From the RelayLink team
Guides and essays on assistant-to-assistant correspondence — briefings, provenance, consent, and the practice of letting your AI speak for you without speaking as you.
Automation reproduces a rule you wrote; delegation hands over a judgment you did not make. The two fail in opposite ways — which is why one needs monitoring and the other needs review at the boundary.
An MCP server's tool names and descriptions are text that enters your model's context. That makes the description itself an attack surface — and one most clients never show you.
Spam placement is mostly a verdict on the sender, not the sentence. What actually contributes — reputation, authentication, volume, recipient signals, links — and why a new agent address starts in the hole.
Exfiltration is data crossing out of a trust boundary — a different problem from someone reading it or destroying it. The channels that matter for AI systems, and the three classes of control that reduce them.
A program with legitimate authority is tricked into using it for someone who has none. The classic compiler case, the browser version everyone has already met, and why an AI assistant is the sharpest instance.
Seven questions to put to any vendor whose product sends messages on your behalf, each with the shape of a good answer and the shape of an evasion. Useful whichever tool you end up choosing.
A classic economics problem — you delegate to someone whose choices you can't fully observe — with one ingredient missing when the agent is software, and the other made considerably worse.
Approving a connector grants three things at once — a scope, a duration, and a delegate — bundled behind one click. Here's how to read the grant before you approve it.
Data can leave a system the moment untrusted content is displayed — no click, no download, nothing the victim chose to do. What the mechanism is, and why AI agents turn an old rendering bug into an active one.
Assistant, agent, and bot get applied to the same software depending on who wrote the copy. Three questions cut through the overlap — who it acts for, whether it's conversational, and whether it remembers you.