Offerings¶

Whether you are building from scratch or hardening an existing environment, Flexible AI offers an architecture, support model, and starter kit for every stage.

Baseline for Building Full-stack AI Platform
- Pre-validated reference architectures combining GPUs, OSS frameworks, and AWS services
- Flexible, scalable design patterns covering many use cases and deployment options
- Self-service portal for unified model and agent access
White-glove Support
- AWS specialist guidance across compute, Kubernetes, storage, and more
- Best practices to maximize GPU value in production
- Deployment support across AWS, on-premises, and edge
Open-source via AWS Marketplace
- OSS stacks pre-configured and optimized by experts
- 1-click launch AMIs — skip the integration code
- Enterprise Edition with hardened security and governance, or BYOL options
Production-ready Starter Kit
- GenAI infrastructure toolkit that accelerates enterprise AI deployment
- AI Gateway, LLM serving, vector DB, embedding models, and E2E observability included
- Production-ready out of the box

Start now¶

The starter kit is ready to use directly from this repository. Three on-ramps:

Path 1 — Read the docs¶

Skim before installing anything:

Why Flexible AI — value proposition and the five flexibility dimensions.
Architecture — building blocks and the layered stack.
Components Overview — 25+ component catalog.
Use Cases — five scenarios and benefits.

No cluster required.

Path 2 — Run the demo¶

If you have an AWS account and the tools listed in Prerequisites, start here:

# 1. Install dependencies
npm install

# 2. Configure environment (writes .env.local)
./cli configure

# 3. Provision infra and deploy the curated stack in parallel
./cli demo-setup

Optional flags:

./cli --parallelism 6 demo-setup   # raise install concurrency
./cli --sequential   demo-setup    # legacy serial behavior

Tear it down with ./cli cleanup-everything.

Path 3 — Take the workshop¶

The Workshop Studio workshop under workshops/eks-genai-workshop/ runs three modules:

Module 1 — interacting with models (gateway + Open WebUI).
Module 2 — adding GenAI components (vector DB, observability, guardrails).
Module 3 — building and deploying an agentic application (Loan Buddy).

Delivery instructions live in workshops/eks-genai-workshop/README.md.

Customer Stories¶

Coming soon

Stories from customers redefining their AI infrastructure strategy with the Flexible AI approach will land here shortly.

Get in touch¶

If you'd like to discuss adoption, please reach out via:

GitHub Issues / Discussions — aws-samples/sample-genai-on-eks-starter-kit
For a direct meeting with the AWS Korea specialist team, please go through your AWS account team (SA / TAM).

Contributions and PRs are welcome — see the Contributing Guide.