Video intelligence platform for coaching programs and training companies. The problem: these businesses sit on 200-500+ hours of video content that becomes a "content graveyard" - students can't find what they need, coaches burn out answering the same questions, churn stays high.
We do deep transcript + metadata extraction, then layer RAG search and an AI assistant that can answer questions with timestamped citations back to the exact video moment. Think "ChatGPT for your video library" but with accurate sources instead of hallucinations.
Tech: Phoenix/Elixir backend, Next.js portals, two-tier RAG architecture.
Currently serving a few coaching programs in high-touch sales mode. Would love feedback from anyone who's built RAG systems over media content - curious how others handle the signal extraction problem (transcripts are noisy, you need to identify what's actually being taught vs filler).
I love this, looks really well done. I don't have a windows computer or steam deck but just got a copy anyway because I like the whole story and vibe around it. Also great that you offer the source as DLC as well, I will def check it out! I wish you both the best of success with this! :)
I'm a Mac user as well, and I bought the Game and DLC. It's such a great idea. Congrats on the game launch (I'll wait patiently for a Mac version rather than trying to get the DLC working), but it was more about supporting the concept than anything.
Thank you very much! If you have a Mac, you may have trouble downloading the source code DLC so drop us a mail if that is the case: make@something.pink
Looks very cool! Besides the search, which works great and feels like a powerful tool, I like how snappy the word highlighting is in the transcripts. Can you elaborate a bit on how that's done? Thank you, this is really great work!
Yes, exactly. We do forced alignment when you edit your transcript. The new words don't have any timestamps, so we need to align them. For short sections we use interpolation. If we need align whole sections we use Gentle[^1].
fun headline if it's not even clear if the driver was driving or not.
> Whether the vehicle was driven by the 43-year-old driver or not is the subject of the investigation and is currently unknown, a police spokesperson said on Tuesday. The cause of the accident remains unclear.
Same here. 2014 maxed out, doesn't do well in the spanish summer. External screen mostly stays disconnected, otherwise it throttles down after 30 mins..
Are there not some kind of cooling pads to help with this shit?
OK, I guess when doing OP's root trick, the root user gets activated/created, and that's that's when the PW gets set to empty. I guess that's where my passwordLastSetTime comes from.
Video intelligence platform for coaching programs and training companies. The problem: these businesses sit on 200-500+ hours of video content that becomes a "content graveyard" - students can't find what they need, coaches burn out answering the same questions, churn stays high.
We do deep transcript + metadata extraction, then layer RAG search and an AI assistant that can answer questions with timestamped citations back to the exact video moment. Think "ChatGPT for your video library" but with accurate sources instead of hallucinations. Tech: Phoenix/Elixir backend, Next.js portals, two-tier RAG architecture.
Currently serving a few coaching programs in high-touch sales mode. Would love feedback from anyone who's built RAG systems over media content - curious how others handle the signal extraction problem (transcripts are noisy, you need to identify what's actually being taught vs filler).