Have you ever explained a bug or issue you’re having to someone, only to discover the solution mid conversation, as if simply describing the problem helped you catch your own mistake? This is actually quite common and has been used by software engineers for decades, with the offi...

When we launched our MCP server, we knew it’d be important for it to have tests, just like any other piece of software. Since our MCP server has over 20 tools, it’s important for us to know that LLMs can pick the right tool for the job. So, this was the main aspect we wanted to t...

Netlify DB is now live – a production ready Postgres database you can provision in one click or CLI command, directly from your Netlify project. Powered by Neon, it spins up in seconds with no external signup required. When you’re ready, you can claim the database to link it to y...

Code generation has been one of the most interesting use cases for LLMs. While the best models can generate decent code for isolated problems, there is a big gap between these code snippets and fully functional applications. Agent based solutions are better suited to create apps....

Our engineering team at Neon works across a large codebase written in TypeScript, Go, Rust, and Python. We’ve been experimenting with Cursor as a tool to help us move faster – here’s our favorite workflows, and where we still find a few things missing. Our favorite Cursor workflo...

Nothing works first time if you are coding, you are debugging. This used to mean console.log(), print statements scattered like breadcrumbs, and hours spent staring at stacktraces trying to decipher what went wrong and where. No longer. Now, errors are chucked into Claude to deci...

Replit just launched App History, a unified timeline that lets you roll back to earlier versions of your app or even preview them live in the browser. Now, you can try multiple approaches when building with Replit Agent, knowing that every version of your app (code and data) is s...

Design teams are constantly battling the clock great ideas lose momentum when they get stuck waiting on engineering resources. Too often, static prototypes aren’t enough to validate real concepts, and the backlog just keeps growing. That’s why we’re taking a new approach leveragi...

Should we be generating Model Context Protocol (MCP) servers directly from existing API specs? MCP is designed to let AI agents like those in Claude, Cursor, and Windsurf interact with tools and APIs. So, can we just treat our existing REST APIs as the interface for LLMs and enti...

If you’re vibe coding an app, don’t leave the database choice up to the AI code generator. Take control and tell it you want to use Neon. Why? Because Neon’s built in safety features ensure your app stays secure and runs smoothly, even if you’re not a database expert! It’s free t...