Run AI on your own platform next to Amazon Bedrock.
A guided run of the Red Hat lab OpenShift AI on AWS: an insurance claims story with LLMs on Amazon Bedrock, retrieval, computer vision, model serving on OpenShift and a GitOps deployment. About two hours hands-on, plus a debrief on what it means for your platform.
- €2,000 per group
- Red Hat OpenShift AI
- ROSA and Amazon Bedrock
- English or German
Layer 4, tried before it is bought.
Teams evaluating Red Hat OpenShift AI[3] usually ask the same thing: what does it feel like for data scientists, and how does it sit next to managed AWS services? This lab answers both on one ROSA cluster[5].
The lab uses a fictional insurer, Parasol, as its story[1][2]. Any time or cost figures in the story belong to that scenario, not to a real customer. What is real is the platform: workbenches, data connections, notebooks, model serving and deployment.
I ran all sections end to end in September 2026, including the optional model retraining and serving, and deliver it with the questions people actually get stuck on.
Seven sections, one claims app.
What your team can do afterwards.
Work in OpenShift AI
Data science projects, workbenches, connections and cluster storage.
Call Bedrock from the cluster
Amazon Nova Pro[6] through LangChain for summarisation, extraction and sentiment, next to a small model running in the cluster.
Add retrieval
Answers grounded in documents through an Amazon Bedrock Knowledge Base[7].
Deploy with GitOps
The claims app deployed through Argo CD[10].
One guided lab, €2,000.
One workshop block for your group. Lab environments are provided through Red Hat or your own ROSA cluster; cluster and AWS usage are not included. Net, plus VAT.
OpenShift AI on AWS guided lab
Environment check, guided lab and debrief, remote or on-site.
€2,000 each, 3 to 4 hours, remote or on-site
Delivered within 5 business days after the last session.
Guided lab
Lab + adaptation plan
The AWS services behind this work.
Plain-language notes on the services I use for this kind of project. Each name links to the official AWS documentation.
Red Hat OpenShift Service on AWS (ROSA)
Managed OpenShift clusters in your AWS account. The base for running OpenShift AI next to other AWS services.
Amazon Bedrock
Managed access to foundation models from several providers through one API. You choose the model and write the prompt; AWS runs the model.
Amazon Nova
Amazon's own foundation models on Bedrock, used for example in the OpenShift AI on AWS lab.
Amazon Bedrock Knowledge Bases
Retrieval-augmented generation: your documents are chunked, embedded and stored in a vector store, and the relevant parts go into the prompt.
Amazon SageMaker AI
Managed platform for the whole machine learning lifecycle: notebooks, training jobs, model registry and endpoints.
Amazon EC2 G6e instances
GPU instances with NVIDIA L40S cards for self-hosted inference, for example with vLLM.
What people ask before booking.
What does the lab cost?
€2,000 net for one guided block with your group. Cluster and AWS usage are billed separately to whoever provides the environment.
Who owns the lab content?
Red Hat. The lab and the Parasol demo application are published on GitHub. I deliver it as a guided session with a debrief.
Do we need a ROSA cluster?
Either your own ROSA cluster with OpenShift AI and Bedrock access, or an environment provided for the session. We check this before the date.
Are the Parasol figures real?
No. Parasol Insurance is a fictional company used as the lab's story.
Which level is it?
Data scientists and platform engineers comfortable with Jupyter notebooks and a terminal.
Linda Mohamed
I design and build AI and cloud systems on AWS and hybrid platforms, and I teach how they work. I have organised the AWS User Group Vienna for more than seven years, co-organise AWS Community Day DACH, teach AI architectures at Hochschule Burgenland, speak at conferences in Europe and the US, and maintain ai-solutions.wiki. Based in Vienna. Remote or on-site, in English or German.
Where the facts come from.
Prices, service names and limits change. The linked official pages are the reference; figures on this page were checked in September 2026.
- Red Hat: AI on ROSA workshop (rh-mobb/ai-on-rosa-workshop)
- Red Hat AI Services: Parasol Insurance demo application
- Red Hat OpenShift AI Self-Managed 3.5 documentation
- Red Hat: OpenShift AI supported configurations 3.x
- AWS: What is Red Hat OpenShift Service on AWS?
- AWS: Amazon Nova documentation
- AWS: Amazon Bedrock Knowledge Bases prerequisites
- OpenVINO Model Server documentation
- Ultralytics YOLOv8 documentation
- Argo CD documentation
Start with one conversation.
30 minutes to look at your idea, your data and the right starting point. Or book 15 minutes if you only have a question.
- Who should attend
- Which environment to use
- What you want to evaluate
- A date for the lab
Vienna, Austria · remote across Europe · [email protected]
