We love building in public. Initially, we got our start by posting reels on Instagram and TikTok, but recently, we made the switch to X due to one very simple reason: community engagement. It's not just us; thousands of other developers, from indie hackers to co-founders of major AI labs, rely on X as a means of garnering user feedback, gauging interest in products/features, and hashing out bugs.
Though X's core mission is to raise the voice of the people above all else, no solution exists that makes end users feel as though they're able to make meaningful contributions to the apps and websites they love. To restore ownership of our products to the millions of valued consumers on X, we created Vector.
Vector is an integrated feedback collector, bug fixer, and code developer that saves developers hours of grunt work and simultaneously makes users feel like they have a voice.
First, a developer posts on X to spread the word about a new product or version update. This could be something like "Grok video gen models now available to try, let us know what you think or if you run into any problems in the comments below!"
Then, Vector deploys a Grok agent to monitor the replies. For a feature request that gains enough traction (by getting a ton of likes, for instance), our Grok agent enters that user's DMs as if it were the original developer who posted the tweet, asking for any deeper thoughts the consumer might have had regarding their request. Here, the Grok agent is also able to process multimodal inputs such as pictures the user might send of their screen.
Vector follows up by raising a Git issue for the feature request and by generating a plan of attack in a markdown file. It feeds this file into our Grok Coding agent, which makes all necessary changes in the codebase, opens a PR, and automatically merges the branch into production after a developer ensures everything looks good.
The final step in the process is to DM the user about their implemented request!
The initial part of the workflow is entirely powered by the X API. We monitor replies to the original post using two webhooks configured with the Account Activity API and interact in DMs using the Python XDK. We use Grok 4 to generate DM replies and to summarize all multimodal inputs of feedback given by the user.
Vector's code generation uses Grok Fast Code to meaningfully contribute to while still maintaining original style, design, and functionality.
The frontend was built with NextJS and TailwindCSS; the backend was built with Flask. For our database, we used Supabase.
At first, the OAuth of the X API was giving us trouble, but thanks to some office hours trips, we eventually learned about the XDK, which was much easier to work with. The added code examples in the github were also helpful.
We're proud of the immense value we're able to create by making users feel like they actually own the product. Their changes, if validated by the support of the community, are integrated into the products they use on a day-to-day basis. It's a major win-win since the developers also don't have to spend nearly as much time coding or scouring the web for scattered feedback.
This was our first time using the X and xAI API/SDK, so it was cool to see how powerful they are when they work in tandem.
We intend to continue developing Vector to support more complex workflows and integrate with additional platforms beyond X.