Scaling A/B Testing for YouTube Shorts
Why we built a custom app to test and learn faster
Indeed's YouTube Shorts came primarily from high-production video shoots. But, when we started to create content based on podcast audio clips, we needed a way to test what types of visuals perform best on the platform. Manually creating these visuals at scale wasn't feasible in our current workflow.
I worked with the YouTube team at Indeed to develop a web app that allowed us to generate YouTube Shorts tailored to podcast audio in minutes and with brand consistency.
The Challenge
The YouTube team wanted to test podcast audio clips paired with 'brain rot'-style animations for YouTube Shorts. This style of animation was a first for the channel, so we needed lots of variations to test. Manually creating these assets was not in scope, so we needed to find a way to automate the process while maintaining brand consistency.
The Approach
I used Cursor to develop a simple web app that codified certain aspects of our brand guidelines. From caption style and color palette to background animations and speaker images, the web app handled the details of our brand identity allowing non-technical team members to focus on the visual varations needed to test against YouTube's algorithm.
Features
- Upload audio and auto-transcribe using OpenAI's Whisper API
- Dynamic waveform visualization synced to audio
- Gallery of generative background animations with brand-approved color palettes
- Speaker images with customizable names and job titles
- Individual layer exports (background, captions, speaker info, waveform)
- Real-time preview before export
The tool created an on-brand interpretation of 'brain rot' visuals, bridging the hyperactive tone of the trend with Indeed's polished, professional identity.
The Impact
This simple, internal tool automated the repetitive parts of asset creation, freeing up our team to focus on the creative aspects of the project. By shifting the focus of our team from the tedious to the creative, we were able to quickly iterate without losing momentum, test more content formats faster, and maintain brand consistency at scale.