Shaped

Introducing Shaped for Agents — retrieval that gets it right the first time Try free Book a demo <50ms query latency +20% avg conversions The real-time retrieval engine for agents, feeds, and search. Connect your data. Train your models. Query text, user or session context and retrieve relevant results in milliseconds. Get started free Get a demo $100 free credits. No credit card required. ShapedQL Query relevance like you query SQL Compile SQL queries into optimized, mutli-stage ranking pipelines. Retrieve Hybrid search across multiple indexes Filter Hard constraints & business rules Score ML models & value functions Reorder Diversity & exploration AI assistant context 01 02 03 04 SELECT doc_id, title, content FROM semantic_search("How do I authenticate the API?"), keyword_search("How do I authenticate the API?") 05 WHERE verified = true 06 07 08 ORDER BY colbert_v2(item, "How do I authenticate the API?") + recency_score(item) 09 10 REORDER BY diversity(strength=0.3) Retrieve the most relevant, non-redundant context chunks for any user question — ready to drop into your LLM prompt. Try this query Personalized hybrid search 01 02 03 04 SELECT title, description FROM semantic_search("wireless headphones"), keyword_search("wireless headphones") 05 06 07 ORDER BY colbert_v2(item, "wireless headphones") + click_through_rate_model(user, item) Blend semantic and keyword search, reranked by what this user actually clicks. Try this query More than just document retrieval Replace flat documents with an engine that treats user context as a first-class input. Elastic Document Retrieval Finds candidates only Retrieval + Ranking Finds candidates and predicts user intent Manual Scripts Hand-tuned boost factors Native AI Models Learns from behavior automatically Flattened Documents Denormalized for search User-Item Graph Rich relational context Boolean Query Complexity Complex nested queries Declarative Config Logic defined in SQL Query Injection Manual query decoration First-Class Input Native user understanding High Friction Weeks to deploy changes Instant Updates Deploy changes in minutes Migrate from Elastic Three-layer architecture A unified, queryable relevance engine Shaped is an end-to-end relevance engine designed for real-time personalization and agent memory. Query layer Real-time retrieval & ranking ShapedQLSQL interface RankingMulti-stage pipeline Results<50ms latency Learn more Intelligence layer ML models & embeddings EmbeddingsDynamicvectors TrainingContinuous learning ModelsUser + itemcontext Learn more Data layer 30+ connectors ConnectorsBatch + streaming TablesUnified schemas ViewsSQL transforms Learn more Proven results Trusted by leading teams Product and engineering teams use Shaped to drive engagement and revenue Read case studies 2.2X Conversion Read case study +131% Watch Time Read case study +79% D6 Retention Read case study +4.9% Bookings Read case study +9% Purchases Read case study +10% Watch Time Read case study +8% CTR Read case study +13% Engagement Read case study +10% Email CTR Read case study +382% Diversity Read case study +16% AOV Read case study 10x Increase in experimentation velocity Ship and test new ranking models in days, not months ~7 days Time to first experiment From data connection to production in under a week Connect your stack. Unify your data. Combine batch and real-time data in a single schema View all connectors Data warehouses SnowflakeBigQueryRedshiftDatabricks Analytics Applications AmplitudeSegmentRudderstackPosthog Streaming KinesisKafkaPub/Sub Catalog Storage PostgresMongoDBShopify Built for every use case One engine to power recommendations, search, and agent retrieval across your entire application 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. View all connectors Enterprise-grade security SOC 2 Type II certified, GDPR/HIPAA compliant, and backed by a 99.95% uptime SLA. Secure + Compliant SOC 2 Type 2, GDPR,  CCPA,  HIPAA Enterprise scale 5B+ documents Reliable 99.95% Uptime View security Enterprise ready Secure SOC 2 Type 2 Compliant GDPR,  CCPA, HIPAA Fast <50ms Latency Reliable 99.95% Uptime Scalable 1,000+ QPS Get started this week Connect your data, build your first model, and deploy to production in 7 days. No infrastructure required. Start building free Book a demo Day 1Connect data Day 2-5Build & iterate Day 7Push live --- Introducing Shaped for Agents — retrieval that gets it right the first time Try free Book a demo Three-layer architecture Plans for every stage of growth Clear, transparent pricing with usage-based billing Starter Our starter plan includes $100/month of free use. Start for free Shaped Data Layer (upload, cache and query your data) Shaped Intelligence Layer (train models and encode embeddings) Shaped Query Layer (serve results for a target use-case) Console access Community support Most popular Standard $500/monthminimum use. Get started Everything in Starter Pay-as-you-go for Data, Intelligence and Query Layer usage Real-time and application connectors Pro support Business hour response SLAs (Sev 1: 8 hours) Private Slack channel Enterprise Custom pricing for mission-critical applications. Contact sales Everything in Standard plan 99.95% Uptime SLA Private networking SOC 2, GDPR, HIPAA 24/7 on-call support 30 min Sev 1 response Dedicated solution engineering Transparent, usage-based pricing Data layer $0.75- $2.25/GB Volume of data stored Intelligence layer $5/hour GPU hours for 
training & encoding Query layer $42/M calls Number of query requests Support tiers Basic Free Support tickets Community slack Pro $500/month Support tickets Private slack channel Architecture and experiment guidance Enterprise Custom pricing Support tickets Private slack Dedicated engineering and data science Onboarding support Get started this week Connect your data, build your first model, and deploy to production in 7 days. No infrastructure required. Start building free Book a demo Day 1Connect data Day 2-5Build & iterate Day 7Push live --- Try free Book a demo Your agent is only as good as the context it retrieves. Shaped is a retrieval API that gives your agent the right 10 results instead of 200 noisy ones. Less hallucination, lower cost, better answers. Try Shaped free Talk to us about migration Works with and any MCP-compatible agent. Powering retrieval for 1B+ queries What Shaped looks like in production. Your agent asks Shaped for context. Here's what comes back. RAG Code Search Agentic Commerce WITH SHAPED "How do I configure SSO for enterprise accounts?" "How do I add middleware to the Express app?" "Find me running shoes for trail running under $150" ShapedQL SELECT content, title FROM text_search('SSO enterprise configuration', mode=vector), text_search('SSO enterprise', mode=lexical), similarity(user_id=$user_id) WHERE doc_type = 'guide' ORDER BY relevance(user, item) LIMIT 10 ShapedQL SELECT file_path, content FROM text_search('middleware express', mode=vector), text_search('middleware express', mode=lexical), file_recency(repo_id='acme-api') WHERE language = 'typescript' ORDER BY relevance(user, item) LIMIT 10 ShapedQL SELECT product_id, name, price, description FROM text_search('trail running shoes', mode=vector), similarity(user_id=$user_id) WHERE category = 'running-shoes' AND price <= 150 ORDER BY relevance(user, item) LIMIT 10 1.docs/enterprise/sso-setup.md0.97 2.docs/enterprise/saml-configuration.md0.94 3.docs/auth/identity-providers.md0.91 4.docs/admin/org-settings.md0.87 5.changelog/v2.4-sso-updates.md0.83 1.src/middleware/auth.ts0.96 2.src/middleware/logging.ts0.93 3.src/app.ts (lines 24-41)0.89 4.docs/middleware-guide.md0.85 5.src/routes/api.ts (lines 8-15)0.82 1.Nike Pegasus Trail 5 - $1290.95 2.Hoka Speedgoat 6 - $1450.93 3.Salomon Sense Ride 5 - $1390.90 4.Brooks Catamount 3 - $1490.87 5.New Balance Fresh Foam Hierro - $1340.84 Also available via Python SDK, TypeScript SDK, or MCP. See docs → WHAT THE AGENT RETURNS: Based on the SSO setup guide and SAML config docs: 1. Navigate to Admin → Org Settings → Authentication 2. Select your identity provider (Okta, Azure AD, Google) 3. Upload your SAML metadata XML See docs/enterprise/sso-setup.md for full walkthrough. WHAT THE AGENT RETURNS: // Following patterns from auth.ts and logging.ts import { authMiddleware } from './middleware/auth'; import { requestLogger } from './middleware/logging'; app.use('/api', authMiddleware); app.use('/api', requestLogger); app.use('/api', yourNewMiddleware); WHAT THE AGENT RETURNS: Based on your running history and past purchases: 1. Hoka Speedgoat 6 ($145) — You loved the Speedgoat 5. Improved grip, same cushion. 2. Salomon Sense Ride 5 ($139) — Great for mixed terrain. 3. Nike Pegasus Trail 5 ($129) — Best value for road-to-trail. WITHOUT SHAPED "How do I configure SSO for enterprise accounts?" "How do I add middleware to the Express app?" "Find me running shoes for trail running under $150" Python import pinecone import cohere from openai import OpenAI # 1. Embed user query res = client.embeddings.create( input=query, model="text-embedding-3-small") query_vec = res.data[0].embedding # 2. Vector search (200 noisy docs) idx = pinecone.Index("my-index") raw_docs = idx.query( vector=query_vec, top_k=200, include_metadata=True) # 3. Rerank with static model co = cohere.Client('API_KEY') reranked = co.rerank( query=query, documents=[d.metadata['text'] for d in raw_docs['matches']], top_n=10) # 4. Stuff massive context and hope context = "\n".join( [doc.document['text'] for doc in reranked.results]) prompt = f"Context: {context}\n\nAnswer: {query}" Python import pinecone from openai import OpenAI # 1. Embed query res = client.embeddings.create(input=query, model="text-embedding-3-small") query_vec = res.data[0].embedding # 2. Pure Vector Search # (Embeddings are notoriously bad at exact code syntax) idx = pinecone.Index("codebase-index") raw_chunks = idx.query(vector=query_vec, top_k=200, include_metadata=True) # 3. No BM25 / Lexical fallback # Misses exact file paths like 'src/middleware/auth.ts' # because semantic meaning != exact code syntax. # 4. Blind chunking destroys context # Stuff 200 random 512-token chunks of code into the prompt # and hope the LLM can piece the file back together. context = "\n---\n".join([c.metadata['code_snippet'] for c in raw_chunks['matches']]) prompt = f"Codebase:\n{context}\n\nAnswer: {query}" Python import pinecone from openai import OpenAI # 1. Embed query # (Embeddings often lose strict intent like "under $150") res = client.embeddings.create(input=query, model="text-embedding-3-small") query_vec = res.data[0].embedding # 2. Vector search with clumsy metadata filters idx = pinecone.Index("product-catalog") raw_docs = idx.query( vector=query_vec, top_k=200, filter={"price": {"$lte": 150}}, include_metadata=True) # 3. Personalization? # Fetching past purchases from Redis to manually rerank # 200 items in Python takes too long. # user_history = redis.get(user_id) # Skipping due to latency... # 4. Stuff generic, unpersonalized products into prompt context = "\n".join([doc.metadata['desc'] for doc in raw_docs['matches']]) prompt = f"Context: {context}\n\nRecommend shoes: {query}" 50,000 TOKENS OF CONTEXT 90% irrelevant. $0.50/query. Static forever. WHAT THE LLM RETURNS: SSO (Single Sign-On) allows users to authenticate using a single set of credentials. Enterprise accounts can configure SSO through the admin panel... // Generic overview with no specific steps WHAT THE LLM RETURNS: // Generic Express.js middleware example app.use((req, res, next) => { console.log('Request received'); next(); }); // No reference to your actual codebase patterns... WHAT THE LLM RETURNS: Here are some popular running shoes: - Nike Air Zoom Pegasus 41 ($130) - Adidas Ultraboost Light ($190) - Asics Gel-Kayano 31 ($160) // Generic bestsellers, not trail-specific, not personalized, wrong prices... 10 results · 2,100 tokens · 38ms · Your agent gets exactly what it needs — nothing more. This is how most agents retrieve context today. Query Embed Vector DB Reranker Stuff into prompt LLM 200 results by cosine similarity Static model doesn't learn 50,000 tokens $0.50/query · 90% noise Too much irrelevant context 200 results. 190 are noise. Your agent re-retrieves, burning tokens and time. No personalization Senior engineers and new hires get the same 200 chunks. Never improves Day 100 is no smarter than day 1. This is how agents retrieve context with Shaped. Query + User Shaped 10 ranked results LLM Learns from every interaction Stop manually tuning. Shaped ingests clicks and other signals to tune your models in realtime. Ranked, minimal context Shaped returns only relevant results. 100% of the context matters. No retry loops Shaped gets it right the first time. Your agent doesn't re-retrieve. Learns from every interaction User rephrases or thumbs-down? Day 100 is dramatically better than day 1. 0x fewer tokens 0ms latency No retry loops Learns from feedback One API. Not five services. Vector DB (e.g. Pinecone) Search engine (e.g. Elasticsearch) Reranker (e.g. Cohere) Feature store (e.g. Redis) Glue code (~2,000 LOC) 5 services5 bills5 points of failure Shaped 1 API · ~40 LOC 1 service1 bill1 endpoint Capability DIY Retrieval Stack Shaped Retrieval Single embedding space Multi-retriever (vector + lexical + behavioral) Ranking Static reranker model ML models that learn from outcomes Personalization None User-aware ranking via user_id Context size 50K+ tokens (top-k dump) 2,500 tokens (ranked LIMIT 10) Infrastructure Vector DB + Search engine + Reranker + Feature store + glue 1 API call Improves over time No - static from day 1 Yes - retrains on agent feedback Query language Multiple SDKs + custom code ShapedQL (SQL-like, declarative) No rip and replace required. Run side by side Keep your existing stack running. Zero risk. Compare results A/B test on real queries. Measure everything head to head. Migrate when ready Swap one API call. Roll back anytime. "After assessing the landscape Shaped became the obvious choice" Han Yuan CTO @ Outdoorsy When agents get the right context, business metrics soar. +79% D6 Retention Read case study +4.9% Bookings Read case study +9% Purchases Read case study +10% Watch Time Read case study +8% CTR Read case study +13% Engagement Read case study +79% D6 Retention Read case study +4.9% Bookings Read case study +9% Purchases Read case study +10% Watch Time Read case study +8% CTR Read case study +13% Engagement Read case study +79% D6 Retention Read case study +4.9% Bookings Read case study +9% Purchases Read case study +10% Watch Time Read case study +8% CTR Read case study +13% Engagement Read case study +79% D6 Retention Read case study +4.9% Bookings Read case study +9% Purchases Read case study +10% Watch Time Read case study +8% CTR Read case study +13% Engagement Read case study Deploy before lunch. Improve forever. 9 AM Connect your data Connect a data source in the Shaped console. Postgres, S3, BigQuery, or any of 20+ connectors. 10 AM Write your first query Configure an engine. Write a ShapedQL query. Test it in the playground. Lunch Deploy to production Your agent connects via MCP or API. <50ms. Retrains on outcomes automatically. Better results. Fewer tokens. Zero hallucinations. Deploy in a morning. Run alongside your existing stack. See the difference immediately. Try Shaped free Talk to us about migration $100 free credits. No credit card required. Sign up, connect a data source, and query in under 10 minutes. See pricing → --- Introducing Shaped for Agents — retrieval that gets it right the first time Try free Book a demo Fully managed platform Shaped Cloud The fully-managed AI ranking platform. No infrastructure, auto-scaling, real-time ML. Get started free Read the docs 99.95% Uptime SLA <10min Setup time 100M+ Queries per day Three-layer architecture Shaped Cloud provides a complete platform with integrated layers for queries, intelligence, and data. Query layer Real-time retrieval & ranking ShapedQLSQL interface RankingMulti-stage pipeline Results<50ms Learn more Intelligence layer ML models & embeddings EmbeddingsDynamicvectors TrainingContinuous learning ModelsUser + itemcontext Learn more Data layer Unified data foundation ConnectorsBatch + streaming TablesUnified schemas ViewsSQL transforms Learn more Built for production Everything you need to run AI ranking at scale Fully managed infrastructure Zero DevOps overhead. We handle provisioning, scaling, monitoring, and maintenance. Auto-scaling Automatically scales to handle traffic spikes and growing data volumes without manual intervention. Continuous ML pipelines Deploy and execute ML models in production with sub-100ms latency at any scale. Enterprise security SOC 2 Type 2 certified with encryption at rest and in transit, plus AWS PrivateLink support. Real-time ingestion & transforms Shaped has a real-time, durable feature store that ingests and transforms your data for training and serving. Full-stack observability From high-level KPIs to deep query-level debugging, understand everything your system is doing. Focus on your product, not infrastructure Shaped Cloud eliminates the complexity of managing AI infrastructure. We handle the entire stack—from provisioning and scaling to monitoring and security—so your team can focus on building great products.Deploy in minutes, scale to millions of users, and sleep soundly knowing your infrastructure is managed by experts. Setup time <5 minutes Manual scaling Zero Infrastructure team Not needed Maintenance windows None Get started with Shaped Cloud Deploy your first AI ranking pipeline in minutes Get started