Your billing data drifts. Customer descriptions go stale, product copy stops matching across the catalog, and invoices pile up with notes that nobody followed up on. The obvious fix is to point an AI at it, but pointing an AI straight at Stripe means handing a model live API access to your billing system, and even then it reads a few records at a time and never sees the whole picture.
Scratch takes the other path. It pulls your Stripe records down to files on your computer, and your AI reads and reasons over all of them there. It surfaces stale descriptions, flags inconsistent product copy, and drafts cleanup proposals as files you read alongside the originals. Stripe is read-only today, so nothing the AI does touches your live account. It proposes, you review. Publish-back is on the roadmap. Scratch is the companion app to Whalesync: Whalesync keeps your tools in sync, and Scratch is where you audit and plan the cleanup first.
What Scratch pulls from Stripe
- Customers (name, description, metadata)
- Products and prices
- Subscriptions and invoices
- Payment intents and charges
How it works
- Scratch pulls your Stripe records into local files. Customers, products, prices, subscriptions, invoices, payment intents, and charges all come down to a folder on your computer, one file per record. This is read-only. Nothing touches your live Stripe account.
- Your AI reviews and proposes cleanup over the files. Open the folder in the agent you already use. It reads every record, audits the data, and writes cleanup proposals, audits, and summary reports.
- You read the AI's output as files alongside the originals. Each proposal sits next to the record it came from, so you can read what the AI found and decide what to do with it. Publish-back to Stripe is on the roadmap. Today this is the read side of the loop.
What teams use it for
- Surface customers with stale descriptions and metadata that no longer matches reality.
- Find products and prices with inconsistent copy across the catalog.
- Flag invoices that need a follow-up note before close.
- Run catalog reviews before a pricing refresh.
- Run end-of-month customer audits.
- Feed billing context into AI workflows without giving the AI direct API access.
Why pull it into files at all?
Because it gives the AI full context over every record without handing it direct API access to your billing system. The AI reads all of your customers, products, and invoices at once, not a sample it paged through over an API. The analysis runs against local files, so it is fast, about 10x faster than the same AI working over an API. And your live Stripe account is never touched. The AI reasons over a copy. Your source of truth stays exactly as it was.
What's safe
Nothing writes back. Stripe is read-only today, so the AI never touches your live billing system. 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. The whole workspace is git-backed, so every pull and every proposal is tracked. Publish-back to Stripe is coming. Scratch is SOC 2 compliant.
Questions Stripe users ask
Can Scratch change my Stripe data?
No. Stripe is read-only today. Scratch pulls your records down to local files, and your AI reads and proposes cleanup over those files. Nothing writes back to your live Stripe account. Publish-back is on the roadmap, but today this is the read side of the loop.
How is this different from giving an AI direct Stripe API access?
Direct API access hands a model live access to your billing system and still only lets it read a few records at a time. Scratch pulls everything into files first, so the AI reasons over all of your records at once, faster, and without ever touching the live system.
Which AI does it use?
Whichever one you already use. Scratch holds no AI credentials and runs no model. You bring Claude, Claude Code, Codex, Cursor, Copilot, Cline, or Windsurf, and it reads the local files.
Is my billing data safe?
Yes. The files live on your computer, the workspace is git-backed, and Scratch is SOC 2 compliant. Because nothing writes back today, the AI can never alter your live Stripe account.
See it on your own Stripe
Pull your Stripe records into files and let your AI audit them, then read the proposals alongside the originals.