Raindrop Launches: Deep Search

Raindrop recently launched!

‍

^{"Deep Research for your Production AI Data."}

‍

https://www.youtube.com/watch?v=pN82WxN-_G0

‍

Founded by Zubin Koticha, Alexis Gauba & Ben Hylak‍

Today, the founders are excited to launch Raindrop Deep Search.

It’s like Deep Research for your Production AI Data.

Search for anything, and Raindrop automatically trains little models to accurately classify any topic or issue, across millions of events.

‍

𝗧𝗵𝗲 𝗣𝗿𝗼𝗯𝗹𝗲𝗺

The Raindrop founders have heard from thousands of AI engineers and they’re struggling to track issues with their agents.

Imagine a user reports a problem: your agent is saying it can’t search the web for documentation. You need to know if this is a one-off problem or a much bigger issue… but how? Keyword search, or even semantic search, doesn’t tell the full story.

‍

𝗖𝗮𝗻’𝘁 𝘄𝗲 𝗷𝘂𝘀𝘁 𝘂𝘀𝗲 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗘𝘃𝗮𝗹𝘀?

Offline evals work well as unit tests. But since they’re running on preset data, you have no visibility into what’s actually happening in production.

Online evals just run these unit tests on a tiny sample of production data, leaving you blind to how widespread problems are.

‍

𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗥𝗮𝗶𝗻𝗱𝗿𝗼𝗽 𝗗𝗲𝗲𝗽 𝗦𝗲𝗮𝗿𝗰𝗵

That’s why Deep Search was built. It’s like Deep Research for your production data.

How Deep Search works:

1. Describe the issue (ex. agent failing to search the web).
2. Deep Search finds examples out of millions of events.
3. Refine search with feedback.
4. Start tracking the issue.

Deep Search runs across all of your production data to give you an accurate metric of issue frequency.

Traditional classification systems require humans to manually label thousands of data points. So to achieve this, Raindrop Deep Search introduces a new research breakthrough, bespoke few-shot classifiers, which only need a few examples.

It’s essentially bootstrapping weaker systems from stronger systems, ultimately training custom small models that analyze millions of events a day. You can think of it like creating materialized views for natural language.

Once you start tracking the issue you can use Raindrop to dive into traces and tool calls to find the root cause. And you can quickly confirm whether your fixes are effective by monitoring issue frequency and receiving real-time Slack alerts.

‍

Learn More

^‍

^{🌐 Visit www.raindrop.ai to learn more.}

^‍

^{💧 You can try out Deep Search at raindrop.ai.}

^‍

^{🎉 The founders are excited to hear what you think!
‍}

^{👣 Follow Raindrop on LinkedIn & X.}

‍