Blog · one trend at a time

DM Explains

One new AI trend at a time, taken apart properly: how it works, where it breaks, and whether you should use it.

No. 032 · Governance

Security guardrails: why screening the prompt isn't enough anymore

Prompt filters catch bad text, but the 2026 data says the bigger danger is what agents are allowed to do once they're inside — not what they were told.

20 Oct 2026 · 14 min read

No. 029 · Governance
Security-aware agent federation: AI agents cooperating without a spying boss
A cluster of new protocols lets AI agents from rival organisations work together and prove the system is healthy, without any single operator seeing what they actually did.
18 Oct 2026 · 16 min read
No. 022 · Governance
Secure multi-agent federation: who checks an AI agent's ID at the border
When an agent from one company calls an agent or tool in another, nothing standard proves who it is, what it may do, or who it answers to. A cluster of 2026 IETF drafts is trying to fix that.
11 Oct 2026 · 15 min read
No. 021 · Governance
Secure federation: how AI agents from different companies trust each other
Proving an agent's identity is nearly solved. The real fight is over how little authority it hands to the next agent in the chain.
10 Oct 2026 · 13 min read
No. 017 · Governance
Agent sprawl: why your company will have 150,000 AI agents by 2028
Every team can now spin up an AI agent in minutes. Without a registry, a lifecycle and an owner, those agents multiply, duplicate, overreach and outlive their purpose — quietly.
6 Oct 2026 · 13 min read

A new explainer lands most mornings. The feed carries each one the moment it publishes.

Subscribe by RSS

DM Explains

Security guardrails: why screening the prompt isn't enough anymore

More explainers

Security-aware agent federation: AI agents cooperating without a spying boss

Secure multi-agent federation: who checks an AI agent's ID at the border

Secure federation: how AI agents from different companies trust each other

Agent sprawl: why your company will have 150,000 AI agents by 2028