Runtime AI Defense in a shared responsibility model

From the source: Sysdig Blog

An AI agent once deleted someone's entire inbox despite being told to confirm first. Not because it was malicious, but because the instruction didn't survive context compaction. Shantanu Gattani, Sysdig's SVP of Product, on why that gap is the real risk in agentic AI, and who should be responsible for closing it.

Read the full story on Sysdig Blog
Originally published by Sysdig Blog on 8 Oct 2026. Techarda links to the original rather than republishing it. Read the full article →

Ask the square

The story is what was announced. If it raises a question for your team, ask the people who run this technology day to day. Your post links back to this story, so the next reader finds it too.

Recent threads in Containers & Kubernetes

Something wrong or out of date? Suggest a correction. We reply within 5 business days.

More from Sysdig

Recent updates from Sysdig, so you can tell whether this is a one-off or part of a pattern.

All Sysdig news →

More in Containers & Kubernetes

What other companies in Containers & Kubernetes are doing. The category page shows who’s active, side by side.

Compare companies in Containers & Kubernetes →