ShapedQL recently launched!

^‍

^{"Connect your data. Train your models. Query text, user or session context and retrieve relevant results in milliseconds."}

^‍

^{TL;DR ShapedQL is a new language purpose built for agents, feeds and search. ShapedQL was built because they realized that while retrieval has become easier (thanks to Vector DBs), ranking and relevance are still incredibly hard.}

‍

Launch video: https://www.youtube.com/watch?v=Owj_uSUPNaU

‍

Founded by Tullie Murrell

Hi everyone 👋 Meet Tullie, the founder of Shaped.

‍

Problem ❌

Most engineering teams Tullie talks to are stuck maintaining a "Frankenstein" stack. To build a "For You" feed or give an AI Agent personalized memory, they have to glue together a vector database, a feature store (like Redis), a reranking service, and thousands of lines of Python spaghetti code.

‍

Solution ✅

ShapedQL was built to turn that "house of cards" into a single interface.

‍

ShapedQL is a domain-specific SQL dialect that compiles down to a high-performance, multi-stage ranking pipeline. With a single query, you can define the four stages of modern relevance:

1. Retrieve: Fetch candidates from multiple sources (Hybrid Search, Collaborative Filtering, Trending).
2. Filter: Apply hard constraints (e.g., "in stock" or "within 50 miles").
3. Score: Rank results using real-time ML models (optimizing for clicks, purchases, or watch time).
4. Reorder: Enforce diversity so your users (or Agents) don't see the same 5 items repeatedly.

At Shaped, they're seeing teams reduce 2,000+ lines of maintenance code down to ~30 lines of ShapedQL, while shipping features like "Cart Upsell" or "Conversational Recommendations" in days instead of months.

If you're not a fan of SQL they also have Python or Typescript SDKs, perfect for a real-time production integration.

‍

Ask 💬

1. ShapedQL has a Product Hunt launch at this link: www.producthunt.com/products/shaped. Any support or and upvote would be greatly appreciated!
2. Please try out their interactive demo at playground.shaped.ai, the team would love to hear any feedback on the new language. Were you able to easily make a query? Do the docs make sense? What is it missing?
3. If the problems above resonate and you’re struggling to get true relevance from your vector store or current retrieval system, please get in touch! Book on this calendar here: www.shaped.ai/contact and mention you’re from YC. Tullie will make sure to jump on the call personally to help you out.

‍

Learn More

^‍

^{🌐 Visit  shaped.ai to learn more.}

^‍

^{👣 Follow  Shaped on LinkedIn & X.}

‍