Trump's lapdog Attorney General, Pam Bondi, has vowed to go after people who employ "hate speech," where hate speech is any speech Donald Trump hates. Trump is already threatening journalists who ask about this clearly illegal move.

Trump is directly threatening a journalist, and it's a bad sign. — Read the rest

The post Trump's DOJ considers dissent to be "hate speech" appeared first on Boing Boing.

Each year, we have an internal conference for the technical writers at Google. I got to keynote today’s session, and it was fun to reflect on what will stay the same, and what will change in the years ahead. These daily reading lists have influenced a lot of my thinking!

[blog] Powering AI commerce with the new Agent Payments Protocol (AP2). This changes things. Would people really trusted unattended agents to perform payment transactions? This new protocol establishes a foundation of trust, and is backed by the companies that matter here. News here too.

[blog] Announcing Tessl’s Products to Unlock the Power of Agents. We’ve seen the early wild-west days of building apps using AI tools, and now the grown-ups are here. This is a product to do more responsible spec-driven development. Sounds good to me.

[blog] Kubernetes 1.34 is available on GKE! This is a short, human-readable summary of what mattered in this latest Kubernetes release.

[article] Oracle Delivers Java 25 Edition of Venerable Programming Language for the AI Era. Java 25 is here, and this language continues to be one of the most relevant in our industry. More coverage here.

[blog] A framework for pricing AI products. It’s not hard to get this wrong, so I appreciate Stripe offering some useful advice on how to think about charging for your AI product.

[blog] The Anatomy of an AI Agent. Good foundational thinking from Allen. The agent is where the next leap comes from. The models alone were never going to change the game.

[article] 15 Best Practices for Building MCP Servers in Production. I don’t know if there are any “best” practices yet, but there are at least good practices that we’ve discovered so far.

[ebook] Building Intelligent Agents with Google ADK. All online and free to access. Great content here on building AI agents using the open source Agent Development Kit.

[blog] Test state, not interactions. Good reminder, especially if you’re leaning on AI to crank out a massive number of unit tests that give you false confidence.

[blog] How to Write Better Python with Ruff on Google Cloud. It seems that with so many folks focused on Python, it’s getting some better developer tooling.

[article] 2-agent architecture: Separating context from execution in AI systems. Here’s some knowledge acquired through experience. When do you introduce a second agent to the architecture? I liked the idea of a context-gathering agent and a real-time agent.

[blog] Learn Your Way: Reimagining textbooks with generative AI. This speaks to me, and I’m fairly convinced it represents the future of education overall. Take trusted, static content and personalize for individual learners.

[blog] Beyond the Horizon: How Angular is Embracing AI for Next-Gen Apps. Angular is doing its thing, and bringing a few new ideas to the table.

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:

Several months ago, GitHub introduced the public preview of its Copilot coding agent, a powerful new capability that allows you to assign GitHub Issues directly to Copilot. From there, the agent works independently in the background, much like a human developer, to complete the task. Copilot evaluates the request based on the information you provide, whether from the issue description or a chat message, then makes the necessary code changes and opens a pull request. Once the work is complete, Copilot asks for your review, giving you the chance to leave comments and request iterations just as you would with any teammate.

It’s a great experience for GitHub users. But what about Azure DevOps customers who rely on Azure Boards for planning and tracking?

Today, we’re excited to announce a new capability in our Azure Boards and GitHub integration: the ability to connect Azure Boards work items with the Copilot coding agent. This means you can create and fill out work items in Azure Boards, then send them directly to GitHub Copilot to handle a wide range of tasks such as:

• Fixing bugs
• Implementing incremental features
• Improving test coverage
• Updating documentation
• Addressing technical debt

How it works

The first step is providing well-crafted instructions in the work item description.

From there, you can click on the Copilot button on the work item to “Create a pull request with GitHub Copilot”. Then select the repository of choice and add any additional instructions as needed.

Once you click Create, the work item is sent to the Copilot coding agent to begin processing. We pass along all relevant content from any large text fields such as Description or Repro Steps, as well as the last 50 comments. The coding agent then generates a branch and a draft pull request, which is automatically linked back to the work item for full traceability.

Depending on the complexity of the requested change, the coding agent may need some time to create and execute its plan. Once the work is complete, its status is updated on the work item. We also add a comment in the discussion letting you know the pull request is ready for review.

From there, it is up to you to review and interact with the pull request directly in GitHub.

Requirements to use this feature

There are a couple of items that are required before you can interact with the GitHub Coding agent from the work item.

1. You must have the Azure Boards and GitHub integration enabled, with the repositories connected to your Azure DevOps project. Learn more.

2. The repos connected to the Azure DevOps project must have the Copilot coding agent enabled. If you are a GitHub Copilot Enterprise or GitHub Copilot Business subscriber, Copilot coding agent is disabled by default and must be enabled by an administrator before it is available for use. If you are a GitHub Copilot Pro or Pro+ subscriber, Copilot coding agent is enabled by default.

   Learn more about how to enable the coding agent on your repositories.

3. Your organization must be enabled for the private preview. See below for details.

4. Go to the Installed GitHub App page and update the Azure Boards app to approve the recent permission changes. This will allow the Azure Boards app to communicate with GitHub Copilot.

   

Signing up for the preview

This feature is currently in private preview, which means it is enabled for organizations by request only. Limiting participation allows us to keep the number of organizations manageable, collect feedback effectively, and work through any technical issues that may arise.

To request access for your organization:

1. Confirm with your organization admin that enabling this feature is approved.
2. Email us your organization name (for example: dev.azure.com/contoso).
3. We will notify you by email once the feature has been enabled.

Expectations

We worked quickly to get this into customers’ hands, so not all planned features are yet included in the preview. Some elements were deferred in order to start gathering feedback earlier. We will be working on these items over the next couple of sprints.

• Backlog levels: The coding agent integration is currently available for most work item types. In the future, this will be refined so that it is only available for work item types in the requirements and task backlog levels, including bugs and issues.

• GitHub Enterprise Cloud with Data Residency: Support for the coding agent was only recently released. Additional work is needed before full integration with Data Residency is available.

Collecting Feedback

If you run into any issues or want to share feedback, please create a report through our Developer Community site. Be sure to include “Azure Boards Coding Agent” in the title so we can track it quickly.

What is next?

As noted above, we still have a couple of sprints of work ahead to round out the experience and continue refining based on your feedback.

We’re excited to put this feature in your hands and can’t wait to see the creative ways you use it. Your feedback is invaluable, and we look forward to hearing from you as we continue to improve this new integration between Azure Boards and GitHub.

The post Azure Boards integration with GitHub Copilot (Private Preview) appeared first on Azure DevOps Blog.

Tomorrow I’ll be giving a webinar on Building AI Agents in RavenDB. I’m going to show off some really cool ways to apply AI agents on your data, as well as our approach to AI and LLM in general.

I’m looking forward to seeing you there.

Caution: This is going to blow your mind.

Learn how OpenAI is building age prediction and parental controls in ChatGPT to create safer, age-appropriate experiences for teens while supporting families with new tools.

Explore OpenAI’s approach to balancing teen safety, freedom, and privacy in AI use.