
Human-in-the-loop patterns for email automation
Five ways to keep a person in control of email automation, from approve-to-send to sampled audits, with guidance on which pattern fits which kind of task.
4 min read
Blog · AI & email · page 5 of 5
AI triage, summaries, drafting and assistants that work with your mail, and how to keep a human in charge of every send.

Five ways to keep a person in control of email automation, from approve-to-send to sampled audits, with guidance on which pattern fits which kind of task.
4 min read

A decision table for AI email agents: rate sorting, summarizing, drafting, sending and deleting on reversibility and blast radius, then decide who acts.
5 min read

A playbook for fixing AI email sorting mistakes: move the message, spot the pattern, add rules only when they are exact, and keep a weekly misfile log.
4 min read

A worked example of testing AI email sorting on your own mail: sample 200 messages, label them by hand, build a confusion matrix and weigh costly errors.
5 min read

AI thread summaries are great for catching up and risky for contracts, numbers and tense conversations. A decision table and a spot-check habit for using them.
4 min read

Email is untrusted text written by anyone. Here is how prompt injection works against AI email assistants, how attackers hide instructions, and what they want.
5 min read

A quick checklist for reviewing AI-drafted email replies before you send: recipients, facts, promises, tone, links and the things a model simply can't know.
4 min read

A bad AI draft costs seconds; a bad sent email costs trust, money or worse. Why the review step between draft and send is a feature, not a limitation of AI.
4 min read

Why Koltrix sorts mail into five fixed categories instead of dozens, what belongs in each one, how teams work through them, and where custom labels still fit.
5 min read

What an AI email classifier actually looks at, how rules and models split the work, why it gets things wrong, and how to judge one on your own inbox.
6 min read