machina discendi

Header image for The Security Cliff Between Your Local MCP Server and Production

The Security Cliff Between Your Local MCP Server and Production

by Corey in Conferences tags: mcp, security, AI_Engineer_Europe, agents

Tun Shwe (LinkedIn) and Jeremy Frenay (LinkedIn), both AI Engineers at Lenses.io, gave a joint talk at AI Engineer Europe 2026 on what happens when MCP servers leave the safety of a developer's laptop. Their central claim: most MCP servers are built for single-player local development and collapse the …

Read more →
Header image for Your AI Agent Is a Junior Developer. Manage It Like One.

Your AI Agent Is a Junior Developer. Manage It Like One.

by Corey in Conferences tags: ai_engineering, agentic_coding, context_engineering, AI_Engineer_Europe

Brendan O'Leary (LinkedIn, X), a Developer Relations Engineer at Kilo Code, opened his AI Engineer Europe talk with a observation that's easy to nod along with and hard to act on: most engineers have used AI tools by now, but almost none of them can articulate how they actually work …

Read more →
Header image for MCP Tools Are Raw Material, Not Finished Products

MCP Tools Are Raw Material, Not Finished Products

by Corey in Conferences tags: mcp, agents, tool_design, context_engineering, AI_Engineer_Europe

Nimrod Hauser (LinkedIn, X), a founding engineer at Baz, opened his talk at AI Engineer Europe with a deceptively simple observation: public MCP servers ship tools designed for everyone, which means they're optimized for no one. When you plug generic tools into a production agent, the agent hallucinates URLs, saves …

Read more →
Header image for Build the Gym, Not the Dataset

Build the Gym, Not the Dataset

by Corey in Conferences tags: reinforcement_learning, LLMs, open_source, small_language_models, AI_Engineer_Europe

Stefano Fiorucci (X, LinkedIn, GitHub) is an AI/Software Engineer at deepset, where he contributes to the open-source LLM framework Haystack. At AI Engineer Europe 2026, he made a case that the next leap for open-source language models isn't better datasets -- it's better environments. The kind where models can act …

Read more →