From the RelayLink team

Blog

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.

Reference 5 min read

What is non-repudiation?

Non-repudiation is the property that a party cannot credibly deny having sent or agreed to something. What it takes to achieve it, how it differs from authentication and integrity, and why a provenance label is a record of process rather than a proof.

Reference 5 min read

What is data exfiltration?

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.

Guides 7 min read

Troubleshooting an MCP connection that won't work

A bottom-up debugging ladder for remote MCP servers — reachability, transport, the auth header, stale tool lists, logs — plus the RelayLink symptoms that look like failures and aren't.

Reference 5 min read

How email threading actually works

A mail thread is not something the protocol stores. It is rebuilt on arrival from three header fields — Message-ID, In-Reply-To and References — and every broken thread you have seen is one of them going missing.

Reference 5 min read

How to evaluate an AI communication tool

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.