We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
Analysis Summary
Ask yourself: “Whose perspective is missing here, and would the story change if they were included?”
Worth Noting
Positive elements
- This video provides a clear visual example of how Model Context Protocol (MCP) and AI agents can interact with a local file system to modify code across multiple files.
Be Aware
Cautionary elements
- The demonstration uses a very simple 'To-Do List' app, which is the 'Hello World' of coding; the ease of 'vibe coding' may not scale as linearly to complex, legacy codebases as the video suggests.
Influence Dimensions
How are these scored?About this analysis
Knowing about these techniques makes them visible, not powerless. The ones that work best on you are the ones that match beliefs you already hold.
This analysis is a tool for your own thinking — what you do with it is up to you.
Related content covering similar topics.
Building an AI App in TypeScript & Bun with Groq SDK using Function Calling
Zaiste Programming
WTF Is OpenClaw? And Should You Even Care?
Elevated Systems
Level Up Your LangChain4j Apps for Production
Java
Building AI agents for 127 million customers: Practical lessons from Nubank
Building Nubank
A Conversation with Jiquan Ngiam About Agent + MCP Security
Unsupervised Learning
Transcript
Vibe coding is a new practice that involves building out an application by using AI prompts. Vibe coding can be really helpful for quickly prototyping an app or experimenting with ideas. In this video, I'm going to show you how we can use Goose to vibe code a to-do list app. So, let's jump right in. Here, I've got Goose open with a brand new iOS app. First, I'm going to ask Goose to build a to-do list app where I can create to-dos, mark them as complete, and delete them. I'll let Goose work on that. And after a bit, we can see the changes it made. Taking a look at the app, Goose seems to have done exactly what I asked for. So, the app works well, but this isn't quite the style I had in mind. I'm going to ask Goose if it can give the app a more dark and minimal look. I'll let Goose make its updates. And great, this looks much better, and everything is still working properly. Next, I'm going to make a feature request. I want to be able to organize my to-dos by grouping them into categories. One of the helpful things that Goose does when it builds a new feature is it tells me what it did as well as how to use the feature. And now I can make different categories for all of my checklists. Last thing, I want to add a progress bar for each category to reflect how many to-dos have been completed. This is a slightly more difficult feature, but again, Goose handles it with no problem. We can see Goose added the new progress bar and it updates as I check off each item. At this point, I can continue to vibe code more features and adjustments or I can jump into the code myself and start to make some tweaks on my own. Either way, Goose has made prototyping this app so much quicker than it would have been otherwise. So go on and give goose a try and see what you can vibe code for
Video description
In this video, we walk through a demo of vibe coding a to do list app with Goose. Vibe coding is a new practice that involves building an application by only using AI prompts. It can be extremely helpful for quickly prototyping an app or experimenting with ideas. If you're curious what it feels like to collaborate with AI as a coding partner, this video is for you. 🔗 Links: Goose docs: https://block.github.io/goose/