AWS Community Day Italy
The Italian community day in Milan, under the theme Learn and be curious, curated by Monica Colangelo. The stage was a 50/50 gender split.
On the programme
From MacBook to Bedrock: Lessons from Building an AI Assistant
2025 · Milan
With Philipp Bergsmann. Building OTTO with InstructLab and Amazon Bedrock, the CrewAI agent architecture behind it, the Slack demo and the running cost of about 30 euro a month.
Women of Cloud workshop
2025 · Milan
Co-hosted with Suzana Melo and Darya Petrashka. No slides published for this one.
- No slides for this one
- Have me give this talk
On stage in Milan
Opening the talk in front of the chat log the agents produced. Photo by Dmytro Hlotenko, AWS Community Day Italy, Milan, 8 April 2025.
Walking through what the crew of agents actually does. Photo by Dmytro Hlotenko, AWS Community Day Italy, Milan, 8 April 2025.
The architecture on screen: from the laptop fine-tune to the model served on Bedrock. Photo by Dmytro Hlotenko, AWS Community Day Italy, Milan, 8 April 2025.
The services doing the work
Read off the slides, not guessed. Each card says what that service did in this build, and links to the page explaining the capability and how to run it somewhere else.
InstructLab
The open-source pipeline behind the fine-tune: documents become Q&A pairs in YAML, synthetic data is generated from them, then the adapter is trained with LoRA. Model-agnostic, and it ran on a laptop.
Amazon Bedrock
The workstation. Claude Sonnet 3.7, Amazon Nova Pro and the custom model are all served from one place.
Amazon Bedrock Custom Model Import
Serves the fine-tuned Llama 3.1 3B as the UG Specialist, so the trained model needs no cluster of its own.
CrewAI
Runs the crew: Q&A agent, agenda producer, header generator, speaker finder, GitHub planner and the UG Specialist.
AWS App Runner
Runs the agent container. The whole system came to about 30 euros a month.
Amazon ECR
Holds the container image App Runner pulls.
Amazon S3
Stores the trained model before Bedrock imports it.
Llama 3.1 3B
The open-weights base model that became the UG Specialist, adapted with LoRA rather than retrained.
Amazon Nova Pro
The agent model, and the teacher that generated the synthetic training data.
Claude Sonnet 3.7
Answers the open questions in the Q&A agent.
Red Hat OpenShift AI
The alternative to training on a Mac: the same run as a Jupyter environment or an OpenShift pipeline.
Slides from the talk
From MacBook to Bedrock, with Philipp Bergsmann. The slides that carry the architecture.
The five steps from a document to a working Slack bot: document knowledge, a Q and A YAML file, synthetic data generation, training, inference. Slide from the From MacBook to Bedrock deck.
Synthetic data generation: a taxonomy feeds a teacher model, Mistral Small 24B, which scales the set thirty times into a training and test dataset. Slide from the From MacBook to Bedrock deck.
The first agent crew: a Meetup Manager on Amazon Nova Pro delegating to a GitHub Planner, a Speaker Finder and an Agenda Producer, with Chroma as short term memory. Slide from the From MacBook to Bedrock deck.
The second crew: Slack talks to a Q and A agent on Claude Sonnet 3.7, a User Group Specialist on a custom Llama 3B model and a Speaker Finder on Amazon Nova Pro. Slide from the From MacBook to Bedrock deck.
The running cost of the entire setup, about thirty euro a month. Slide from the From MacBook to Bedrock deck.
The longer write-ups
Where the builds behind these sessions are explained properly.
From AI Demo to Enterprise Solutions
The longer write-up: the build, the services and what it costs to run.
Enterprise AI Consultant vs. AI Consultant
The longer write-up: the build, the services and what it costs to run.
What is an AWS Community Day?
The longer write-up: the build, the services and what it costs to run.
10 Years of AWS User Group Vienna
The longer write-up: the build, the services and what it costs to run.
The same talk, other stages
Same session, a different room. Each page carries its own deck.
- AWS re:Invent
- AWS Community Day DACH
- AWS Community Day Slovakia
- AWS Community Day Czech Republic
- AWS Community Day Romania
- AWS Community Day Poland
- CTRL+ESC Malta
- AWS Student Builder Group St. Pölten
- Cloud Day FH Burgenland
Where all of this comes from
Every claim on this page traces back to the deck, the recap or the event’s own site.
- awscommunityday.it, the event’s own site
- Slides: From MacBook to Bedrock: Lessons from Building an AI Assistant, 2025
- Recap: From MacBook to Bedrock: Lessons from Building an AI Assistant, 2025
- From AI Demo to Enterprise Solutions
- Enterprise AI Consultant vs. AI Consultant
- What is an AWS Community Day?
- 10 Years of AWS User Group Vienna
Everything here is free to read, use and share. No email needed for the slides. If you reuse something, please credit the source.
This page mirrors the talk page on lindamohamed.com, where it was first published.