As of 13 August 2026, AI can only partly unsubscribe from spam emails safely.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, no skill needed, and roughly 15 minutes until you can act on the result.

   How to actually do it

   1. Open the suspicious message without clicking any links or downloading attachments, and note the sender name, subject and visible message text.
   2. Remove your name, email address, order numbers, addresses, phone numbers and any other private details from the text before pasting it into the prompt.
   3. Ask the chatbot to classify the message as an ordinary marketing email, suspicious spam or possible phishing, and to explain whether the safest route is your email provider's built-in controls or the sender's official website.
   4. If it is ordinary marketing from a sender you recognise, open your email provider's built-in unsubscribe, block or spam control rather than using an unfamiliar link in the message.
   5. If it is a sender you recognise but your provider has no safe unsubscribe control, type the sender's official website address yourself, find its contact or email preferences page, and unsubscribe there without entering a password from an email link.
   6. If the message looks suspicious or asks for login, payment or personal information, mark it as spam or phishing in your email provider and delete it instead of unsubscribing through the message.
   7. Check your inbox over the next few days for further messages from the same sender, and block or report them through your provider if they continue.

   Prompt

   Help me decide how to stop receiving this email safely. Do not tell me to click a link inside the message unless there is strong evidence that it is a genuine marketing email from a sender I recognise. Prefer using my email provider's built-in spam, block or unsubscribe controls, or navigating to the sender's official website myself. Do not open links, download attachments or submit passwords, payment details or other personal information. Explain what clues support your recommendation, what cannot be confirmed without live access, and what I should do if the message looks like phishing. Here is the sender name and the visible message text, with personal details removed:
   
   Sender: [sender name]
   Subject: [subject]
   Message text: [paste visible text here]

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.