
Velvet
Warehouse AI requests with 2 lines of code







About | Details |
---|---|
Name: | Velvet |
Submited By: | Roberto Smith |
Release Date | 10 months ago |
Website | Visit Website |
Category | Software Engineering Data & Analytics Developer Tools |
Warehouse every AI request to your database. Query logs to analyze usage and costs, evaluate models, and generate datasets. Install the proxy with 2 lines of code. Itโs free to get started, and you own your data.
Concept is so intersting like logging and analyzing AI requests directly from my app sounds practical
10 months ago
๐ Congrats on the launch! This product is a game-changer, and I can't wait to start using it. You're amazing! ๐ช @emmalawler24
11 months ago
I noticed the demo video link seems to be broken . It would be great to see it working to get a full picture of Velvetโs capabilities.
11 months ago
Congrats on the launch @emmalawler24 !! As a user of Velvet, I can't think of a better tool for us to monitor LLM usage.
11 months ago
Big congrats on the launch Emma and Chris. Velvet looks great. Good luck to you today โค๏ธ๐ฆ
1 year ago
Congratulations on launch @emmalawler24 and @chris_hendel! I've been beta testing Velvet for a couple of months, and I'm excited to see it go live. Every startup reaches a point where they outgrow Amplitude or Mixpanel. These tools enforce specific data structures, and their SDKs get blocked by many browsers. They completely break with multi-tenancy and barely support organizations. The best-in-class in-house analytics stack is Snowflake, Fivetran, and PowerBI. However, this costs about a quarter million dollars, and requires hiring a data team to maintain and analyze it. This stack can answer any question you want, but PMs lose the ability to easily ask questions directly. Velvet bundles this warehouse/import/analysis stack, and sprinkles in amazing UX and AI to make it modern. Now, any startup can build an advanced data analytics stack that answers any question in their data, and its AI editor makes the product easy enough that PMs can self-serve questions - no data analysts required. In the age of AI, controlling your data is key. Velvet centralizes your databases, third-party events (like Stripe), and even first-party events from your app - storing them in one place and letting you write queries that join across sources.
1 year ago
Congrats on the launch! Making our LLM requests actually queryable has been on our wishlist and isn't quite satisfied by logging/observability providers we know about. Excited to test it out ๐ฅ
1 year ago
Congrats Velvet team! Such an easy product to use and adds to much value to product & eng teams
1 year ago
Everything Chris builds is great! And this makes me feel so much better for never getting good at SQL.
1 year ago
Go Emma go! ๐ I wish I had this years ago, as a new PM struggling with SQL. ๐
1 year ago
I can vouch for Emma and Velvet. I was one of the early users and have enjoyed the product mindset the team has, I am excited about this pivot. Good Luck.
1 year ago
I haven't yet tried the new version but I've been impressed with how consistently the Velvet team has learned, iterated, and shipped since we first chatted a year ago. I can see this approach replacing the request-export-spreadsheet workflow that hampers a ton of data-informed decision making for a lot of people. - It's great for startups that don't have a full data team in place - It's also great for larger cos with dedicated analytics engineering practitioners building data assets to be used downstream The potential for enabling (and upskilling) power users is pretty exciting.
1 year ago
This tool is a must-have for anyone working with AI. Being able to warehouse and query AI requests in a centralized database is incredibly valuable for understanding usage patterns, optimizing costs, and improving model performance. Congratulations on the launch!
1 year ago
The Velvet team is stellar--I've been watching them constantly improve the product for the better part of a year by eliciting and responding (swiftly) to feedback.
1 year ago
Woah, this is so impressive ! Writing SQL queries can be such a hassle. It's a clever application of AI. Would love to try it !
1 year ago