Agent Builder in Copilot turns one prompt into a working agent. The person who knows the process best builds it, no code required. See Agent Builder in action. piped.video/dlS2meHJWAk Build a specialist AI agent without writing a line of code. Describe what you want in one prompt, and Copilot Agent Builder generates the name, instructions, skills, and knowledge setup for you — grounded only in the SharePoint sites, files, and Copilot Connectors you choose. #CopilotAgentBuilder #aiagents #copilot #microsoft365 #microsoft

Playwright MCP or Playwright CLI: pick either, your agent gets all of this 🎭 🧰 WebMCP: pages hand the agent their own tools 🔎 Find: grep the page instead of reading all of it 🪶 Leaner snapshots, fewer tokens on every step 🔴 Do it by hand once, get Playwright code back 🗣️ Codegen in TypeScript, Python, Java and C# 🔌 Your real Chrome, logins included 🎬 60 fps video with an animated cursor and chapters 📱 Mobile and device emulation 🌗 Light/dark flipped mid-session 🌐 Mock any request, or pull the plug and go offline 📸 Hi-res screenshots 🩹 Crashed tab or dropped connection? It'll recover npx @playwright/mcp@latest github.com/microsoft/playwri… npm i -g @playwright/cli@latest github.com/microsoft/playwri…

I miss Prague and Bratislava… the beer is so good in Europe.

AI Guardrails vs AI Governance 𝗔𝗜 𝗴𝘂𝗮𝗿𝗱𝗿𝗮𝗶𝗹𝘀 are built to control what an AI system can do. They can filter risky prompts, block sensitive data, restrict what information can be retrieved, or limit which tools and APIs an agent can use. That makes them useful for enforcing specific technical boundaries inside the system. But guardrails only solve part of the problem. With 𝗔𝗜 𝗴𝗼𝘃𝗲𝗿𝗻𝗮𝗻𝗰𝗲, the focus is broader. It defines how AI should be managed across the organization: what risks are acceptable, who owns them, what standards teams should follow, and how systems are reviewed over time. So governance defines what should be allowed and who is accountable. Guardrails help enforce what the AI can actually do. But for coding agents, that creates another challenge: how do you make those engineering standards available while the agent is actually writing code? 𝗜𝗳 𝘁𝗵𝗲𝘆 𝗼𝗻𝗹𝘆 𝘀𝘂𝗿𝗳𝗮𝗰𝗲 𝗮𝘁 𝗿𝗲𝘃𝗶𝗲𝘄 𝘁𝗶𝗺𝗲, the code has already been written. That’s where Qodo’s Agentic Toolbox comes in. It lets coding agents pull in team rules and codebase context, then bring in independent review while they work, 𝗯𝗲𝗳𝗼𝗿𝗲 𝘁𝗵𝗲 𝗣𝗥 becomes the first real checkpoint. So the same agent writing the code isn't the only agent checking it. Install the Toolbox → lucode.co/agentic-toolbox-qo… What else would you add? —— ♻️ Repost to help others learn AI. 🙏 Thanks to @QodoAI for sponsoring this post. ➕ Follow me ( Nikki Siapno ) to improve at AI and system design.

I don't get how secondary market ticket price gouging is legal. There should be a limit over the price of the ticket, and they should have to be sold by individuals, not companies who use bots to gobble them up...

Does it matter? They're going to get away with it anyway and there will be no consequences. Why aren't Democrats following on his office claims. Surely someone could find out if he's working or not??? Image one of us AWOL from work, nobody knows if you're coming back. Fired day 2

.@Canada you should rename Lake Superior to Lake Canada is Superior

🚀 Most engineers know CI/CD. Fewer truly understand GitOps. And MLOps? That’s where modern AI systems scale. If you’re building cloud-native or AI-powered products in 2026, understanding the difference between these three workflows is no longer optional. Here’s the simplest breakdown 👇 🔹 CI/CD → Automates software delivery From writing code → testing → building → deploying faster and safer. 🔹 GitOps → Uses Git as the single source of truth Infrastructure and deployments become declarative, auditable, and automatically reconciled. 🔹 MLOps → Brings discipline to Machine Learning lifecycle From feature engineering and model training → monitoring → retraining AI models in production. 💡 Think of it this way: ✅ CI/CD = Shipping applications efficiently ✅ GitOps = Managing infrastructure reliably ✅ MLOps = Operating AI systems at scale As companies move toward AI-native engineering, these three practices are increasingly working together — not separately. 📌 Which one are you currently working with the most: CI/CD, GitOps, or MLOps? 𝗕𝗲𝗰𝗼𝗺𝗲 𝗯𝗲𝘁𝘁𝗲𝗿 𝗮𝘁 𝗔𝗜 𝗶𝗻 𝗷𝘂𝘀𝘁 𝟭 𝗺𝗶𝗻𝘂𝘁𝗲 𝗮 𝗱𝗮𝘆. 𝗝𝗼𝗶𝗻 𝗺𝘆 𝘄𝗲𝗲𝗸𝗹𝘆 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿 𝘄𝗵𝗲𝗿𝗲 𝗜 𝗱𝗼𝗰𝘂𝗺𝗲𝗻𝘁 𝘁𝗵𝗲 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝗷𝗼𝘂𝗿𝗻𝗲𝘆 𝗼𝗳 𝗔𝗜 𝘁𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻. 👉 𝗦𝗶𝗴𝗻 𝘂𝗽 𝗳𝗿𝗲𝗲 now → avsl.beehiiv.com/ Follow @AiswaryaVenkit1 for more such insights!!

🚀 Microsoft Fabric — Explained Simply Most companies don’t have a data problem. They have a “too many tools” problem. That’s where Microsoft Fabric changes the game 👇 👉 Imagine having: • Data pipelines * Storage * Analytics * Dashboards * AI All in one single platform That’s exactly what Microsoft Fabric delivers. 💡 What makes it powerful? ✅ One unified data lake (OneLake) ✅ Built-in ETL + Data Engineering ✅ Real-time + batch analytics ✅ AI integrated with Copilot ✅ Seamless with Azure + Microsoft 365 No silos. No tool switching. No complexity. ⚡ Before vs After ❌ Multiple tools (Data Factory + Synapse + Power BI) ❌ Data duplication ❌ Complex architecture ✅ One platform ✅ Faster insights ✅ Lower cost ✅ Easier collaboration 🧠 Think of it like this: Microsoft Fabric = Operating System for Data Just like Windows manages apps, Fabric manages your entire data ecosystem. 📊 Use cases: * Business dashboards & reporting * AI/ML model building * Real-time analytics (IoT, logs) * Data warehousing & lakehouse 🔥 If you're working with data in 2026, this is not optional — it's foundational. Would you replace your current stack with Fabric? 𝗕𝗲𝗰𝗼𝗺𝗲 𝗯𝗲𝘁𝘁𝗲𝗿 𝗮𝘁 𝗔𝗜 𝗶𝗻 𝗷𝘂𝘀𝘁 𝟭 𝗺𝗶𝗻𝘂𝘁𝗲 𝗮 𝗱𝗮𝘆. 𝗝𝗼𝗶𝗻 𝗺𝘆 𝘄𝗲𝗲𝗸𝗹𝘆 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿 𝘄𝗵𝗲𝗿𝗲 𝗜 𝗱𝗼𝗰𝘂𝗺𝗲𝗻𝘁 𝘁𝗵𝗲 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝗷𝗼𝘂𝗿𝗻𝗲𝘆 𝗼𝗳 𝗔𝗜 𝘁𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻. 👉 𝗦𝗶𝗴𝗻 𝘂𝗽 𝗳𝗿𝗲𝗲 now → avsl.beehiiv.com/ Follow @AiswaryaVenkit1 for more such insights!!

SharePoint and the Future of Work, Apps, and Agents

Chicago folks! Join us Thursday evening at the Aon Center to learn more about cloud computing! Azure MVP Brian McKeive (@mcbeev ) will present "Faster .NET on Azure App Service: The Hard Lessons I Paid For"! Learn more and register at meetup.com/the-chicago-cloud…

💡 Weekly update on the @m365pnp upcoming community calls from Microsoft365 & Power Platform Community • Calls for this week with agenda details 📅 • Focus on #Copilot, #Microsoft365 & #PowerPlatform • Demos this week by Joseph Jang, @vesajuvonen, Sandeep PS, @tavikukko & Ramin Ahmadi 📝 See details → pnp.github.io/blog/weekly-ag…

Great post from @clamanna It is fun to see this in existing teams and products like OneDrive and SharePoint. Here is one example of a team that 4x’d their delivery spanning fundamentals and features to customers. With Cowork, Scout, Copilot Studio, and GitHub we’re bringing you the tools we use to help teams go faster - and have more fun.

July was a big month for Copilot in PowerPoint. We made it easier to apply a previous deck's style or your company brand to your presentation, use Copilot to help you keep feedback organized by supporting comments and made several updates your iOS and iPad experience.

Today we’re expanding model choice in Microsoft 365 Copilot with the addition of Anthropic’s latest model—Claude Opus 5. msft.it/6017vCQ3v

Copilot in #SharePoint updates - creating Office content and interactive HTML dashboards, organizing content, automating workflows, leveraging skills. Excited to see what you make! techcommunity.microsoft.com/…

What ever happened to padded toilet seats?

Copilot in SharePoint is now in expanded public preview. Turn ideas into action, from creating sites and pages to organizing content, building lists, and keeping information up to date. ▶️Learn about Copilot in SharePoint at msft.it/6015vmM6F

A few months ago, we introduced codename MDASH, our new multi-model agentic scanning system, now in expanded private preview. Built to discover, validate, and prove software vulnerabilities at AI speed, the system is helping us explore new benchmarks and insights as we apply it across some of our most complex environments. Read the latest updates: msft.it/6011vlLW3

Here are some interesting links published this week: linkedin.com/pulse/microsoft… microsoft.com/en-us/microsof… piped.video/live/CkPIus2qYxo… learn.microsoft.com/en-us/mi… #CopilotFriday