
Reviewing and revoking AI app connections to your mailbox
A runbook for the life of an AI app connected to your email: how OAuth grants work, a quarterly review, when to revoke, what revoking does, admin off switches.
5 min read

A runbook for the life of an AI app connected to your email: how OAuth grants work, a quarterly review, when to revoke, what revoking does, admin off switches.
5 min read

A five-part request, read-before-write, named filters, evidence, rules for doubt and one draft at a time: prompt habits that make an email assistant dependable.
5 min read

A daily routine for working email through Claude or ChatGPT once connected: summarize unread, find threads, apply labels, draft replies, then review and send.
5 min read

How AI assistants turn your requests into mailbox searches, and how to phrase prompts with names, dates and domains to find the right thread the first time.
4 min read

Email is mostly reading, sorting and replying, with small reversible actions and a natural draft checkpoint. Here is why it suits MCP, and where it needs care.
5 min read

Before you connect Claude, ChatGPT or another AI assistant to your email, run this checklist: account, permissions, sending, revocation, admin rules and logs.
5 min read

MCP, the Model Context Protocol, explained for people who live in email: clients and servers, how connections work, and what an email server should expose.
5 min read

A ten-minute morning routine: check categories, summarize what matters, list what needs a reply, answer three now and defer the rest. Includes a sample prompt.
5 min read