SSW General Manager Talks AI and YakShaver at CompTIA
Last month, our General Manager, Ulysses, had the opportunity to speak at the CompTIA conference about how SSW is creating AI agents like YakShaver. The talk focused on how we’ve used AI to simplify task delegation and issue reporting, making it more accessible and efficient for everyone on the team, from designers to developers. One of SSW's lead designers, who wasn’t initially familiar with AI or its capabilities, was especially impressed by the "one and done" nature of AI tools like YakShaver.At SSW, YakShaver has become an essential tool...
Figure: Ulysses on the panel at CompTIA
We often have several Sprints running simultaneously across different projects and teams, with only a few senior managers overseeing them. YakShaver automatically routes tasks to the right people, cutting down on the back-and-forth during Sprints, which everyone appreciates. What made Uly’s talk stand out was showing that AI doesn’t have to be complicated—it can work quietly in the background, improving workflows without requiring technical expertise from users.Uly shared real examples from our team, highlighting how AI has streamlined our processes without adding complexity. The response at CompTIA was positive, with many attendees eager to learn how they could adopt similar approaches in their own projects.
For us, it was a great opportunity to show how AI can be practical and useful, making every day work easier without being overwhelming. YakShaver is just one way we’re achieving that, and it was exciting to share our experience with a wider audience.
Recent Articles
Support for MacOS!
With the addition of .mov file extension support, YakShaver now supports the default MacOS recording tool, Screenshot App!
Known tools that are currently supported:
- Other recording software that creates .mov or other video extension files (see the FAQ)
Optimising File Sizes for YakShaver
YakShaver now can process videos greater than 25MB! This means longer and higher quality videos will now be able to be processed through YakShaver, resulting in better quality work items or emails!
Why 25MB limit in the first place?
We are using Azure OpenAI's Whisper AI model, which currently has a 25MB file size limit
Azure OpenAI's Whisper AI model allows you to batch transcribe, why not do that?
Giving no hard limits on the size and truncating the video into 25MB chunks to be batched process is not a great idea in the long run. It can be used to waste a great amount of processing power and can be easily abused to be sent an extremely large file if no checks are in place.
Furthermore, this feature requires your video files to be stored in blob storage, which means greater costs in order to process longer videos.
How did we overcome this 25MB limit?
The short answer is we didn't, we just removed the parts that Whisper doesn't need - the visuals that take up the majority of bytes in a video file.
We use a library that implements FFmpeg in code, called Xabe.FFmpeg, which allows us to manipulate and process media files. By extracting only the audio from the video file, we significantly reduce the size to only have the data that matters for a transcription service, the audio.
Here are some examples of what it has done to the file size before transcription: 1-minute video in 4K - 38.87 MB -> 0.62 MB audio .mp3 (1.5% of the video size) 30-minute video in 2K - 209.89 MB -> 7.95 MB audio .mp3 (3.8% of the video size)