The only vector database with a feedback loop
Connect your data. Train your models. Query text, user or session context and retrieve relevant results in milliseconds.
Benchmarks
Highest performance across every metric
Best-in-class ranking accuracy and hit rates compared to legacy providers.
Accuracy @ K=10 ?
Shaped consistently outperforms AWS Personalize and Recombee in Hit Rate, Ranking Relevance (MRR), and Precision.
| Metric | Shaped | AWS Personalize | Recombee |
|---|---|---|---|
| Hit Rate | 49.5% | 45.7% | 28.7% |
| Ranking Relevance (MRR) | 29.8% | 22.3% | 12.4% |
| Precision | 10.7% | 4.6% | 11.3% |
ShapedQL
One query. Any use case.
Retrieve by text, user ID, or item ID — whatever context you have.
Agent context
SELECT doc_id, title, content
FROM
semantic_search("How do I authenticate the API?"),
keyword_search("How do I authenticate the API?")
WHERE verified = true
ORDER BY
colbert_v2(item, "How do I authenticate the API?") + recency_score(item)
REORDER BY
diversity(strength=0.3)
Unlike a vector store, Shaped knows who's asking. Results are personalised per user and get better with every interaction.
Personalized hybrid search
Blend semantic and keyword search, reranked by what this user actually clicks.
SELECT title, description
FROM
semantic_search("wireless headphones"),
keyword_search("wireless headphones")
ORDER BY
colbert_v2(item, "wireless headphones") + click_through_rate_model(user, item)
Also available via Python SDK, TypeScript SDK, or MCP.
Built for decisions, not documents
Legacy RAG stacks require endless duct tape. Shaped unifies retrieval, ranking, and learning in one query.
Traditional agent stacks
| Feature | Traditional Agents | Shaped |
|---|---|---|
| Cost per answer | $1.50 | $0.03 |
| Retry loops | Yes | No |
| Sliced data | 5 systems, 5 calls | One call |
| Static embeddings | No improvement | Continuous learning |
| Build everything yourself | Yes | 30+ native connectors |
Three-layer architecture
A unified, queryable relevance engine
Shaped is an end-to-end relevance engine designed for real-time personalization and agent memory.
Proven results
Product and engineering teams use Shaped to drive engagement and revenue.
Built for every use case
For you feeds
Personalized content feeds that adapt in real-time to user behavior.
Search & discovery
Hybrid search combining keyword and semantic relevance.
Agent retrieval
Power AI agents with contextual memory and retrieval.
Similar items
Content-based and behavioral similarity at scale.
Personalized email
Dynamic email content personalized per recipient.
AI assistants
Context-aware recommendations for conversational AI.
30+ Native Connectors
Ingest raw event logs directly from your warehouse or real-time streams. No ETL required.
Enterprise-grade security
SOC 2 Type II certified, GDPR/HIPAA compliant, and backed by a 99.95% uptime SLA.
Get started this week
Connect your data, build your first model, and deploy to production in 7 days. No infrastructure required.