Skip to main content
Plain filters two kinds of unwanted email: senders you mark as spam, and automated replies it detects on the way in. You can also use AI to catch spam that gets past both.

​
Marking customers as spam

To mark a sender as spam, use a keyboard shortcut:
  • Go to one of the threads associated with the spam address.
  • Press ⌘ + K and select Mark customer as spam.
Once marked, threads will still be created but will be ignored, meaning you won’t receive notifications or see them in your To-Do list. You can see customers that you’ve previously marked as spam from Settings → Spam.

​
Using AI to ignore spam

The AI prompt condition in workflows can act on the content of a thread, not only its metadata, and it’s well-suited to detecting spam.

​
Setting up a spam detection workflow

The AI condition prompt is a free-text field (up to 2,500 characters). A well-written prompt is the most important part of making this reliable. Example prompt:
This thread is spam or should be silently ignored. Examples include: unsolicited sales or partnership outreach, automated phishing or credential-harvesting messages, irrelevant mass marketing unrelated to our product, test messages with no genuine support intent, or messages that appear to be sent to the wrong company entirely. If you are uncertain whether this is spam, treat it as spam and return true.
Your workflow structure would be:
  1. Trigger: Thread created (or Message added, if you want to catch spam that arrives as a follow-up)
  2. Condition: AI prompt condition with your spam criteria
  3. Action: Set Status → Ignored

​
What this approach handles well

  • Text-based outreach spam: Sales emails, partnership pitches, automated marketing blasts: anything where the message content reveals the intent.
  • Misdirected messages: Threads clearly sent to the wrong company or product.
  • Phishing and credential requests: Messages asking for login details, wire transfers, or similar.
  • Pattern-based spam: If your spam follows recognizable patterns, you can describe them explicitly in the prompt and the model will apply them consistently.
  • Attachment content is not analyzed
  • No external reputation signals: the AI condition works exclusively with data Plain has stored about the thread and customer. There is no access to email headers, sender IP reputation, domain blocklists, or DMARC/SPF results. If you need header-level or network-level filtering, that has to happen upstream at your email provider before the thread reaches Plain.
  • Already-flagged spam customers are handled separately: if a customer has already been marked as spam in Plain, workflows do not run for their new threads. They are caught earlier in the pipeline and their threads are automatically closed as ignored.

​
Auto-reply detection

When emails are forwarded into Plain, every inbound message is automatically scanned before a thread is created. If Plain detects that an email is an auto-reply, such as an out-of-office response or any other automated message, it is filtered out. No thread is created and no notifications are sent. This prevents common feedback loops where automated systems reply to each other indefinitely, and keeps your queue free from noise.

​
What Plain detects

Plain checks a combination of standard email headers and subject line patterns to identify auto-replies. Email Headers
  • Auto-Submitted (RFC 3834): the industry standard for marking automated messages
  • Precedence: auto_reply or Precedence: bulk
  • X-AutoReply
  • X-Autorespond
  • X-Amazon-Auto-Reply
  • X-amzn-vacation (Amazon WorkMail)
  • X-SFDC-AutoResponse (Salesforce)
  • X-ServiceNow-Generated
  • X-Front-Autoreply (Front)
  • X-CodeTwo-AutoResponse / X-C2AutoRespond
  • X-MDAutoResponse
  • X-QQ-Auto-Reply
  • X-MS-Exchange-Generated-Message-Source

​
Subject line patterns

Plain also recognizes common auto-reply subject prefixes across more than 20 languages, including:
  • English: “Automatic reply:”, “Out of office:”, “Autoreply:”, “Auto response:”
  • German: “Automatische Antwort:”, “Abwesenheitsnotiz:”
  • French: “Réponse automatique :”
  • Spanish: “Respuesta automática:”
  • Japanese: “自動応答:”
  • Chinese: “自动答复:”, “自動回覆:”
  • And many more (Polish, Czech, Turkish, Arabic, Hebrew, Greek, Russian, and others)
Subject line patterns alone are not sufficient to filter an email. Plain requires at least one supporting header signal alongside a matching subject to reduce the chance of false positives.

​
What happens to filtered emails

Emails identified as auto-replies are routed to filtered emails. They are not lost, but they do not create threads, trigger workflows, or generate any notifications. You can review filtered emails in your workspace settings if you need to inspect or recover a message.

​
If auto-replies are slipping through

Some automated systems do not include standard auto-reply headers. In these cases, Plain cannot identify the message as automated and will create a thread as normal. The best workaround is to set up a workflow rule that catches these threads after creation:
  1. Go to Settings → Workflows and create a new rule.
  2. Set the trigger to Thread created.
  3. Add a condition using Message contains with phrases typical of automated acknowledgements. For example: “your request has been received”, “a ticket has been created”, “this is an automated response”.
  4. Optionally, add a Sender email includes condition to scope it to known helpdesk addresses.
  5. Set the action to Mark as Done.
This combination keeps your queue clean without affecting legitimate threads from the same senders. If you are seeing a high volume of looped threads from a specific source, contact us. We may be able to add the sender’s headers to Plain’s detection rules.