Docs/Platform

Platform

Architecture

Last updated March 3, 2026

Understand the fundamental concepts behind the Cencori platform: CIP, Data Residency, and Global Infrastructure.

Cloud Intelligence Provider (CIP)

Cencori is not just an "AI Proxy." We are a Cloud Intelligence Provider (CIP).

  • AI Proxy: A simple pass-through layer that forwards requests. (e.g., Cloudflare AI Gateway).
  • CIP: A fully managed infrastructure layer that provides stateful intelligence. Cencori maintains context (Memory), enforces security (Scan), and orchestrates multi-step logic (Workflows) before requests ever reach a model provider.

Request Lifecycle

Understanding the flow of a single request helps clarify where value is added:

  1. Application: Your code calls the Cencori SDK.
  2. Edge Network: Request hits the nearest Cencori Edge node (deployed globally across 35+ regions).
  3. Security Scan: Payload is analyzed for PII, prompt injection, and policy violations. Latency: <10ms.
  4. Routing Engine: Cencori determines the optimal provider based on cost, status, and your project rules.
  5. Provider Execution: Request is forwarded to OpenAI/Anthropic/Google.
  6. Observability: Response is logged, token usage is calculated, and async evals are triggered.
  7. Response: Final payload is returned to your application.

Cold Starts: Cencori's edge network is built on warm execution environments. There is zero cold-start latency for standard API requests.

Data Residency & Privacy

We take data sovereignty seriously.

  • Logs & Analytics: Stored in our secure US-East (N. Virginia) cluster by default. Enterprise plans support EU-only storage.
  • AI Memory (Vector Store): Embeddings and vector data are encrypted at rest in dedicated isolated clusters.
  • Ephemeral Processing: Determining PII or routing logic happens in-memory on edge nodes and is never persisted to disk.

Global Infrastructure

Cencori is multi-cloud and multi-region by default.

  • Availability: 99.99% uptime SLA for Enterprise.
  • Regions: We route traffic through AWS, GCP, and Cloudflare networks to ensure lowest-latency connectivity to AI providers.
  • Failover: If a region goes down, traffic is automatically re-routed to the next nearest healthy node.

Platform Limits

To ensure fair usage and stability, the following limits apply:

LimitFree TierPro PlanEnterprise
Concurrent Requests10100Unlimited
Requests per Month10k1MCustom
Log Retention3 Days30 Days90+ Days
Team Members15Unlimited

Keys & Authentication

  • Project Keys (csk_...): Scoped to a specific project. Used by your application SDKs. If compromised, only that single project is affected.
  • Organization Keys (Coming Soon): Admin-level keys for programmatic management of multiple projects.

Comparison

Why choose Cencori over other solutions?

FeatureCencori (CIP)Helicone / PortkeyLangChain / LangSmith
Primary GoalProduction InfrastructureObservability & LoggingPrototyping Framework
Security (PII/Injection)Native / Built-inPlugin / ExternalManual Implementation
Unified SDKYes (One API)No (Proxy only)Yes (Abstractions)
Multi-ProviderNativeNativeNative
Vector MemoryIntegratedNoExternal (Vector DB)
Latency Impact< 15ms~50-100msN/A (Client-side)

Glossary

  • Gateway: The unified entry point for all AI requests.
  • Memory: Cencori's managed vector store for RAG and long-term history.
  • Scan: The security engine that inspects requests for vulnerabilities.
  • Namespace: A logical partition within Memory to isolate data (e.g., per-user or per-document).