The generative AI use cases that pay for themselves
One workshop to sort your GenAI ideas: which ones are worth building, whether prompts, retrieval or fine-tuning fits each, and what a first concept looks like on your data.
- €4,000 with 2 results
- Amazon Bedrock and open models
- Remote or on-site
- English or German
Most GenAI ideas die on data and fit long before the model matters
Every team has a list: a chatbot, document summaries, a writing assistant, contract checks. The model is rarely what decides success. What decides it is whether the right knowledge is reachable, whether the task needs a large model at all, and how you will know the answers are right.
Generic models miss your business context. Most use cases need retrieval over your own documents[2]; a few need fine-tuning[3]; some are better served by a ready-made service like Amazon Textract[4]. The workshop makes that call per use case, before anyone buys a licence.
Model choice comes last. The LLM landscape page on ai-solutions.wiki, one of its most-read pages, shows how quickly the options change[7].
Ready-made service or generative model?
The same invoice, two ways. Many GenAI ideas turn out to be layer-1 problems that a cheaper, predictable service solves.
What you walk away with
€2,000 for the workshop, €1,000 per written result. The standard package includes the first two.
GenAI use-case shortlistIncluded
Candidates scored on value, data readiness, risk and effort, with a recommended first use case.
Technique decision per use caseIncluded
Prompting, retrieval, fine-tuning or a ready-made service, with the reasons and the data each option needs.
Concept test on your dataOptional
A small sample run through the chosen approach, with example outputs and what went wrong.
Risk and evaluation notesOptional
Prompt injection, data leakage and hallucination risks for the use case[5], and how to test answers.
One workshop, results you choose
Net prices, plus VAT.
Generative AI Use Case Workshop
Intake, one workshop with up to 8 people, 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.
GenAI workshop
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.
AI Contract Analysis and Review
Automated contract review, clause extraction, risk identification, and obligation tracking using NLP and large language models.
Read on ai-solutions.wiki →Customer supportAI Knowledge Base Automation for Customer Support
Automated knowledge base creation, maintenance, and optimization using AI to keep support content accurate, comprehensive, and discoverable.
Read on ai-solutions.wiki →MediaAutomated Content Metadata and Tagging with AI
Auto-tagging video and audio content, scene classification, topic extraction, and SEO metadata generation for media libraries.
Read on ai-solutions.wiki →GuideMultimodal RAG guide
Retrieval over text, images and documents, with architecture options.
Read on ai-solutions.wiki →InsuranceAI Policy Document Processing for Insurance
Automated extraction, classification, and analysis of insurance policy documents, endorsements, and regulatory filings using NLP and document AI.
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.
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 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 Bedrock Guardrails
Filters for topics, harmful content and personal data on the way into and out of the model.
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 OpenSearch Service
Search and vector search engine, often the vector store behind a knowledge base.
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 GenAI use case workshop cost?
€2,000 for the workshop plus €1,000 per written result. With the shortlist and the technique decision it is €4,000 net.
Do we need to pick a model beforehand?
No. The workshop decides the use case and the technique first. Model choice follows from data, quality and cost requirements.
Is our data safe with a managed model?
Amazon Bedrock does not use your prompts and outputs to train models[9] and runs in the AWS Region you choose. Retrieval runs in your environment; the workshop checks what may cross that boundary.
Can this run on open models or on-premises?
Yes. If data may not leave, the technique decision includes self-hosted models, for example on Red Hat OpenShift AI.
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: What is Amazon Bedrock?
- AWS: Amazon Bedrock Knowledge Bases prerequisites
- AWS: Model customization in Amazon Bedrock
- AWS: Amazon Textract document limits
- OWASP Top 10 for LLM Applications
- ai-solutions.wiki: Multimodal RAG guide
- ai-solutions.wiki: LLM landscape 2026
- ai-solutions.wiki: Build vs buy for AI
- AWS: Data protection in Amazon Bedrock
Book it right here.
All prices are net. Companies outside Austria pay no VAT and can book directly by card. Companies in Austria, please choose “Pay by invoice”: 20% VAT is added there.
AI Discovery Workshop
One session and two written results, starting with the scored use-case shortlist.
Buy now →Pay by invoiceAdditional written result
Add a written result to any workshop. Choose the quantity at checkout.
Buy now →Pay by invoiceStart 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 GenAI ideas you have
- What data they need
- Whether retrieval or fine-tuning fits
- Whether AWS funding could apply
Vienna, Austria · remote across Europe · [email protected]
