
Event
AI for DevOps & SRE: From Impressive Demos to Operational Trust
Online
About
A practical, vendor-neutral session from Bucharest XDevOps Meetup on the risks of AI-assisted operations and the controls that help manage them. It takes place online on Friday, 20 November 2026.
What to expect
The session works through three synthetic scenarios in isolated environments and the controls that help manage the risks of AI-assisted operations.
- The command is valid, the objective is wrong
- The query returns no data, the agent is confident
- The agent picks a tool outside operator boundaries
- Controls: scoped permissions and validation before execution
- Also human approval, audit trails, outcome verification
- Discussion of what these controls cannot guarantee
- 90 minutes, ending with discussion and Q&A
FAQ
What is the session about?
A practical, vendor-neutral session exploring the risks of AI-assisted operations and the controls that help manage them.
Three synthetic scenarios in isolated environments
What the controls catch and what they cannot guarantee
Who is it for?
DevOps engineers, SREs, platform engineers, developers and technical leaders exploring AI-assisted operations.
Familiarity with infrastructure operations is helpful
Experience building AI agents is not required
How do I register?
Register through the Meetup event page:
https://www.meetup.com/bucharest-xdevops-meetup-group/events/316850587/
What is the agenda?
A 90-minute agenda:
0–10: Introduction — what does operational trust require?
10–30: Three failure scenarios
30–55: Practical controls
55–75: Revisit the scenarios
75–90: Discussion and Q&A