Harald Nezbeda
Python Technical Lead
Klagenfurt am Wörthersee, Austria
Actions
Hi, my name is Harald and I'm a passionate Python developer interested in development, DevOps and AI. I'm currently located in Austria working as a Senior Software Developer and Python Technical Lead for Anexia Digital Engineering.
I also work on Open Source Projects and write Articles and Tutorials on my blog.
Area of Expertise
Topics
The Unmanaged Node: Policy and Audit for AI Coding Agents
AI coding agents run on developer machines with full credentials. They execute shell commands, install packages, read every file in the project, and call external APIs. Your platform has network policy, workload identity, scoped secrets, and an audit trail — none of it reaches that machine. A public archive of 58 sourced incidents shows what goes wrong: deleted volumes, dropped production databases, leaked .env files, malicious packages installed on request. How do you put these agents back under policy?
This talk shows a practical approach, built on the observation that everything an agent does that you can't see leaves the machine over HTTP. That's where the control belongs. I'll show how an intercepting proxy enforces allow/deny rules per container rather than globally, why the client-supplied Host header can't drive that decision, when the filter should fail open and when it must fail closed, and how a bypass in our own policy parser was caught in review.
The same proxy produces the evidence. Every request lands in a local SQLite database with its host, source container, filter mode, block reason, and token spend, with credentials redacted before the write. I'll demonstrate the whole thing live using VibePod, an open source implementation.
Prompt Engineering Hands-on
This hands-on workshop teaches prompt engineering by working directly with Large Language Models. You'll learn how LLMs function under the hood and master practical techniques to get better results from them.
We'll use Google Colab for interactive coding and Groq's API for fast inference with open models—both free to use. You'll work hands-on with real LLMs, learning to craft effective prompts and apply advanced reasoning techniques you can immediately use in your own projects.
Cloud Native AI Summit - EUROPE 2026 Sessionize Event Upcoming
WeAreDevelopers World Congress 2026 - Europe Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top