This page helps you assess readiness for a self-hosted Vijil deployment. Complete this checklist before beginning infrastructure work.Documentation Index
Fetch the complete documentation index at: https://docs.vijil.ai/llms.txt
Use this file to discover all available pages before exploring further.
Team Readiness
Self-hosted deployment requires coordination across multiple teams. Verify you have access to people with these skills:| Skill Area | Required For | Can You Access? |
|---|---|---|
| Kubernetes administration | Cluster setup, Helm deployments, troubleshooting | Required |
| Cloud IAM (AWS/GCP/Azure) | Service accounts, role policies, cross-service permissions | Required |
| Database administration | PostgreSQL provisioning, backup configuration | Required |
| Network/Security | VPC configuration, security groups, TLS certificates | Required |
| Auth0 administration | Application setup, SSO configuration | Required |
In smaller organizations, one platform engineer may cover multiple areas. The critical factor is having someone with permissions to provision each resource type.
Timeline Expectations
A typical deployment takes 2–4 weeks:| Phase | Duration | Activities |
|---|---|---|
| Prerequisites | 1 week | Provision infrastructure, configure networking |
| Deployment | 1 week | Install Vijil, configure data stores |
| Integration | 1 week | Connect Auth0, test agent connectivity |
| Validation | 3–5 days | Test evaluations, verify Guardrails |
Infrastructure Requirements
Before deploying Vijil, ensure you have the following resources available:- AWS Account: You must have access to an AWS account with sufficient permissions to create and manage EKS clusters, RDS/Aurora databases, OpenSearch domains, and S3 buckets.
- AWS CLI: Install and configure the AWS CLI on your local machine.
- kubectl: Install kubectl to interact with your Kubernetes cluster.
- IAM Permissions: Ensure your AWS user/role has permissions to create and manage EKS, RDS/Aurora, OpenSearch, and S3 resources.
- Basic Kubernetes Knowledge: Familiarity with Kubernetes concepts and resource management is required.
- Networking: Understanding of VPC, subnets, and security groups in AWS.
Dependencies
The following AWS resources and services are required for a production deployment of Vijil Evaluate:Core
- Amazon EKS Cluster: The primary compute environment for running Vijil Evaluate services.
Datastores
- PostgreSQL Database: Used for persistent storage of application data. This can be provisioned using:
- Amazon Aurora (PostgreSQL-compatible) – recommended for high availability and scalability.
- Amazon RDS for PostgreSQL – suitable for smaller-scale or non-production deployments.
- Any other PostgreSQL solution you want that your EKS cluster has permission to access
Object Storage
- Amazon S3: A single S3 bucket for storing evaluation artifacts, configuration files, Diamond resources, and file uploads. You will also need to add CORS configurations to the bucket so that it can accept signed URL file uploads from your browser. Below is an example of what to add in an AWS S3 bucket’s CORS configuration (it will be very similar in the cloud storage equivalents of other cloud providers):
JSON
Authentication
- Auth0 - You will require an Auth0 account and the ability to create an Auth0 application in your tenant
Summary Table
| Dependency | AWS Service / Provider | Purpose | Who Creates It |
|---|---|---|---|
| Compute | EKS | Run Vijil workloads | Customer |
| Relational DB | Aurora/RDS (PostgreSQL) | Persistent application data | Customer |
| Object Storage | S3 | Evaluation artifacts, configs, file uploads | Customer |
| TLS Certificate | ACM | HTTPS for console and API domains | Customer |
| DNS | Route 53 | Domain routing for console and API | Customer |
| Container Images | ECR (cross-account) | Pull Vijil container images | Vijil + Customer |
| Diamond Artifacts | S3 (copy to customer bucket) | Evaluation harnesses, detector configs, model weights | Vijil copies to customer S3 |
| AI Runtime | Bedrock AgentCore | Custom harness execution | Customer |
| Block Storage | EBS CSI Driver | Persistent volumes for telemetry | Customer |
| Pod AWS Access | EKS Pod Identity | Scoped AWS credentials for pods | Customer |
| LLM API Key | Groq, OpenAI, Anthropic, or local | Diamond evaluation and report generation | Customer |
| Evolution Engine | Darwin (separate Helm chart) | Agent evolution (optional) | Customer |
Note: All resources should be provisioned in the same AWS region for optimal performance and cost efficiency.Once these pre-requisites and dependencies are in place, you can proceed to the deployment steps.