Automation that keeps a person at the point it matters
Document processing, media pipelines and agent workflows on AWS, designed with retries, audit trails and approval steps from the start. Start with one workshop that maps your process and prices the automation.
- Workshop €2,000
- €1,000 per result
- AWS Step Functions and Bedrock
- English or German
Automation breaks at the edges, where the demo never goes
The happy path is easy to automate. The value sits in the documents that do not match, the clip without audio, the request that needs a person to approve it. Those edges decide whether an automation runs for years or is switched off after a month.
I design workflows as explicit state machines[1]: each step visible, retried when it fails, and routed to a person when the model is unsure. AI services do the reading, listening and deciding; the workflow keeps the record.
Documents, media, agents
Intake to decision
Forms, contracts and invoices read with Amazon Textract[3] or Bedrock Data Automation[2], checked against rules, routed for approval.
Footage to finished content
Transcription with custom vocabularies[5], scene detection, AI briefs and rendering for each channel[6][7].
Requests to actions
Agent crews on Amazon Bedrock AgentCore[4] that call your tools with narrow permissions and ask before anything irreversible.
What the automation workshop delivers
€2,000 for the workshop, €1,000 per written result. The standard package includes the first two.
Process map with automation candidatesIncluded
Your process step by step, with the steps worth automating, the edge cases and the expected savings.
Architecture and cost per workflowIncluded
AWS services, state machine outline and monthly cost at your volume.
Human-in-the-loop and audit designOptional
Where people approve, how uncertain results are routed, and what is logged.
Prototype backlogOptional
The first build, split into steps your team or a partner can pick up.
Map it, price it, then build
Net prices, plus VAT. Online booking for a 60-minute consulting session and the workshop series is below.
AI automation workshop
Intake, one workshop with the process owners, written results within 5 business days.
€2,000 each, 3 to 4 hours, remote or on-site
Delivered within 5 business days after the last session.
Real patterns, documented in the open.
Each link opens a write-up on ai-solutions.wiki, the open engineering reference I maintain. Architecture, services and trade-offs are explained there in full.
Intelligent Document Processing with AI
A practical architecture for extracting structured data from invoices, contracts, and forms: combining OCR, classification, and LLM-based extraction.
Read on ai-solutions.wiki →Public sectorAI Permit Processing for Government Agencies
Automated permit application review, compliance checking, and workflow management to reduce processing times and improve consistency.
Read on ai-solutions.wiki →Customer supportAI Ticket Routing and Classification
Automated support ticket classification, priority assignment, and intelligent routing to the right agent or team based on content analysis and historical patterns.
Read on ai-solutions.wiki →MediaBuilding an AI Video Pipeline on AWS
Architecture guide for an end-to-end AI video pipeline: S3 ingest, Lambda trigger, Rekognition analysis, Bedrock processing, FFmpeg editing, and Step Functions orchestration.
Read on ai-solutions.wiki →InsuranceAI for Insurance Claims Processing
Automated claims intake, fraud detection, and document extraction for insurance operations: from first notice of loss to payment authorization.
Read on ai-solutions.wiki →HRAI Employee Onboarding Automation
Streamlined employee onboarding using AI for personalized orientation, automated provisioning, knowledge delivery, and early engagement monitoring.
Read on ai-solutions.wiki →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.
AWS Step Functions
Workflow engine that runs steps in order or in parallel, with retries and waits, and shows every run.
AWS Lambda
Runs small pieces of code on demand without servers to manage. You pay per request and duration.
Amazon EventBridge
Routes events between services and schedules jobs.
Amazon Textract
Reads text, forms and tables from scanned documents and returns them as structured data.
Amazon Bedrock Data Automation
Extracts structured output from documents, images, audio and video with one managed call.
Amazon Transcribe
Speech to text with word timings, speaker labels and custom vocabularies.
AWS Elemental MediaConvert
File-based video transcoding into the formats and aspect ratios each channel needs.
Amazon Bedrock AgentCore
Runtime, memory, identity and tool gateway for AI agents built with any framework, such as Strands or CrewAI.
Check AWS funding before you pay.
Many AI proofs of concept and cloud migrations qualify for AWS funding: credits for the AWS usage and, in some partner programmes, funds for the delivery work. What applies depends on the project, the programme and the AWS account team. I check it in the Idea Call, and the workshop results are written so they can go straight into an application.
Proof of concept
For a prototype on AWS with a clear path to production.
Migration
For larger cloud moves, planned in phases.
What people ask before booking.
What does the automation workshop cost?
€2,000 for the workshop plus €1,000 per written result. With process map and architecture it is €4,000 net.
Which processes are good candidates?
High-volume, rule-heavy work with documents, audio, video or tickets, where mistakes can be caught by a person or a rule.
Do you build the automation too?
Yes, as a prototype after the workshop, or with your team or a delivery partner. The prototype backlog result prepares that.
Is the video pipeline available?
Yes, as a customer project set up for your media workflow. It will be published as open source later.
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.
- AWS Step Functions developer guide
- AWS: Amazon Bedrock Data Automation
- AWS: Amazon Textract asynchronous operations
- AWS: What is Amazon Bedrock AgentCore?
- AWS: Amazon Transcribe custom vocabulary
- Blog: How I built an AI film crew on AWS
- ai-solutions.wiki: Building an AI video pipeline on AWS
- ai-solutions.wiki: Intelligent document processing with AI
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.
- Which process to automate first
- Where people must stay in the loop
- What it costs to run
- Whether AWS funding could apply
Vienna, Austria · remote across Europe · [email protected]
