-to-run-evals-for-the-model-router/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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</p>https://cyrilbouharb.github.io/posts/2026-05-14-governance-at-the-speed-of-agents-microsoft-agent-framework-/Thu, 14 May 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-05-14-governance-at-the-speed-of-agents-microsoft-agent-framework-/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-05-12-foundry-local-1-1-live-transcription-embeddings-and-response/Tue, 12 May 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-05-12-foundry-local-1-1-live-transcription-embeddings-and-response/<p>There&rsquo;s been an important development in the <strong>RAG (Retrieval Augmented Generation)</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-05-12-what-s-new-in-microsoft-foundry-april-2026/Tue, 12 May 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-05-12-what-s-new-in-microsoft-foundry-april-2026/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="tldr">TL;DR</h3> <ul> <li> <p>Foundry Local (generally available, GA):Local model inference is production-ready on Windows, macOS on Apple Silicon, and Linux x64.</p> </li> <li> <p>GPT-5.5:The latest GPT-5 family model is available in Microsoft Foundry, with default quota for Tier 5 and Tier 6 subscriptions.</p> </li> <li> <p>Microsoft Agent Framework tracing (Preview):Agent Framework agents can emit OpenTelemetry traces into Foundry for debugging and production observability.</p> </li> <li> <p>Hosted-agent tracing (Preview):Hosted-agent sessions, tool calls, and run steps can now surface in Foundry traces.</p> </li> </ul>https://cyrilbouharb.github.io/posts/2026-05-06-from-local-to-production-deploy-your-microsoft-agent-framewo/Wed, 06 May 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-05-06-from-local-to-production-deploy-your-microsoft-agent-framewo/<p>There&rsquo;s been an important development in the <strong>Microsoft Foundry</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-04-24-chat-history-storage-patterns-in-microsoft-agent-framework/Fri, 24 Apr 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-04-24-chat-history-storage-patterns-in-microsoft-agent-framework/<p>There&rsquo;s been an important development in the <strong>Azure OpenAI &amp; GPT Models</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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?</p>https://cyrilbouharb.github.io/posts/2026-04-22-from-local-to-production-the-complete-developer-journey-for-/Wed, 22 Apr 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-04-22-from-local-to-production-the-complete-developer-journey-for-/<p>There&rsquo;s been an important development in the <strong>AI Agents</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-04-22-introducing-the-new-hosted-agents-in-foundry-agent-service-s/Wed, 22 Apr 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-04-22-introducing-the-new-hosted-agents-in-foundry-agent-service-s/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <p>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.</p>https://cyrilbouharb.github.io/posts/2026-04-22-introducing-toolboxes-in-foundry/Wed, 22 Apr 2026 00:00:00 +0000https://cyrilbouharb.github.io/posts/2026-04-22-introducing-toolboxes-in-foundry/<p>There&rsquo;s been an important development in the <strong>GitHub Copilot</strong> 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.</p> <h2 id="whats-new">What&rsquo;s New</h2> <h3 id="available-in-public-preview-today">Available in Public Preview Today</h3> <p>Toolbox is a new way tocurate, configure, and reusetools across all of your AI agents without rewiring them every time from Foundry.</p> <p>Today, teams build agents across different frameworks and runtimes. Each agent often wires tools directly, with its own authentication, credentials, and integration code. As organizations scale agent usage, this leads to duplicated work, inconsistent behavior, and fragile production deployments.</p>