Analytics as Code is slowly turning into the norm for analytics options, a lot the identical as Infrastructure as Code and Safety as Code. The extent of confidence in your resolution that you just get from model management and CI/CD pipelines is difficult to beat.

In the meantime, sensible IDEs, like Cursor and Windsurf, are getting increasingly more standard, serving to software program engineers to be extra productive. For information analysts, Cursor may help write SQL or Python code. It’s usually good with widespread applied sciences and languages, as there’s plenty of information to coach on. However how are you going to reap the benefits of AI options for extra area of interest applied sciences like Analytics as Code?

On this article, I’ll present you how one can take advantage of any AI-powered IDE when working with Analytics as Code by leveraging rule information, VS Code extensions, and MCP servers.

I need to admit, once I first tried utilizing our Analytics as Code with Cursor, I used to be fearful we’d must make plenty of adjustments to our setup to reap the benefits of AI options in full. However the out-of-the-box expertise was surprisingly good.

Work by Instance

To start with, AI coding brokers are fairly good at creating new code by instance. In case you’re not ranging from scratch and have already got some analytics within the workspace, the possibilities are Cursor will work nice for you. It helps that our Analytics as Code syntax is predicated on YAML, and AI fashions know how one can write a legitimate YAML file already — that’s included within the coaching. They solely want to determine the proper schema for our particular use case.

VS Code Extension

The second contributing issue is that we have already got a VS Code extension — that works in Cursor and Windsurf as they’re each primarily based on VS Code.

The extension is out there in each Microsoft Market for VS Code and OpenVSX Market for Cursor. Simply seems for “GoodData” within the extensions tab.

Our extension does plenty of issues, from syntax highlighting to autocomplete, reference decision, and previews. However most significantly, schema validation and reference integrity validation. Cursor listens to any validation errors the extension produces and is able to fixing them robotically.

Let’s say you’re constructing a brand new visualization: Cursor will have a look at any present visualizations for examples and produce a brand new one. Positive, it could hallucinate a reference to some non-existing metric, however then our extension will spotlight the error and recommend a listing of legitimate metrics that can be utilized as a substitute. And since Cursor works iteratively, it could possibly select the suitable metric and repair the code earlier than handing management again to you.

However we are able to take this even additional by leveraging extra superior Cursor options, rule information and MCP server integration.

It’s price noting that many of the options described right here will even work in different VS Code-based sensible IDEs, like Windsurf.

Cursor Guidelines

The rule information are designed for builders to give Cursor extra context concerning the workspace. It’s a easy Markdown file the place you may describe how one can work with sure file varieties, how the challenge is structured, how one can carry out a selected job, and so forth. All of the stuff you most likely ought to have had within the inner documentation a very long time in the past, however have been too lazy to write down down.

Rule information are the right place to offer Cursor with examples to scale back its dependence on pre-existing gadgets for examples, in addition to to cowl uncommon circumstances that you just doubtless don’t have within the workspace simply but.

MCP Server

I used to be testing Mannequin Context Protocol (MCP) and seen plenty of commonalities with Language Server Protocol (LSP). Each protocols present a helpful abstraction for the communication between server and shopper, in addition to options discoverability, authentication, and transport for the messages. This implies you may implement your LLM app as an MCP shopper and never have to care if the MCP servers you’re connecting to are written in several programming languages, working domestically, or deployed on a third occasion server.

This makes an MCP server an ideal companion for AI-driven growth in Cursor, because it enhances the Language Server. It will probably present further context and set off (read-only) actions on the person’s behalf — all good issues on your productiveness.

Think about you have got a brand new desk added to the information supply. With well-defined guidelines, Language Server and MCP Server, Cursor can robotically:

• Scan the database mannequin to overview the brand new desk.
• Pattern the information to know the contents.
• Create the dataset definition.
• Validate it and repair any points.
• Run the dataset preview to confirm the end result.

Beginning v0.14.0, the GoodData for VS Code extension comes with batteries included for AI-assisted growth.

New Challenge Initialization and Cursor Guidelines

When beginning a brand new challenge, now you can cross a --cursor parameter so as to add boilerplate Cursor guidelines and a configuration for the MCP server to let Cursor understand how to connect with it. See all instructions and choices in our documentation.

The rule information are a superb start line for any analytics challenge, however be happy to edit these as you establish any gaps in Cursor’s understanding of your code.

Bundled MCP Server

The extension itself now comes with the MCP server bundled in. As soon as enabled and configured in Cursor, it can present instruments for database schema scanning, every kind of previews, in addition to shortcuts for workspace deploy and clone instructions.

AI-assisted software program engineering is in a unstable state nowadays. Some folks swear by it, others hate it. Some say it’s a productiveness booster, whereas others name it a time-waster. It’s not clear what ultimate type it can take when all is claimed and executed, nevertheless it’s fairly clear that software program engineering is altering. And, extra importantly, information analysts take be aware, or danger being left behind.

Wish to study extra?

In case you’d wish to study extra about our totally different AI initiatives, you may learn a few of our different articles, corresponding to Why AI in Analytics Wants Metadata or our different technical articles.