Weekly MailerLite list cleanup with NeverBounce

By General Input

Every Monday morning, your full MailerLite list is bulk-verified, risky addresses are removed, and your marketing-ops channel gets a clean health summary in Slack.

Integrations

  • MailerLite
  • NeverBounce
  • Slack

Type

Agentic Task

Categories

  • Marketing
  • Operations

Build me an agent workflow that runs on a weekly cron, every Monday at 7am Eastern, and does a full list-hygiene sweep on my MailerLite account using NeverBounce bulk verification.

Step 1: page through MailerLite List All Subscribers to collect every active subscriber. Keep each subscriber's id, email, and sign-up source fields (groups, form id, or whatever opt-in metadata is present) so the agent can attribute bad addresses back to a source later.

Step 2: hand the resulting email list to NeverBounce Create Bulk Verification Job with input_location set to supplied, auto_parse enabled, and auto_start enabled. Give the job a filename that includes the date so it is easy to find in NeverBounce later.

Step 3: poll NeverBounce Get Bulk Job Status until the job status is complete. Use a reasonable backoff (start around 30 seconds, grow to a few minutes for larger lists). If the job lands in under_review or any error state, stop the workflow and post a short note in the Slack channel explaining what happened so a human can take a look.

Step 4: page through NeverBounce Retrieve Bulk Job Results to pull every row. Match each result back to the MailerLite subscriber by email.

Step 5: act on each result. For invalid addresses, call MailerLite Delete Subscriber. For disposable addresses, call MailerLite Update Subscriber to set status to unsubscribed. For catchall and unknown results, do not touch the subscriber but include them in the report. Leave valid subscribers alone.

Step 6: post a Slack Send a Message summary to a marketing-ops channel I will specify when I set this up. The summary should include: total subscribers checked, counts by result type (valid, invalid, disposable, catchall, unknown), the number of subscribers unsubscribed vs deleted, the approximate credit spend for the run (one credit per non-duplicate address is a fine estimate, but use the actual tally from NeverBounce where you can), the worst-offending sign-up sources if any pattern is discernible from the MailerLite metadata, and a short two or three sentence paragraph the marketer can paste straight into their next list-health review.

Treat the unsubscribe-versus-delete threshold and the summary writing as places where the agent should use judgement. Keep the prompt structured so I can later swap the channel, tweak which result codes get cleaned up, or change the cron schedule without rewriting the whole thing.

Related prompts

Explore more prompts
Call overdue Xero customers with an AI collections agentWin back LiveChat visitors whose chats went unansweredChat quality review board for LiveChat support leadsWin back no-show and cancelled appointments every morningLive Loop returns analytics with product-level drill-downNewsletter pre-flight and approval board for Mailjet sendsTurn a prospect spreadsheet into personalized sequence enrollmentsMailjet email delivery lookup console for support teamsCatch feature flags that never got switched on in productionKajabi customer support console for member access fixes