Your developers build a working multi-agent system in one day.
A guided run through the AWS workshop Once Upon Agentic AI: Strands Agents, custom tools, MCP servers and agent-to-agent communication on Amazon Bedrock. Every chapter runs on the attendees' machines, and I explain where the SDKs have moved on.
- €5,000 per group
- Up to 12 developers
- Level 300
- English or German
The workshop is free. Finishing it is the hard part.
Once Upon Agentic AI is an AWS workshop at level 300: about two hours, eight chapters plus cleanup, available in English, French, German and Korean[1]. The code is open on GitHub[2].
In practice teams stall on the setup, on version changes and on the step from one agent to four processes talking to each other. When I ran every chapter in September 2026, four places had moved on: a deprecated built-in tool in strands_tools and a renamed server class in the MCP Python SDK among them.
The guided format keeps the whole group moving, answers the questions the page does not, and ends with a conversation about what the same pattern means for your own systems.
Four processes, one game master.
A role-playing game as the teaching story: a game master agent orchestrates a rules agent with a vector knowledge base, a character agent and a dice service behind MCP. The pattern is the same one used for support, claims or operations agents.
Eight chapters, each one runs.
What your developers can do afterwards.
Write tools that models use correctly
Custom @tool functions where the docstring is the contract the model reads.
Move tools behind MCP
Share one tool across agents and teams with a Model Context Protocol server.
Connect agents with A2A
Agents as servers, an orchestrator that calls them, structured output and a web UI.
Debug a multi-process agent system
Ports, logs and the typical failure points, plus the SDK changes to watch.
One group, one day.
Two workshop blocks (€2,000 each) and one written result: a starter repository adapted to your context with debrief notes (€1,000). Net, plus VAT.
Agentic AI hands-on workshop
Setup check before the day, two guided blocks for up to 12 developers, remote or on-site.
€2,000 each, 3 to 4 hours, remote or on-site
Delivered within 5 business days after the last session.
Core chapters
Full workshop
Attendees can use the free AWS Builder Center sandbox environment for the day[5] or your own AWS account with Bedrock model access.
Setup, build, transfer.
Setup check
A short checklist: git, uv, Python, AWS access. Blockers are solved before the day, not during it.
Agents and tools
First agent, built-in tools, custom tools, then the dice service as an MCP server.
Multi-agent system
Rules and character agents behind A2A, the game master, the web page, and a debrief on your use cases.
Real patterns, documented in the open.
Where the same agent patterns show up in production, documented on ai-solutions.wiki.
Building Enterprise AI Chatbots That Actually Help
Practical guidance for building customer-facing AI chatbots that deliver real value: architecture, knowledge base design, escalation patterns, and quality measurement.
Read on ai-solutions.wiki →InsuranceAI Claims Assistant - From Intake to Payout Recommendation
An AI assistant that guides claims from first notice of loss through evidence gathering, missing information detection, fraud screening, and payout recommendation: with human adjuster sign-off at every decision gate.
Read on ai-solutions.wiki →Public sectorAI Caseworker Assistant - Intake, Risk Flags, and Next Actions
An AI assistant that helps social services caseworkers process intake forms, surface risk signals, and identify appropriate next actions: reducing manual review time while keeping humans in control of all decisions.
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 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.
What people ask before booking.
What does the workshop cost?
€5,000 net for one group of up to 12 developers: two guided blocks plus a starter repository with debrief notes. A half-day version with the core chapters is €3,000.
Is the workshop content yours?
No. The workshop and its code belong to AWS and are published as aws-samples under an open licence. I deliver it as a guided session, with my notes on the current SDK versions and a debrief on your use cases.
What do attendees need?
A laptop with git, Python and uv, and access to an AWS account with Amazon Bedrock model access, or the free AWS Builder Center sandbox.
Which level is it?
Level 300. Attendees should be comfortable with Python and a terminal. No prior agent experience needed.
Can it run in German?
Yes. The workshop pages exist in German, and I run the session in German or English.
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 Workshop Studio: Once Upon Agentic AI, a developer's epic journey
- aws-samples: sample-once-upon-agentic-ai on GitHub
- Strands Agents SDK for Python on GitHub
- Model Context Protocol specification
- AWS Builder Center: workshops and free sandbox
- AWS: What is Amazon Bedrock AgentCore?
- AWS: What is Amazon Bedrock?
- OWASP Top 10 for LLM Applications
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.
- Group size and level
- Remote or on-site
- Sandbox or your own AWS account
- A date for the workshop
Vienna, Austria · remote across Europe · [email protected]
