Typically, an issue you didn’t know existed meets an answer you didn’t got down to construct. That’s exactly what occurred when a routine dialog about our developer docs became an AI-powered instrument for our content material crew.

Right here’s the way it all got here collectively:

How It Began

At first of 2025, my crew at Automattic (WordPress.com’s father or mother firm) had taken over duty for updates and upkeep of the WordPress.com Developer Docs.

As a part of this course of, we met with Alexa, a content material advertising and marketing supervisor for WordPress.com, to talk about processes and pointers round this handover.

Towards the tip of the assembly, Justin Tadlock, my crew lead, requested a easy query, “Is there the rest we can assist you with?” Alexa replied, “I’ve a query, but it surely’s unrelated to the docs. Do any of you already know if a calendar view of GitHub Points is feasible?”

The Drawback

Alexa defined that her crew makes use of GitHub Points and Initiatives to handle content material publishing, a typical apply in software program corporations. 

The method typically labored effectively however was lacking one crucial piece for visibility into scheduled content material and content material gaps: a calendar view. Their crew couldn’t view these content material points in a month-to-month calendar to get a fast snapshot of what was deliberate for the month forward, because the GitHub Initiatives view solely affords a roadmap-style view—useful for growing software program however not supreme for content material planning. Nick Diego was in that assembly. You most likely know Nick from his Revolutionize Your WordPress Development with Cursor AI video.

Since management at Automattic inspired us to discover AI instruments like Cursor, Nick and I had spent the previous few months experimenting and had some improbable successes, constructing every thing from WordPress plugins to a desktop app for viewing a local WordPress debug log. 

In case you’ve by no means heard of Cursor, it’s an AI-powered code editor. Forked from the favored Visual Studio Code editor, Cursor takes the thought of AI-assisted coding to the following stage by including a ChatGPT-like agent to the combo. This AI-powered chatbot interprets your written prompts into working code. This idea has turn out to be so standard it even has its time period—vibe coding, or utilizing a big language mannequin for coding.

We have been each impressed by an Automattic City Corridor in December, the place certainly one of our engineering leads used Cursor to routinely generate a pull request for a challenge he was engaged on.

Now, I can’t say this for certain as a result of it was throughout the digital divide of Google Meet, however I’m virtually certain Nick and I regarded immediately at one another and had the identical thought on the identical second. 

“This isn’t that onerous to unravel with AI.” Nick was the primary to specific this concept, so we spent the following jiffy chatting about it. We each agreed that the one difficult half could be determining the best strategy to question the information we would want to fetch the related GitHub Points from the challenge view; constructing the precise calendar app could be fairly straightforward.

Thankfully for us, our colleague Birgit Pauli-Haack was additionally on that decision. She talked about that, sure, GitHub Initiatives have a publicly queryable API. Nonetheless, it was not a REST API however a GraphQL API. She had explored querying GitHub Challenge knowledge with some success, however she hadn’t dived into one thing like this earlier than.

Sitting on that decision and listening to all this info, I felt like producing a calendar view for these GitHub Points could be doable and comparatively easy. I simply needed to:

1. Determine the GraphQL question.
2. Use Cursor to construct an online app round it.

How exhausting may or not it’s?

Perplexity to the Rescue

The very first thing I needed to do was work out the GraphQL question, and I’ll be the primary to confess that my data of GraphQL is restricted.

I’ve written tutorials on utilizing GraphQL to construct static frontends for WordPress web sites, also referred to as “Headless” or “Decoupled” WordPress websites. In that course of, I used the WP GraphQL plugin that our colleague Jason Bahl developed; nevertheless, I’ve by no means used it in a manufacturing surroundings or used it to construct an online app.

So I questioned if I may take a shortcut on this studying curve with AI and craft the GraphQL question with out understanding it deeply and fully.

Then I remembered that WordPress.com had partnered with Perplexity. Perplexity is comparable in some ways to ChatGPT, but it surely describes itself as an AI-powered reply engine that allows you to analysis the net.

What I like about Perplexity is that when it outputs the generated AI response, it additionally consists of all of the sources of data it has used. If the reply you get from Perplexity isn’t fairly what you have been searching for, you’ll be able to open the supply hyperlinks to do additional guide analysis.I additionally wanted a strategy to take a look at and validate the GraphQL question that Perplexity would offer. Thankfully, GitHub has a GraphQL API Explorer, which lets you authenticate along with your GitHub account and run legitimate GraphQL queries on any personal or public GitHub repositories you’ll be able to entry.

It took me a complete of two Perplexity Threads (back-and-forth conversations with Perplexity) to determine the GraphQL question. The primary Thread was me asking it to construct fundamental variations of the question, operating them within the explorer, after which I fine-tuned the question primarily based on the information from the explorer. After three rounds of fine-tuning, I began a brand new Thread and created a extra particular immediate, utilizing all the teachings I’d discovered from the earlier Thread. Testing that question within the Explorer returned the precise knowledge set I’d want for the net app.

The Cursor Construct

The subsequent step was to start app improvement with Cursor. One of many issues that I found early on (each by way of Nick’s video and this Twitter thread) was the thought of utilizing Cursor to generate an directions file. The concept is to have a “dialog” with the Cursor agent and share the fundamental necessities of the appliance.

You then instruct the agent to jot down out these necessities to a necessities.md markdown file. Subsequent, you ask the agent to undergo the necessities file itself and ask you any clarifying questions in regards to the necessities. As you reply the clarifying questions, you instruct the agent to replace the necessities file.

After you have the necessities file, you instruct the agent to create the directions.md file primarily based on the necessities file, which outlines the steps wanted to construct the appliance.

As a result of I already had the GraphQL question, I additionally added it to a file within the challenge listing. Armed with my necessities.md file, directions.md file, and the file containing the question, I instructed the Cursor agent to start out constructing the app step-by-step, following the directions.

In about two hours, I had a working prototype. I returned to Perplexity a couple of times to assist me clear up one thing that Cursor couldn’t do by itself. I wrote no different code past operating one or two terminal instructions to arrange the challenge listing and its dependencies or operating the event server to serve the app for testing.

It took me perhaps one other hour to shine the app the next Monday morning (largely including colours and making GitHub Points clickable). By noon, I felt I had one thing very near what Alexa’s crew wanted.

All that remained was to search out an inner location to host it, which satirically took longer than the app construct as a result of this was so new.

By Wednesday, I shared the hyperlink with Alexa and my crew in an inner submit.

Everybody was actually pleased with the end result. Alexa and some of her teammates examined it out and picked up one or two small points.

A kind of bugs was fascinating; evidently Alexa noticed all of the objects within the calendar sooner or later earlier than they have been as a consequence of be printed. I fed this data again to the Cursor agent, and it confirmed this was as a consequence of some timezone-related bug, which it promptly fastened.

One week later, we had a working GitHub Initiatives Content material Calendar.

Last Ideas

With all the AI instruments out there at the moment, software program improvement is at an inflection level. 

I felt the identical method when Google launched its search engine and Gmail. That is most likely how folks felt in 1886 when the first practical modern automobile was invented. 

LLMs and AI brokers will certainly change how we develop software program, from dashing up how we study new issues to aiding us in our precise improvement. 

I don’t imagine they’ll substitute the necessity for human builders as a result of if we don’t use them responsibly, we’ll find yourself with mountains of inefficient code. However it’s definitely doable at the moment to construct issues with the next success price than it was once. Based mostly on my expertise creating the content material calendar app, I made one other GitHub-related internet app that allows you to view any GitHub issues assigned to you across all your GitHub repositories.

As somebody who works throughout a number of repositories, I’ve needed a dashboard like this for years—and I used to be in a position to construct it myself!

Getting used to how these instruments work additionally has different advantages. For instance, you’ll have seen that this weblog submit consists of hyperlinks to my colleagues’ on-line accounts or merchandise’ web sites. I added all these hyperlinks just by exporting the content material to a markdown file and asking Cursor to “search for all correct nouns within the textual content, discover the web URL for each, and add the hyperlink to the right noun.” 

I wanted to spot-check the hyperlinks, however discovering and linking them myself would have taken me half an hour. I did it in minutes with Cursor.

In case you’re a developer, I encourage you to experiment with these instruments. Your subsequent nice product thought could also be simpler to construct than you assume!