“The future is already here — it’s just not very evenly distributed.” –W. Gibson

I was on an AI-focused podcast last week talking about how a new software engineer should work differently in this new era of AI. It reminded me of a conversation I had recently with a college grad in their first professional software engineering career. They were asking for advice from a wizened old coder (I was even wearing the suspenders). With the latest in AI coding tools, they were productive for sure, but they didn’t understand all of the code that the AI agent was producing. They were afraid that without being forced to write the code they old-fashioned way for cough 40 years cough, that they weren’t ever really going to understand what they were doing.

In a recent tweet, Dinko makes an excellent point about much of our Dart ecosystem being comprised of “hobby project[s]” and having “limited support.” He’s not wrong and that applies to Flutter as well. Most of the Flutter ecosystem is driven by passionate OSS developers. And that passion drives different devs to do different things — some like the code, some like the samples, some like the docs, some like the support and some just like to publish a package right out of flutter create and then move on with their day.

A little while ago, I was inspired by Thorsten’s blog post on building an AI Agent using Rust to build an AI Agent using Dart. The combination of a conversation with Gemini and a set of tools allowed us to build an agent that could take some prompts from the user and turn them into not just responses (Ask mode), but actions (Agent mode!). In the spirit of Agentic Apps month for Flutter this month, I wanted to share how to do the same thing in your Flutter app using the most recent release of the Flutter AI Toolkit.

The Python community has a library called pydantic that adds type checking at run-time to a dynamically typed language. The library allows them to be “pedantic” about type validation in Python aka pydantic; get it? : )

To say that there has been a lot of activity in the AI space for developers lately would be an understatement. As we transition from “Ask” mode in our AI-based dev tooling to “Agent” mode, it’s easy to see agents as something magical.

I often find myself maintaining open source projects. I’ve contributed to many over the years, even hosting multi-person “source available” projects on this very website in zip files before there were such things as GitHub or Pull Requests or Open Source Software. No matter what mechanism I’m using to manage the project, if it’s popular, I get issues filed against that project. Those issues break down into two categories:

Hello, again, and welcome to another installment of “Flutter + AI = Joy.” In today’s episode, we’re taking a behind-the-scenes look at the design and implementation of the generative AI features in the latest version of DartPad. Before we get started, if you haven’t already read Amanda’s most excellent blog post for an overview of the new functionality, I recommend starting there.