Koltrix
AI & email
Read, organize, draft, never send: a capability model for AI email
A five-tier capability model for AI in email: read, organize, draft, send and delete, with the risk and reversibility of each and why the line sits before send.
5 min read
AI & emailDefending AI email assistants against hidden instructions
Layered defenses against prompt injection in email: capability limits, human approval, untrusted-content handling, hidden HTML, tool chains and logging.
5 min read
AI & emailRed-teaming your AI inbox setup with safe test emails
Send yourself harmless test emails with embedded instructions to see if your AI assistant obeys mail content. Test cases, expected behavior and a scoring sheet.
5 min read
AI & emailAuditing what an AI assistant did in your mailbox
Why every AI tool call in your mailbox should be logged, what a good audit trail records without storing mail content, a weekly review routine and red flags.
4 min read
AI & emailCatching hallucinated facts in AI email replies
AI drafts can invent features, dates, policies, links and names. Five worked examples of each kind of error, plus a habit that catches them before sending.
5 min read
AI & emailHuman-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
- AI & email
Prompt injection in email: what it is and why inboxes are exposed
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