Shaped @shapedai

Connect your data. Train your models. Query text, user or session context and retrieve relevant results in milliseconds. shaped.ai New York City Joined August 2021

Tweets

476
Followers

2K
Following

80
Likes

768

Shaped @shapedai

2 months ago

HNSW: the algorithm powering fast vector search hierarchy = speed • sparse layers (express lanes) • dense bottom (local streets) 96% recall, 44x faster than brute force shaped.ai/blog/hnsw-expl…

0 0 1 78 0

View Details

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: docs.shaped.ai/docs/v2/engine…

0 0 1 46 0

View Details

Shaped @shapedai

3 months ago

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

1 0 1 58 0

View Details

Shaped @shapedai

3 months ago

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: shaped.ai/blog/introduci…

2 0 1 133 0

View Details

Shaped @shapedai

3 months ago

$100 free credits. No credit card. → shaped.ai/agent-context If you're building agents and retrieval quality is killing you, try it. We'd love your feedback.

0 0 0 24 0

View Details

Shaped @shapedai

3 months ago

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.

1 0 0 93 0

View Details

Shaped @shapedai

3 months ago

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. 🧵

1 1 1 86 0

View Details

Shaped @shapedai

3 months ago

Netflix doesn't just personalize which movies you see. It personalizes which ROWS you see. We wrote the playbook on how to build it. shaped.ai/blog/how-to-bu…

1 0 2 55 0

View Details

Shaped @shapedai

4 months ago

discover weekly = hybrid filtering collaborative: fails for new releases content-based: too obvious hybrid: ELSA + AI enrichment + adaptive scoring shaped.ai/blog/how-to-bu…

0 0 1 88 0

View Details

Shaped @shapedai

4 months ago

"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 shaped.ai/blog/ab-testin…

0 0 2 65 0

View Details

Shaped @shapedai

4 months ago

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 shaped.ai/blog/gitops-fo…

0 0 2 82 0

View Details

Shaped @shapedai

4 months ago

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 shaped.ai/blog/sub-100ms…

0 0 2 89 1

View Details

Shaped @shapedai

4 months ago

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: shaped.ai/blog/context-w…

0 0 2 60 0

View Details

Shaped @shapedai

4 months ago

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 shaped.ai/blog/the-statu…

0 0 3 60 0

View Details

Shaped @shapedai

4 months ago

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 👇 shaped.ai/blog/why-your-…

0 0 0 81 0

View Details

Shaped @shapedai

5 months ago

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: shaped.ai/blog/building-…

0 0 0 24 0

View Details

Shaped @shapedai

5 months ago

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.

1 0 0 24 0

View Details

Shaped @shapedai

5 months ago

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 🧵