Shaped

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

[Shaped @shapedai]

Why guess with your rankings? 🤔
With ShapedQL, you can explicitly weight Keyword vs. Semantic search using simple SQL.
10% BM25 + 90% Vector? Done in one line. ⚡️
Watch the demo 👇

[Shaped @shapedai]

HNSW: the algorithm powering fast vector search

hierarchy = speed
• sparse layers (express lanes)
• dense bottom (local streets)

96% recall, 44x faster than brute force

https://t.co/9jXyaDSPe4

[Shaped @shapedai]

It's not just for ranking models. Signals power search relevance, agent context enrichment, faceted filtering, and any workload that needs fresh features at query time.
Docs: https://t.co/7QcJYbBvGh

[Shaped @shapedai]

We just shipped the Signal Engine.

Define a feature once. Get training, serving, and streaming for free.

25+ signal primitives
<5ms serving
Point-in-Time correctness by default
Change a feature, see evaluation results in hours

Blog post: https://t.co/aftLcSMY7I

[Shaped @shapedai]

Signal primitives ship today: aggregations, ratios, cross features, vector similarity, geo distance, text similarity, cyclic time encoding, sequences for SASRec/BERT4Rec, and more.

[Shaped @shapedai]

$100 free credits. No credit card.

→ https://t.co/Wjntw33tHf

If you're building agents and retrieval quality is killing you, try it. We'd love your feedback.

[Shaped @shapedai]

Your AI agent spends 50,000 tokens per query.

90% of that is noise.

When the answer is wrong, it re-retrieves — another 50K tokens, another ~$0.50 in LLM token costs, another few seconds of latency.

The problem isn't the LLM. It's the retrieval.

We built Shaped to fix it. 🧵

[Shaped @shapedai]

We just shipped an MCP server.

pip install shaped-mcp

Works natively with Cursor, Claude Code, Windsurf, VS Code Copilot, Gemini, OpenAI — any MCP-compatible agent.

Add it to your config. Your agent has better retrieval instantly. No custom integration code.

[Shaped @shapedai]

Netflix doesn't just personalize which movies you see. It personalizes which ROWS you see.

We wrote the playbook on how to build it.

https://t.co/Imtw5MqL10

[Shaped @shapedai]

discover weekly = hybrid filtering

collaborative: fails for new releases
content-based: too obvious

hybrid: ELSA + AI enrichment + adaptive scoring

https://t.co/u4ukySd6qT

[Shaped @shapedai]

"the new model feels better"

that's not a metric

offline eval:
Recall@10: 0.45 → 0.50 (+11%)
NDCG@10: 0.54 → 0.61 (+13%)

online A/B test:
CTR: +15%
Conversion: +19%

now you have proof

https://t.co/9XhRnTYEtl

[Shaped @shapedai]

your agent's config:
• ranking formula in .env
• filters hardcoded
• vector DB settings in UI
• features scattered

when it breaks: 🤷

with GitOps:
• everything in Git
• PR review before deploy
• one command to rollback
• clear audit trail

https://t.co/PC9qKw3pVz

[Shaped @shapedai]

your agent: 5 seconds to respond
your LLM: 3 seconds

where are the other 2 seconds?

retrieval.

vector DB: 220ms
filtering: 50ms
scoring: 120ms
reordering: 60ms
network hops: 4x

= 450ms+ per query

Shaped's fast_tier: 30-100ms for all 4 stages unified

https://t.co/euREfIEbFz

[Shaped @shapedai]

The scaling law for agents isn't model size. It's what goes into the context window.

Attention is quadratic. 2x tokens = 4x cost.

10 ranked results > 200 stuffed chunks. Every time. At 10x lower cost.

We wrote the math:
https://t.co/LH8X7AzRRm

[Shaped @shapedai]

your agent: "order has shipping tier 4 and status 7"

what the customer needed: "ships in 2 days via FedEx, in transit"

AI Views fix this—enrich at write time, not read time

https://t.co/CtALPq0pJF

[Shaped @shapedai]

most "AI hallucinations" are just stale retrieval

user: "is this in stock?"
agent's index: last updated 2am
product: sold out at 9am
agent: "yes"

the model is fine. your data pipeline is broken.

how to fix it 👇
https://t.co/bLN2NDjyGi

[Shaped @shapedai]

We built a complete technical guide:

✓ Working code
✓ Architecture diagrams
✓ Dynamic weight tuning patterns
✓ Real-world use cases (e-commerce, travel, content) ✓ When NOT to use this approach

Read it here: https://t.co/f6lFHCDHpc

[Shaped @shapedai]

Your agent just cost you $40,000.

It recommended wireless headphones to a customer who bought the exact same pair yesterday.

The problem? It optimized for semantic similarity. It ignored business logic.

Here's how to fix it 🧵

[Shaped @shapedai]

Real production benchmarks:

Traditional stack:
→ 250-500ms (3-4 network hops)
→ Hours to update weights
→ 42% precision@5

Value models:
→ 50-100ms (single query)
→ Seconds to update weights
→ 68% precision@5

Same data. Better architecture.