Feeds

We’re continuing to make it easier for developers to bring their services into the AI ecosystem with the Model Context Protocol (MCP). Today, we’re announcing two new capabilities: Streamable HTTP Transport: The Agents SDK now supports the new Streamable HTTP transport, allowing you to future-proof your MCP server. Our implementation allows your MCP server to simultaneously handle both the new Streamable HTTP transport and the existing SSE transport, maintaining backward compatibility with all remote MCP clients. ...

Taking a short trip to Sunnyvale tonight so that I can talk to and learn from a couple of customers tomorrow. It was also a chance to refresh some demos and keep the skills sharp! [blog] Using Google ADK to Build and Deploy a Stock Market AI Agent to Cloud Run in Minutes. If agents feel abstract to you, keep skimming through examples to get a sense for when and where you’d deploy one. ...

Top Links EPISODE 15 – Scott & Mark Learn To… Vibe Coding (Part 2) (Scott Hanselman & Mark Russinovich) Getting Started with Azure MCP Server: A Guide for Developers (Lee Stott) Microsoft announces new European digital commitments (Brad Smith) Retrieval-augmented generation with Llama Stack and Node.js (Michael Dawson) Docker Desktop 4.41: Docker Model Runner supports Windows, Compose, and Testcontainers integrations, Docker Desktop on the Microsoft Store (Yiwen Xu) Visual Studio 2022 v17.14 Preview 5 release notes (Microsoft Learn) ...

HCP Vault Radar is now generally available to help organizations discover and prioritize unmanaged secrets, expanding on Vault’s secret lifecycle management capabilities. Accompanying GA is the ability to import unmanaged secrets discovered in collaboration platforms and Git-supported version control into HashiCorp Vault for centralized management. Securing sensitive data in Vault, such as secrets, is crucial for protecting an organization's most valuable assets and ensuring that access to critical systems is tightly controlled. Securely storing secrets with Vault also presents the opportunity to transition unmanaged secrets to dynamic secrets or implement an automated rotation strategy that minimizes risks associated with credential exposure. ...

This is a continuation of the blog Getting Started with DevOps and .NET MAUI showcasing how to build a .NET MAUI Library using DevOps. This blog uses a sample project made Mike Parker that shows how to use MSBuild files in NuGet packages. In this blog, the focus is on the GitHub Actions workflow to automate the building, packaging, and publishing of the sample .NET MAUI Library. Overall Workflow Overview The build_publish_nuget.yml defines the end-to-end workflow for building and publishing the .NET MAUI Library NuGet Package. The versioning step handles versioning of the NuGet package for every build via GitHub Actions. The workflow consists of two main jobs: buildLibrary and publish. These jobs use dotnet commands to build and pack the .NET project. The publish job depends on the buildLibrary job completing successfully. Once you have created the NuGet package, we can push it to nuget.org (or an Azure DevOps Internal Feed). ...

We are inspired by the possibilities of AI to help people be more creative, productive, and stay closely connected on WhatsApp, so we set out to build a new technology that allows our users around the world to use AI in a privacy-preserving way. We’re sharing an early look into Private Processing, an optional capability that enables users to initiate a request to a confidential and secure environment and use AI for processing messages where no one — including Meta and WhatsApp — can access them. To validate our implementation of these and other security principles, independent security researchers will be able to continuously verify our privacy and security architecture and its integrity. AI has revolutionized the way people interact with technology and information, making it possible for people to automate complex tasks and gain valuable insights from vast amounts of data. However, the current state of AI processing — which relies on large language models often running on servers, rather than mobile hardware — requires that users’ requests are visible to the provider. Although that works for many use cases, it presents challenges in enabling people to use AI to process private messages while preserving the level of privacy afforded by end-to-end encryption. ...

This post follows on from my previous post, in which I discussed some theoretical/experimental dependency-injection lifetimes, based on the discussion in an episode of The Breakpoint Show. In the previous post I provided an overview of the built-in Dependency Injection lifetimes, and described the additional proposed lifetimes: tenant, pooled, and drifter. The previous post provided a overview of each of these proposed lifetimes, and an implementation of the drifter (time-based) lifetime. In this post I provide an example of the “pooled” lifetime. ...

Today’s edition is chock-full of fascinating items to read. How do you measure collaboration within a team? Or run AI developer tool experiments? How should you roll out AI tools to a team? What’s reinforcement learning all about in modern LLMs? Dig in. [article] Software Development Is a Team Sport. Here’s some new research that measures collaboration quality between members of a team. [article] How to Run a Generative AI Developer Tooling Experiment. This looks at AI coding results when Cursor and Copilot go head to head. ...