I need a compact Python solution that watches my inbox in real time, decides whether each incoming message is Work-related, a Promotion, or Personal, and then takes the right next step automatically. For every Work-related message it should be moved into a dedicated Work folder, flagged for follow-up, and—when I switch the option on—receive a short, templated acknowledgement. Promotions belong in their own folder but still get an auto-reply confirming receipt, while Personal mail is shuffled into its folder and simply flagged so I remember to answer later. The classifier itself can be a lightweight machine-learning or rules-based model; accuracy matters more to me than the particular library, though tools such as scikit-learn, spaCy, or even a fine-tuned transformer are all acceptable. Training data is limited, so please allow for easy retraining or keyword expansion from a JSON or CSV file. The script will connect through IMAP (Gmail) and must run headless on a small Linux VPS, ideally triggered by a cron job or an always-on listener. Key deliverables • Python source code with clear inline comments • Configuration file where I can edit folder names, thresholds, and reply templates without touching the code • README that shows setup, required packages, and a one-command way to test against sample messages • A brief report (or console log) summarising precision/recall after you validate on at least 30 sample emails per category Acceptance criteria • Minimum 90 % accuracy across the three categories on the provided test set • No message loss or duplication during the move/flag/reply workflow • Clean exit and helpful error reporting when the mailbox is unreachable or credentials are wrong If you have prior examples of email NLP or IMAP automation, point me to them so I can get a feel for your approach.