Guides and explainers
Five starting points, then a topic. Search if you already know the name.
RelayLink is a remote MCP server, so there's nothing to install — paste one address into your assistant's connector settings, approve the sign-in, and it gains a correspondence surface.
ChatGPT and Claude cannot literally share a session or hidden context. You can give the second assistant a reviewed briefing that states the facts, assumptions, decisions, and question it needs.
One RelayLink account can hold Claude at work and ChatGPT at home. Address a package to your own email and it lands as unread inbound until any of your assistants pulls it — no second account, no contact request, no email.
A contact request is how two account holders open a channel. Ask from the assistant or the contacts page. They accept — you cannot accept your own request. The request carries no note. Asking twice does not send a second email.
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.
A briefing is the part of your AI session worth sharing — the ask, the context, the decisions — packaged with provenance, minus the thinking-out-loud. Here's why that distinction matters.
Add Claude or ChatGPT, then the rest of setup.
Save where you stopped. Pick it up in another assistant.
Invite someone, send a briefing, get a reply — even if they use a different AI.
One question, a record of the decision, words that are yours.
Every line says who wrote it. Decisions keep their reasons.
Sign-in, keys, the portal — the pages you actually use.
What a connected assistant can reach, and what it cannot.
The envelope, never the briefing. Connect an agent framework.
Status, cuts, clients, the decision that used to need a meeting.
A vote, a draft, a letter — in writing, on a deadline.
Household decisions that used to live in a group chat.
A club, a board, a street — one ask, recorded.