LMS are these great reasoning engines. You throw you throw a lot of text at them and tell them what to do with it and they'll do it for you. We collate from multiple different indexes, multiple crawls of the web and pull up the relevant links. And then we ask to LMS to do all the reasoning on top and then we give you the answer. Now the magic is that all this happens so fast. Back then the latency used to be like five to six seconds per query. In fact, one of our investors, Daniel Gross, he used to joke to me saying you should call it a submitted job and not a submitted query. It's that slow.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode