pinecone.io

Visible text is 1.9% of HTML weight (4750/256107 bytes). Low. Markup may be crowding out agent-usable text.

Fix: Heavy ad or navigation markup crowds out agent-usable text. Aim for a text-to-DOM ratio above 15%.

1 recommended-field warning(s). First: WebSite recommends "potentialAction" (improves agent comprehension). 1 block(s) skipped — type outside the set we check.

Fix: Validate your JSON-LD with Google Rich Results test. Fix missing required properties.

No Content-Signal directives. Add e.g. `Content-Signal: ai-train=no, ai-summarize=yes` to declare granular AI usage policy beyond binary allow/disallow.

Fix: Add `Content-Signal:` directives to your robots.txt. This is the emerging standard (Cloudflare-driven) for declaring fine-grained AI usage policy beyond a binary allow/disallow.

No valid MCP Server Card at /.well-known/mcp/server-card.json. Publish one so agents can discover your tools without HTML scraping.

Fix: Publish an MCP Server Card describing the tools your site exposes. Agents discover capabilities via `/.well-known/mcp/server-card.json`. See modelcontextprotocol.io for the schema.

The vector database to build knowledgeable AI | Pinecone Pinecone Nexus is now in Public Preview - Read the announcement Dismiss Products Enterprise Customers Resources Pricing Contact Log in Start for free Build Knowledgeable AI Give agents knowledge Fast retrieval. Accurate results. Lower costs. Start in seconds. Start Building Get a Demo GET STARTED {Claude Code} {Cursor} {Copilot} {Codex} {Gemini} {CLI} {MCP} View Docs $ claude plugin install pinecone Copy Install — run above command in terminal Start Claude Code — run claude (or restart if already running) Run /pinecone:quickstart for next steps Cost-performance at any scale Estimate the cost of your workload. See full pricing I'm building a RAG pipeline for a passion project Get an estimate Your indexes, always visible Monitor performance, explore your data, and manage indexes from a clean, fast console — or stay in the terminal. Your call. app.pinecone.io Get started Database Quickstart Indexes (3) Backups Assistant Inference API keys Manage Indexes + Create index Name Status Records Region Type Dimensions s-cache Ready 55,611 aws us-east-1 Dense 1,536 ··· product-search Ready 2,418,302 aws us-west-2 Dense 3,072 ··· user-profiles Ready 847,211 aws eu-west-1 Dense 1,024 ··· s-cache Record count 55,611 Region aws us-east-1 Type Dense Host s-cache-vjxlb1i.svc.aped-4627-b74a… ··· Connect Browser Metrics Namespaces (4) Imports Configuration Records Upsert record Namespace cache_bench-test ▾ Operation Search by ID ▾ ID entry_01KQJG0RTKR8SF2KHY97XYQAK9 Top K 10 Filter Rerank Search Search: 10 results (top_k=10) 1 RUs ⓘ 1 Score 0.9997 ··· _id: entry_01KQJG0RTKR8SF2KHY97XYQAK9 cached_at: 1777663501 expires_at: 1777749901 hit_count: 0 last_hit_at: 0 query: “. what is a corporation?” s-cache Record count 55,611 Region aws us-east-1 Type Dense Host s-cache-a1b2c3d.svc.pinecone.io ··· Connect Browser Metrics Namespaces (4) Imports Configuration Metrics All metrics are represented in your local timezone. Updated less than a minute ago. Longer time ranges use lower resolution. 15m 4hrs 12hrs 1d 2d 1w Read units Write units Requests per second Query Upsert Update Delete Fetch List Request latency Query Upsert Update Delete Fetch List p50 p95 p99 Storage size Record count Architecture How Pinecone works Read the whitepaper Pinecone is a fully managed vector database built for AI. Writes are instantly searchable, indexing is automatic, and queries stay fast at any scale. 01 · WRITE <100ms acknowledgment Acknowledged in under 100ms, searchable within seconds. vector throughput, streaming in 02 · INDEX Automatic no tuning required Algorithms selected per data size, upgraded in the background automatically. index continuously rebalancing 03 · QUERY Consistent at any scale All data searched in parallel. Speed holds steady regardless of scale. p99 latency, improving with scale Use cases What teams build with Pinecone {agents} Isolated memory for every agent, at any scale. One namespace per agent, no separate indexes required. As your fleet grows, the knowledge each agent needs is already there — compiled, not assembled at query time. One namespace per agent, no separate indexes required. As your fleet grows, the knowledge each agent needs is already there — compiled, not assembled at query time. 400 QPS 1.7M namespaces {search} Semantic search at billion-vector scale. A single index handles billions of vectors and maintains recall without manual intervention. 31ms p50 at 1B vectors. 31ms 1B vectors · p50 {recommendations} Filtered results at the same speed as unfiltered. Metadata filtering runs inside the query, not after. Relevance and ranking land together, without added latency. 12ms P50 with filters Enterprise Building for your organization? Explore Enterprise Meet the compliance, security, and scale requirements to bring enterprise AI to market faster. Secure Encryption at rest and in transit, SSO, RBAC, CMEK, private networking. Compliant SOC 2 Type II, HIPAA, GDPR, and ISO 27001 certified. Reliable Uptime SLAs, support SLAs, and dedicated customer success built in. Start building knowledgeable AI today Create your first index for free, then pay as you go when you're ready to scale. Start Building Get a Demo Subscribe to Pinecone Subscribe Products Vector Database Dedicated Read Nodes Assistant Documentation Pricing Security Integrations Resources Community Forum Learning Center Blog Customer Case Studies Status What is a Vector DB? What is RAG? Company About Partners Careers Newsroom Contact Legal Customer Terms Website Terms Privacy Cookies Cookie Preferences © Pinecone Systems, Inc. | San Francisco, CA Pinecone is a registered trademark of Pinecone Systems, Inc.

Running AI agents of your own? AgentSpeed also monitors them in production — every run, its latency, cost, and failures, with alerts when something breaks. Free for 10,000 events a month, no credit card.