What problem does it solve?
It helps you operate a Mathematica mail database by generating correct code for showing, searching, updating, and replying to mail while preventing privacy-unsafe model routing.
Core Features & Use Cases
- Privacy-safe LLM routing: Uses $ClaudePrivateModel when mail privacy is high, and restricts $ClaudeModel use to public emails (privacy <= 0.5).
- Correct MailDBObject workflow: Ensures you load mail once via mailEnsureLoaded and pass a MailDBObject into showMails/searchFromMails (never a raw mbox string).
- Deadline and priority-aware filtering: Supports Period, HasDeadline, MinPriority/MaxPriority, MaxPrivacy, and dataset Select-based fallbacks for older versions.
- LLM-assisted deadline summaries and analysis: Uses mailAskLLM with security-aware auto model assignment and options like IncludeBody and HasDeadline.
- Ongoing maintenance tasks: Provides updateMonthlyMaildb, batchUpdateMaildb, and checkNewMail for keeping databases current, plus sendReply and translation-reply helpers.
Quick Start
Ask an AI to “Show my univ emails from the last week that have deadlines, and route any privacy-sensitive content correctly.”