Overview

Deploy Confident AI on your AWS infrastructure for complete control over your evaluation and observability platform.

Architecture

The AWS deployment uses Terraform to provision a production-ready infrastructure with the following components:

VPC & Networking

Public/private/database subnets with NAT Gateway, Internet Gateway, and S3 VPC Endpoint.

EKS Cluster

Managed Kubernetes with autoscaling node groups and EBS CSI driver.

RDS PostgreSQL

Managed database in isolated subnets with automated backups, encryption, and password rotation.

ALB

HTTPS load balancer managed by ALB Controller with ACM certificates.

ArgoCD

GitOps tool for managing Kubernetes deployments.

S3 Storage

Private buckets for test cases, payloads, and ClickHouse backups with VPC endpoint access.

The Kubernetes cluster runs the following services:

Service	Namespace	Description
confident-backend	confident-ai	Express.js API service handling core platform logic
confident-frontend	confident-ai	Next.js web application for the Confident AI dashboard
confident-evals	confident-ai	FastAPI service for running LLM evaluations
confident-otel	confident-ai	OpenTelemetry collector for trace ingestion
redis	confident-ai	In-memory cache for session and queue management
ArgoCD	argocd	GitOps continuous delivery
ClickHouse Operator	clickhouse-operator	Manages the analytics database
ALB Controller	kube-system	Creates ALBs from Kubernetes Ingress resources
External Secrets	confident-ai	Syncs credentials from AWS Secrets Manager