An import or a tagging migration leaves drift everywhere. The same tag is spelled three ways. Notes ramble or contradict each other. Custom fields fill in formats that no longer match. None of it is hard to fix on one subscriber. The problem is that it is thousands of subscribers deep, and the dashboard makes you do it one at a time, so the cleanup keeps getting pushed.
Scratch pulls your subscribers down as files on your computer. Your AI reads them all, standardizes the tag spelling, tightens the notes, and cleans up the custom-field drift across the whole list, not a sample. Every change comes back as a word-level diff next to the original, and nothing reaches Audienceful until you approve it. Status, dates, and engagement metrics are never touched.
Scratch is the companion app to Whalesync. Whalesync keeps your tools in sync; Scratch is where you clean the subscriber data up first, so what syncs out is already consistent.
What Scratch edits in Audienceful
- Subscriber tags
- Subscriber notes
- Custom fields
How it works
- Scratch pulls your subscribers into files. Your Audienceful subscribers come down to a folder on your laptop, one file per subscriber, with their tags, notes, and custom fields. Nothing touches the live list.
- Your AI edits the fields you point it at. Open the folder in the agent you already use. Try a prompt on a few subscribers, then let it run across the whole list. Standardize the tag spelling, tighten the notes, clean up the custom-field drift. Status, subscription dates, double-opt-in, bounce flags, and open and click rates stay read-only, so the agent edits the copy but cannot move them.
- You review every diff and publish. In the Scratch desktop app, each changed field shows next to the original, word by word. Approve what ships, and Scratch writes only the subscribers you approved back through the Audienceful API.
What teams use it for
- Standardize tag spelling after a tagging migration, so one tag stops appearing under three names.
- Tighten and normalize subscriber notes that drifted across imports and admins.
- Clean up custom-field drift, so the same field reads the same way for everyone.
- Reconcile tags and fields after an import, so a fresh batch matches the existing list.
- Collapse near-duplicate tags into one canonical spelling across thousands of subscribers.
- Roll back a tag or field change, per subscriber, when a pass went wrong.
Why not let AI write straight to Audienceful?
A direct API write or an MCP server hands the AI the publish button straight to your live list. There is no diff, no review queue, no rollback. One blind pass across thousands of subscribers can retag the wrong segment or overwrite notes you meant to keep, and a bad tag write can quietly change who gets your next send. By the time you notice, it is already live and the original is often gone.
Scratch gives the AI the same access, but against a local copy of your subscriber list. The write-back step is pulled out and handed to you. The agent can change anything in the copy, only you commit it, and Scratch writes back only the fields you changed, so status, dates, and engagement metrics, and the fields you did not touch, stay exactly as they were. Every subscriber Scratch writes back is reversible on its own.
What's safe, and what's locked
Status, subscription dates, double-opt-in, bounce flags, and open and click rates are read-only system fields. They are stripped before write-back, so the agent cannot push them even if it edits the copy. You bring your own AI: Scratch holds no AI credentials and runs no model, so you sign into Claude, Claude Code, Codex, Cursor, Copilot, Cline, or Windsurf the way you already do. By default, nothing leaves your machine until you publish. Every published change is reversible per subscriber. Optional Python validators, which the AI can author, flag edits that touch a protected field or break a tag convention, right next to the diff.
Questions Audienceful users ask
Can Scratch change a subscriber's status or engagement metrics?
No. Status, subscription dates, double-opt-in, bounce flags, and open and click rates are read-only. The agent edits a local copy, and those fields are stripped before write-back, so they never reach Audienceful. Scratch only writes back the tags, notes, and custom fields you approve.
Will a retag go live across my list before I see it?
No. Every tag change lands in local files first and shows next to the original as a word-level diff in the Scratch desktop app. You approve subscriber by subscriber, and Scratch writes only the subscribers you approved back through the Audienceful API, so a blind retag across thousands of people cannot happen.
Does the AI get my subscriber data, or send it anywhere?
You bring your own AI and sign into it yourself. Scratch holds no AI credentials and runs no model. Your subscriber files stay on your machine, and nothing leaves it until you publish the changes you approved.
Can I undo a tagging pass after it has written back?
Yes. Every subscriber Scratch writes back is reversible on its own. Roll back one subscriber or the whole pass, and Scratch restores the original tags and fields for you to publish.
See it on your own Audienceful
Pull your subscribers into files and watch the AI standardize one tag across the whole list, then publish only what you approve.