AI agents for your business, built to survive production
Two days with your team. At the end, a multi-agent prototype runs on Amazon Bedrock against your data, with narrow permissions, evaluation and cost limits built in from the start.
- €5,000 net
- 2 workshop days
- Amazon Bedrock AgentCore
- AWS funding checked
The agent demo is the easy part
A demo on clean data takes an afternoon. A system that reads your real data, calls your tools and passes a security review is different engineering: identities, tool permissions, evaluation after model updates, cost per request, and a human for anything irreversible[6].
This workshop builds those parts in on day one, so the prototype you see on day two is shaped like the system you would run.
One request, end to end
A reference architecture from my lecture on AI architectures: an assistant whose crew runs on Amazon Bedrock AgentCore[1], with one narrow role per agent. The workshop builds the same shape for your use case.
A production-shaped prototype, against your data
Two workshop days (€2,000 each) and one written result, the prototype itself (€1,000): €5,000. Add written results if you need them.
Working agent prototypeIncluded
A multi-agent system in your AWS account or a sandbox you control, running against your data, code in your repository.
Architecture and permission mapOptional
Agent roles, hand-offs, tools, data access and the IAM role behind each agent.
Evaluation and cost planOptional
Test questions with expected answers, token budgets per agent, latency targets and alarms[2].
Production roadmapOptional
What it takes to run it: security review, operations, scaling, in weeks.
Two days, €5,000
Net prices, plus VAT. AWS proof-of-concept funding often applies; I check it in the Idea Call.
AI Agent Workshop
Pre-session architecture review, two workshop days with your engineers, the prototype in your account.
€2,000 each, 3 to 4 hours, remote or on-site
Delivered within 5 business days after the last session.
Two days, structured
Each block ends with something you can see working.
Architecture
Use case scope, agent roles, framework choice (Strands, CrewAI or LangGraph), tools and data mapped.
Tools and first run
Each agent's tools built, data wired, first end-to-end run on test data.
Hardening and hand-over
Permissions, evaluation and cost limits, run on real data, roadmap and hand-over to your team.
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 AgentCore
Runtime, memory, identity and tool gateway for AI agents built with any framework, such as Strands or CrewAI.
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.
AWS Identity and Access Management (IAM)
Who and what may call which service. For agents: one narrow role per agent.
Amazon CloudWatch
Logs, metrics and alarms. For AI systems: latency, errors and cost per call.
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 AI agent workshop cost?
€5,000 net for two workshop days and the working prototype. Optional written results cost €1,000 each.
Which framework do you use?
Strands Agents, CrewAI or LangGraph, chosen on day 1. All run on Amazon Bedrock AgentCore Runtime. Classic Bedrock Agents are in maintenance mode[3], so new builds use AgentCore.
Do we need our own model?
No. Most prototypes use models on Amazon Bedrock. If you have a tuned open-weight model, Custom Model Import can serve it[7].
Is this a training for developers?
No, this is a build for your use case. For a hands-on developer training, see the agentic AI hands-on workshop.
Where does it run?
On-site in Vienna or remote. The prototype runs in your AWS account or a sandbox you control.
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.
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 Agent Workshop (2 days)
Two workshop days and the working multi-agent prototype on Amazon Bedrock in your AWS account.
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.
- Whether your use case fits a 2-day build
- Which data and tools the agents need
- Your AWS account setup
- Whether AWS funding applies
Vienna, Austria · remote across Europe · [email protected]
