Daily insights on Cloud & AI from a Microsoft Solution Engineer
Build agents that automate tasks across public and private websites with managed browsers, native toolbox integration, Live View, and human control. The post Browser automation tool in Microsoft Found
Explore September's models, Routines, Tool Search, Model Router, and Insights through one two-agent workflow that turns public releases into a Foundry developer changelog. The post What’s new in
Explore the new Azure MCP Server 3.0 stable release, with AI agent tools for Terraform, backup, recovery, and troubleshooting, plus stronger security defaults. The post Azure MCP Server 3.0 stable rel
Learn how Azure Content Understanding grounding, field-level confidence, and calibration help teams prioritize human review and build reliable document workflows. The post From extraction to action: U
Learn how Azure Content Understanding prebuilt analyzers combine domain knowledge with grounding and confidence, and what Advanced Contextualization preview benchmarks show about quality, modeled cost
Learn how to add custom instructions and skills to your repository, use custom agents, and connect MCP servers like Playwright. The post GitHub Copilot app for Beginners: How to teach Copilot about yo
Azure Functions is the event-driven application platform, and Hosted Skills adds AI reasoning to your app. Dynamic Workflows give the app a durable way to carry out AI-led, multi-step work after the t
Compare Azure Document Intelligence and Azure Content Understanding across extraction architectures, workload fit, Layout capabilities, deployment options, and practical evaluation criteria. The post
Add bounded AI reasoning to Python function apps with Azure Functions Agent bindings, while keeping deterministic application code in control. The post Bring agentic reasoning to Python function apps
A look at the targeted AI taskflows behind these findings, the critical Android bugs they uncovered, and how to run the same open-source agent on your own app. The post How we found 24 Android vulnera
In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent
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 c
How we rebuilt the diff surface in the GitHub Copilot app to open a million-line pull request with hundreds of inline review comments. The post Rendering huge pull requests in the GitHub Copilot app a
LangChain Deep Agents is 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 gener
We dive into these questions and other AI hot takes on the latest episode of the GitHub Podcast. The post Should you read the code, is RAG dead, and did Skills kill MCP? appeared first on The GitHub B
From loop engineering to harnesses, squads, and open weights, the GitHub Podcast breaks down the AI terms showing up in developer conversations. The post Decoding the new AI lingo: Loops, harnesses, s
Use Azure Connector Namespace to host MCP servers and give Azure SRE Agent access to the operational tools it needs without managing the server infrastructure yourself. The post Power Azure SRE Agent
These are the lessons we learned evaluating LLMs for real-world secret scanning. The post How to evaluate LLMs before production appeared first on The GitHub Blog.
Structured outputs, web search, web fetch, MCP connector, and tool search are now available for Claude models hosted on Azure in Microsoft Foundry, turning a model endpoint into a production agent pla
See how the open source projects in Session 4 of the GitHub Secure Open Source Fund combined AI-assisted workflows, maintainer expertise, GitHub security tools, expert guidance, and funding to improve
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 Unders
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 docu
Learn how to build tools to simplify how you work—without writing a single line of code. The post How the GitHub legal team used Copilot CLI to streamline their workflows appeared first on The GitHub
Instead of one huge, un-reviewable pull request, teach coding agents to decompose work into a clean, ordered stack with GitHub stacked pull requests. The post Turn one giant AI-generated pull request
A practical GitHub Copilot workflow for prototyping, planning, implementing, and reviewing software without chasing every new AI tool. The post The harness is all you need (mostly) appeared first on T
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? I
Copilot now bills usage at listed API rates. Compare direct model access with the coding workflow, policy, and harness work around it. The post Copilot vs. raw API access: What are you actually paying
The cost of writing code dropped; the cost of owning it didn't. A framework for deciding which changes are actually cheap in the AI era. The post The cost of saying yes has changed appeared first on T
Claude is now generally available in Microsoft Foundry. Here's everything else that shipped between Build 2026 and the end of June — autopilot agents, expanded Toolboxes and Routines, Agent Optimizer'
Explore how the GitHub Copilot agentic harness delivers strong results across multiple benchmarks and leading token efficiency, while maintaining flexibility to choose among more than 20 models. The p
Qubot, our internal Copilot-powered analytics agent, allows any GitHub employee to ask questions about our data in plain language. Here's what we learned as we built it. The post How we built an inter
We shipped a lot at Build 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 new repository-level dataset, published on GitHub under CC0-1.0, helps researchers and developers discover multilingual developer content across READMEs, issues, and pull requests. The post Accelera
Alerts are more trustworthy and actionable when noise is reduced. See how we improved the verification step with context-aware LLM reasoning. The post Making secret scanning more trustworthy: Reducing
Install and configure LSP servers for GitHub Copilot CLI, replacing brute-force grep/decompile with real code intelligence. The post Give GitHub Copilot CLI real code intelligence with language serve
Why edge AI development is still hard AI is no longer confined to cloud experiments. Developers are increasingly expected to deliver AI inside apps, devices, and edge systems where responsiveness, pr
Microsoft Foundry Managed Compute is a new GPU platform-as-a-service for hosting open-source and custom AI models behind the same endpoint, SDKs, and bill as frontier models. The post Announcing Found
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
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 too
Learn how new Document Translation capabilities in Azure Translator, available in Foundry Tools, help developers translate images, PDFs, Office files, DITA, XLIFF, and future LLM-powered document work
With hosted 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 th
Memory has always mattered for personalization and continuity. But as customers move agents from demos into production, another requirement becomes just as important: reliability. Enterprise teams n
Learn a practical model lifecycle for Microsoft Foundry: select the right model, evaluate quality, optimize cost, operate safely, and improve as production needs change. The post A Developer’s Guide t
Your healthcare app needs “La médica” not “El médico.” Your legal documents need precise terminology, not generic translations. When domain-specific language matters, generic L
Learn how Microsoft Foundry helps developers build, deploy, and operate production-ready agents with Agent Framework, Toolboxes, hosted agents, Microsoft 365 distribution, observability, and agent opt
Learn how Foundry IQ helps developers ground agents with unified enterprise knowledge, serverless retrieval, improved agentic retrieval quality, and production-ready security. The post Foundry IQ: Bui
Microsoft Build 2026 brings a major set of Microsoft Foundry updates for developers building agents: hosted runtimes, Toolboxes, memory, Voice Live, Foundry IQ, new models, managed compute, and trust,
May ships trace-based evaluation for any agent on any cloud, Grok 4.3 and DeepSeek V4 in the model catalog, GPT-5 Reinforcement Fine-Tuning at gated GA, three Microsoft Research on-device agent models
Stop paying for idle GPUs while model weights copy to disk. Stream them straight into GPU memory instead with Run:AI Streamer from Azure Blob Storage. The Problem: Every Cold Start Costs You More Than
Walk through running quality, cost, and latency evaluations for the Foundry model router using an open-source GitHub repo designed for router-aware eval pipelines. The post How to run evals for the mo
Foundry Local 1.1 adds live transcription, embeddings, Responses API, WebGPU plugin, and download cancellation. The post Foundry Local 1.1: Live Transcription, Embeddings, and Responses API appeared f
April brings a wave of model arrivals — GPT-5.5, GPT-image-2, Microsoft first-party MAI models for image, voice, and transcription, Gemma 4, and Claude Opus 4.7 — alongside Foundry Local GA, Microsoft
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
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 brie