Guardrailed AI in Constrained Environments & MCP Principles and Practice
Details
✨ Engineering Guardrailed AI in Constrained Environments & MCP: Principles & Practice ✨
Ready to dive into the next generation of practical, secure AI engineering?
Join us at Talent Garden Calabiana for a deep-dive technical night, co-hosted by Scops.ai and TAG.
We'll tackle two major frontiers in the modern AI landscape: the complex realities of engineering guardrailed AI in highly constrained environments, and the hands-on mechanics of the Model Context Protocol (MCP). Whether you're building rock-solid enterprise safeguards or giving your AI agents powerful new tools, this meetup is for you.
Agenda
- 18:30 Doors Open
- 19:00 Introduction
- 19:10 Talk: Engineering Guardrailed AI for Constrained Environments with Daniele Zonca
- 19:50 Talk: Model Context Protocol: Principles and Practice with Luca Baggi
- After the meetup we will organize a dinner close to the venue, anybody who wants to join is welcome!
Venue: Talent Garden, Via Arcivescovo Calabiana 6 (M3 Lodi or Brenta)
The event will be recorded and streamed on Python Milano Youtube channel (links will appear here close to the event)
Engineering Guardrailed AI for Constrained Environments
Daniele Zonca, Senior Principal Software Engineer @ Red Hat
Model Context Protocol: Principles and Practice
Large‑language‑model agents are only as useful as the context and tools they can reach.
Anthropic’s Model Context Protocol (MCP) proposes a universal, bidirectional interface that turns every external system—SQL databases, Slack, Git, web browsers, even your local file‑system—into first‑class “context providers.”
In just 30 minutes we’ll step from high‑level buzzwords to hands‑on engineering details:
How MCP’s JSON‑RPC message format, streaming channels, and version‑negotiation work under the hood.
Why per‑tool sandboxing via isolated client processes hardens security (and what happens when an LLM tries rm ‑rf /).
Techniques for hierarchical context retrieval that stretch a model’s effective window beyond token limits.
Real‑world patterns for accessing multiple tools—Postgres, Slack, GitHub—and plugging MCP into GenAI applications.
Expect code snippets and lessons from early adoption.
You’ll leave ready to wire your own services into any MCP‑aware model and level‑up your GenAI applications—without the N×M integration nightmare.
Luca Baggi, AI Engineer @ xtream
Luca is an AI Engineer in xtream (now part of TeamSystem). He is a active member to the Python and PyData communities in Europe, and an open source contributor.
✋ Please use your real Name and Surname to register, we cannot assure you will be able to access the venue if not.
** If you have a last minute issue please remember to cancel the RSVP.**
** Thanks for your cooperation**