There’s a reason software engineers who are entrepreneurs or are entrepreneurial are the most positive / excited about AI.
Yes it is rocking + transforming the software engineering profession. And yes many will thrive in this new world, and some stay behind, as all tech shifts
MCP is becoming event-driven.
Something interesting happened in the MCP ecosystem today.
MCP Events is now in beta.
Until now, most MCP interactions have followed a request-response pattern.
An agent needs something, it calls a tool, the server responds, and the agent continues.
But think about how most real-world applications work.
Things happen without us asking for them.
An email arrives. A payment succeeds. Someone opens a GitHub issue. A production server goes down.
Wouldn't it be better if an agent could subscribe to these events and get notified when they happen?
That's exactly what MCP Events is trying to make possible.
Instead of constantly asking a server whether something has changed, clients can subscribe to event types and receive updates through different delivery mechanisms:
- Polling: Check for new events.
- Push: Receive events as they become available.
- Webhooks: Get events delivered through a webhook endpoint.
And this opens up some interesting possibilities.
Imagine an agent that monitors your inbox and prepares replies when important emails arrive.
An agent that watches your GitHub repositories and investigates new issues.
Or an agent that monitors production incidents and starts investigating as soon as something goes wrong.
These are just a few examples.
I think this is an important step for MCP.
We've been making it easier for AI agents to interact with different applications. But interaction isn't just about asking questions and executing actions. It's also about knowing when something happens.
That's a big part of building agents that can operate continuously rather than waiting for someone to prompt them.
One thing worth remembering: receiving an event doesn't automatically authorize an agent to take action. Event payloads are also untrusted input, so security and permission boundaries still matter.
MCP Events is still in beta, and I'm looking forward to seeing how clients and servers start adopting it.
@AgenticAIFdn@aiDotEngineer
Cooking my first skill for non-devs
It's called /vector, and it guides you on how to delegate AI for any task.
Six simple steps, and you'll have a workflow that is easy to use, easy to trust, and gets better over time
I'm planning on releasing frameworks and docs around it so you can run your own VECTOR sessions at your company:
- Find workflows that AI could help with
- Give agents the right context
- Reorder the workflow
- Identify ways it can improve over time (via memory)
Releasing soon. Would you use this?
📰 Newsletter 055 is out.
📌 News item of the week: Anthropic is now a public company, so anyone can buy shares in the company behind Claude, listed on Nasdaq as "ANT".
You can view the edition (and subscribe if you like it!) here: https://t.co/ahDI7Pi2mk
Microsoft Copilot SDK 2.0 is here.
Build faster agents with a new Rust core, serve many users from one shared runtime, and resume sessions across restarts, with control over each session’s identity, tools, and permissions.
🔗https://t.co/ygdoz4kbVI
IT'S HERE! 💫 Aspire 17, our latest major release, has arrived. You've streamlined your stack, and now Aspire is your platform team's favorite tool too! Plus, a new dashboard, Go AppHosts, and lots more.
Blog 👉🏻 https://t.co/lncmJsyoKq
Full What's New 👉🏻 https://t.co/VZJ3atxr5Z
Automate browser tasks with the new GitHub Copilot extension for Chrome & Edge!
Try it in the GitHub Copilot app today with the Enable Browser Use setting.
https://t.co/Q9LcKpiHrI
Has anyone else noticed a recent Claude Code desktop bug where the conversation is rendering an older part of the conversation at the very end of the chat?
In Claude Code, what do you use to indicate your current active sessions?
Pin them? Create a custom section? Something else?
I was using pins heavily for this - but just trying with a custom section called "👉 Active" instead. Seems to work well, and also adds better separation from my pinned dashboards.
I've got a few other sections, like "⏸️ Paused", "♻️ Ongoing agents", etc.
I'm interested to hear what workflows work well for others regarding managing multiple active sessions across different projects.
I do normally just pin current "work in progress" sessions, which also works well. But with Chat sessions and Code sessions being separate lists, if I'm doing stuff in both, then I don't have a list of all wip sessions together. Would be nice to have a way of listing all pinned entries together.
Windows Powertoys has a great new feature called 'Window Hopper' which allows you to `alt-backtick` through windows of the same app.
Claude desktop allows you to pop out chats or code sessions into their own window.
This actually works really well when jumping between multiple agent sessions.
📰 Newsletter 054 is out.
📌 News item of the week: Jensen Huang has resigned as Nvidia's CEO, just as Anthropic gets ready for its IPO.
You can view the edition (and subscribe if you like it!) here: https://t.co/ahDI7Pi2mk
We just shipped Dometrain for iOS and Android! 📱 Start a course on your laptop, then pick up where you left off on your commute.
🍎 App Store: https://t.co/uRI6BfLWro
🤖 Google Play: https://t.co/bNVlD6oR5F
#dometrain