[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![tbpn Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1838288550569349120.png) TBPN [@tbpn](/creator/twitter/tbpn) on x 94K followers
Created: 2025-07-17 22:26:15 UTC

We asked @douwekiela (Co-Founder & CEO @ContextualAI) about the challenges of scaling RAG to enterprise-level data.

"AI should be able to search your inbox and get the right answer."

"Search is a hard problem. The way you do proper retrieval is multi-stage cascading with smarter models."

"When you talk to enterprise customers, the data is all over the place and search breaks down so you can't give the right answer even if you have a great language model."

![](https://pbs.twimg.com/amplify_video_thumb/1945973289601687552/img/ACswvyItQrZoT0DV.jpg)

XXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1945973349940953370/c:line.svg)

**Related Topics**
[coins ai](/topic/coins-ai)

[Post Link](https://x.com/tbpn/status/1945973349940953370)