Open source I maintain, and where it gets used
What I publish, what I contribute to, and the AWS services behind it. Every project below feeds the workshops and reviews: the patterns are tested here before they reach a customer.
- AWS Community Hero
- Open engineering reference
- Workshop walkthroughs
- Vienna
Projects you can read, fork and use
Freelancer AutomationPublic site
Workflow recipes and AI playbooks for independent consultants[14].
An AI video pipeline on AWS
A config-driven pipeline that turns raw event footage into finished cuts for several channels, built on AWS AI and media services with an agent crew for editorial decisions. I presented it at AWS Community Day Athens 2026 and describe it in my blog[10]. It will be published as open source; today it is available in customer projects, set up for each media workflow.
Walkthroughs of public labs
I run public AWS and Red Hat labs end to end before I deliver them, and document where the steps have changed.
Once Upon Agentic AI
Strands Agents, MCP and A2A on Amazon Bedrock. Level 300, eight chapters. Guided workshop →
OpenShift AI on AWS
Claims processing with Amazon Bedrock, RAG, computer vision and GitOps on ROSA[9]. Guided lab →
Where the patterns get tested in public
Von Managed zu Hybrid: KI-Architekturen
Master course at Hochschule Burgenland on AI architecture layers, hybrid routing and cost. The layer map →
AWS User Group Vienna
Organiser for more than seven years, co-organiser of AWS Community Day DACH.
AWS Community Days 2026
Talks on agent identity and agents as a new layer 8 in Istanbul, a live multi-agent build in Athens.
The AWS services I build with.
Grouped by what I build with them. For each service: what it does in plain language, with a link to the AWS documentation, and what I use it for in my projects. For the AI services there is a page on the technology itself and the other ways to run it, on Azure, Google Cloud or your own machines: AI technologies explained →
Media and video pipelines
Turning raw video and audio into searchable, structured content and channel-ready files.
How I built an AI film crew on AWS →What it isSpeech to text with word timings, speaker labels and custom vocabularies.
How I use itSpeech to text with custom vocabularies.
What it isDetects objects, scenes, text and faces in images and video.
How I use itLabel and scene detection in video.
What it isExtracts structured output from documents, images, audio and video with one managed call.
How I use itStructured output from media.
What it isFile-based video transcoding into the formats and aspect ratios each channel needs.
How I use itTranscoding into channel formats.
What it isWorkflow engine that runs steps in order or in parallel, with retries and waits, and shows every run.
How I use itOrchestrating parallel analysis workflows.
Models and agents
Foundation models for analysis and briefs, and agent crews that act on their own.
AI agent systems →What it isManaged access to foundation models from several providers through one API. You choose the model and write the prompt; AWS runs the model.
How I use itFoundation models for briefs, analysis and agents.
What it isRuntime, memory, identity and tool gateway for AI agents built with any framework, such as Strands or CrewAI.
How I use itRunning agent crews with memory.
The serverless backbone
What holds every pipeline together: storage, small functions, state, queues and monitoring.
AI use cases on AWS →What it isObject storage for raw files, documents, training data and results.
How I use itRaw media, documents, model weights and pipeline state.
What it isRuns small pieces of code on demand without servers to manage. You pay per request and duration.
How I use itPipeline steps and small services.
What it isServerless key-value database for state, sessions and job records.
How I use itPipeline and job state.
What it isEvent routing and scheduling (EventBridge) and message queues that buffer work between steps (SQS).
How I use itScheduling and queues between pipeline steps.
What it isRuns containers without managing servers or clusters.
How I use itRunning containers.
What it isLogs, metrics and alarms. For AI systems: latency, errors and cost per call.
How I use itLogs, metrics and alarms.
Platforms and accounts
The ground teams build on: accounts with guardrails, a developer portal and managed OpenShift.
Cloud architecture and modernization →What it isGroups AWS accounts, applies guardrail policies and consolidates billing.
How I use itAccount vending for the developer portal.
What it isOne sign-in for people across many AWS accounts and applications.
How I use itSign-in for account vending and the developer portal.
What it isRuns a container web app from an image with scaling and HTTPS handled by AWS.
How I use itHosting the Backstage developer portal.
What it isManaged OpenShift clusters in your AWS account. The base for running OpenShift AI next to other AWS services.
How I use itThe OpenShift AI on AWS lab.
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.
- ai-solutions.wiki
- GitHub: linda-mhmd/ai-solutions-wiki
- GitHub: linda-mhmd/freelancer-templates.org
- freelancer-templates.org
- GitHub: linda-mhmd/community-gameday-europe-stream-templates
- GitHub: linda-mhmd/community-gameday-europe-event
- GitHub: linda-mhmd/sample-once-upon-agentic-ai (fork of aws-samples)
- AWS Workshop Studio: Once Upon Agentic AI
- Red Hat: AI on ROSA workshop (rh-mobb)
- Blog: How I built an AI film crew on AWS
- Remotion
- Backstage, an open platform for developer portals
- AWS: What is AWS App Runner?
- freelancer-automation.com
Want this for your team?
30 minutes on what you want to build and which of these patterns fits. Or 15 minutes for a quick question.
Vienna, Austria · remote across Europe · [email protected]
