Julia Fedorin's banner

Julia Fedorin

@juliafedorin • 5,771 subscribers

Storytelling @Composio🎙️🎥 | Podcast Host | Prev Marketing @Shopify | @UWaterloo Class ‘26 | Designing conversations that help ideas travel

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Vector databases are a scam. Not technically, they do exactly what they say. Return the most cosine-similar string to your query. The scam is the entire industry pretending that's the same thing as relevance. It isn't. Search "Apple." You get the fruit, the company, the watch, and a recipe blog. Your agent picks one at random and calls it retrieval. Your customer calls it broken. Most AI agents shipping right now are duct-taped on top of this. They demo well because demos are easy. They die in production because production is real. HydraDB's Founder Nish (Nishkarsh) said the quiet part out loud — "vector databases suck, similarity is not relevance" — and the demo signups haven't stopped since. He raised $6.5M because he was the first to name what everyone in the room already knew. If your retrieval layer is a flat embedding index, you're not building infrastructure. You're building a liability with a prettier name. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) AI Needs Context (01:30) HydraDB Explained (07:41) Vector Search Breaks (09:32) Messaging That Converts (13:41) Writing the Viral Tweet (16:07) Similarity Not Relevance (20:46) POC to Production Gap (35:35) Raising 6.5 Million Fast (39:33) Founder Lesson on Messaging This is a Composio "Agents at Work" podcast, where I chat with founders building the next leap of AI. Follow for more:)

Vector databases are a scam. Not technically, they do exactly what they say. Return the most cosine-similar string to your query. The scam is the entire industry pretending that's the same thing as relevance. It isn't. Search "Apple." You get the fruit, the company, the watch, and a recipe blog. Your agent picks one at random and calls it retrieval. Your customer calls it broken. Most AI agents shipping right now are duct-taped on top of this. They demo well because demos are easy. They die in production because production is real. HydraDB's Founder Nish (Nishkarsh) said the quiet part out loud — "vector databases suck, similarity is not relevance" — and the demo signups haven't stopped since. He raised $6.5M because he was the first to name what everyone in the room already knew. If your retrieval layer is a flat embedding index, you're not building infrastructure. You're building a liability with a prettier name. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) AI Needs Context (01:30) HydraDB Explained (07:41) Vector Search Breaks (09:32) Messaging That Converts (13:41) Writing the Viral Tweet (16:07) Similarity Not Relevance (20:46) POC to Production Gap (35:35) Raising 6.5 Million Fast (39:33) Founder Lesson on Messaging This is a Composio "Agents at Work" podcast, where I chat with founders building the next leap of AI. Follow for more:)

179,451 views • 26 days ago

Hi Shopify, room for one more?

Hi Shopify, room for one more?

1,227,745 views • 1 year ago

How did Dhravya Shah get a Cloudflare internship at 18? "I built something, it got DDoSed, so I reverse-engineered Cloudflare to protect it — wrote a blog about it, it went viral and the CTO just said: do you want to work here?" Dhravya (now founder of supermemory) didn't apply. He just built in the open until the right person noticed. Full interview about his journey below.

How did Dhravya Shah get a Cloudflare internship at 18? "I built something, it got DDoSed, so I reverse-engineered Cloudflare to protect it — wrote a blog about it, it went viral and the CTO just said: do you want to work here?" Dhravya (now founder of supermemory) didn't apply. He just built in the open until the right person noticed. Full interview about his journey below.

168,120 views • 2 months ago

At 16, with zero programming knowledge, Tejas taught himself to build a website for the motel he grew up in. It made $48K/year. Tejas Bhakta grew up literally living in a Budget Inn motel in Anaheim — from birth until he was 18. "My parents only did sixth grade, there was really no means for them to build the website or even set up wifi." "I barely knew how to code, so I was hacking something together with WordPress." That same instinct to just figure it out carried him to Tesla, to YC, to founding Morph. Watch the full Composio interview here:

At 16, with zero programming knowledge, Tejas taught himself to build a website for the motel he grew up in. It made $48K/year. Tejas Bhakta grew up literally living in a Budget Inn motel in Anaheim — from birth until he was 18. "My parents only did sixth grade, there was really no means for them to build the website or even set up wifi." "I barely knew how to code, so I was hacking something together with WordPress." That same instinct to just figure it out carried him to Tesla, to YC, to founding Morph. Watch the full Composio interview here:

11,338 views • 2 months ago

hi female founders, this one’s for u. it’s clear there’s a real gap for initiatives like this. me and the girls are filling this gap. jan 8-11th all expenses paid retreat in a luxury cottage. no boys allowed. apply link in comments ;)

hi female founders, this one’s for u. it’s clear there’s a real gap for initiatives like this. me and the girls are filling this gap. jan 8-11th all expenses paid retreat in a luxury cottage. no boys allowed. apply link in comments ;)

20,709 views • 6 months ago

No more content to load