# TensorCost Docs

## Docs

- [Agent installation](https://docs.tensorcost.com/agent-installation.md): Install the unified TensorCost agent — IMDSv2 auto-detect, HMAC-SHA256 authentication, ≤15-minute onboarding via CloudFormation, Terraform, or Helm.
- [API reference](https://docs.tensorcost.com/api-reference.md): REST gateway for TensorCost — JWT auth, tenant-scoped, versioned at /v1/, organized by service.
- [Architecture](https://docs.tensorcost.com/architecture.md): A tour of TensorCost's multi-tenant control plane — 15 backend services, 14 microfrontends, 21 shared packages, and the data and event paths between them.
- [Bedrock integration](https://docs.tensorcost.com/bedrock-integration.md): Connect Amazon Bedrock to TensorCost in ≤15 minutes — read-only IAM, four shipped recommenders, multi-account / Organization mode, and the redaction guarantee.
- [Configuration](https://docs.tensorcost.com/configuration.md): Tenant configuration — RBAC, tag mapping, budgets, alert routes, branding, RLS policies, and the feature-flag surface.
- [Feature flags](https://docs.tensorcost.com/feature-flags.md): How TensorCost rolls out features safely with LaunchDarkly, the `useFeature()` pattern, and the quarterly stale-flag cleanup ritual.
- [Get started](https://docs.tensorcost.com/getting-started.md): Sign up, connect your first cloud account, see your first recommendation within 48 hours.
- [TensorCost](https://docs.tensorcost.com/index.md): The control plane for every dollar your company spends on AI — across GPUs, managed inference, and agent workloads.
- [ML, anomaly detection, and forecasting](https://docs.tensorcost.com/ml-anomaly-detection.md): How TensorCost detects anomalies and runaway loops, forecasts cost, and surfaces recommendations across GPU and managed-inference workloads.
- [Observability](https://docs.tensorcost.com/observability.md): Distributed tracing, structured logs, and graceful shutdown behavior across GoCloudera backend and agent.
- [Real-time events](https://docs.tensorcost.com/realtime-events.md): Subscribe to live tenant-scoped events via socket.io — recommendations, alerts, agent state, runaway loops, ML training. Plus the MCP server.
- [SOC 2 readiness and security posture](https://docs.tensorcost.com/soc2-readiness-guide.md): TensorCost's compliance posture — SOC 2 Type I in progress, RLS architecture, secret rotation, customer-onboarding least-privilege IAM, tenant offboarding, and the trust portal.