Moco holds the agency together, so it drifts the way agency records do. Company records get written three ways across the team, contact bios go stale, and project descriptions and metadata never quite line up when you go to pull references for the next pitch. Cleaning it up by hand means opening one record at a time, right when you want the CRM presentable for a new pitch cycle.
Scratch pulls your Moco CRM down as files on your computer. Your AI reads and edits every record, not the first few hundred, about 10x faster than it works over an API because it reads the files directly instead of making a call per record. Every change comes back as a word-level diff next to the original, and nothing writes back until you approve it, per record. Scratch is the companion app to Whalesync: clean the CRM up here, then let Whalesync keep it in sync once the records are right.
What Scratch edits in Moco CRM
- Company records and notes
- Contact records and bios
- Project descriptions and metadata
How it works
- Scratch pulls your Moco CRM into files. Companies, contacts, and projects come down to a folder on your laptop, one record per file. Billing rules, time entries, and structural relationships are pulled for context only and stay where they are.
- Your AI edits the fields you point it at. Open the folder in the agent you already use. The AI rewrites the prose, the company records and notes, the contact bios, and the project descriptions and metadata. Try a prompt on a few records, then let it run across the whole CRM. The AI edits the files, never the live system.
- You review every diff and write back. In the Scratch desktop app, each changed field shows next to the original, word by word. Approve what looks right, and Scratch writes only the records and only the fields you approved back through the Moco API. Untouched fields are left exactly as they were.
What teams use it for
- Standardize company records across the agency so they read the same way.
- Tighten contact bios that went stale between engagements.
- Clean up project descriptions and metadata before a new pitch cycle.
- Normalize naming and copy that drifted as it passed between teams.
- Reconcile records after a migration into Moco, so the source of truth matches again.
Why not let AI write straight to Moco?
A direct API write or an MCP server hands the AI the publish button straight to your live CRM, and it is the slow path on top: every record is an API call. There is no diff, no review queue, no rollback. One confident bulk pass rewrites every record at once, can trip the automations watching those fields, and skews any reporting built on the data. By the time you catch the bad edit it is already live, and the original is often gone.
Scratch gives the AI the same access, but against a local copy. The write-back step is pulled out and handed to you. The AI can change anything in the copy; only you commit it, you keep the publish button, and Scratch writes back only the fields you changed. Every published record is reversible on its own, so a pre-pitch cleanup is never a one-way door.
What's safe, and what's locked
Billing rules, time entries, and structural relationships stay put and are never edited. 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. Nothing leaves your machine until you publish. Scratch writes back only the fields you changed, so untouched fields are left exactly as they were, and locked or never-touch fields you flag are stripped before write-back. Every published record is reversible per record, and optional Python validators, which the AI can author, flag edits that break a length cap or touch a field you protected, next to the diff. Scratch is SOC 2 compliant.
Questions Moco teams ask
Will it touch billing rules or time entries?
No. Billing rules, time entries, and structural relationships stay put and are never edited. The AI works only on the prose, the company records and notes, contact bios, and project descriptions and metadata. Scratch also writes back only the fields you changed, so anything you did not touch is left exactly as it was.
Will a bulk pass fire automations or skew reporting?
Edits in the local copy fire nothing and change no report. When you approve a record, Scratch writes it back like any normal update, so an automation watching that field can fire, the same as a manual edit would. The difference is that you choose which records write back, instead of one bulk pass tripping every automation at once.
Is this a good fit for an agency cleaning up before a pitch?
Yes. That is the common case: tighten company records, refresh contact bios, and normalize project descriptions and metadata so the CRM is presentable for a new pitch cycle. The AI reads every record, not the first few hundred, and you review each change as a diff before it writes back.
Can I undo a run after it wrote back to Moco?
Yes. Every written record is reversible from Scratch, per record. Roll back one record or the whole run, and Scratch restores the original for you to publish. A pre-pitch cleanup is never a one-way door.
See it on your own Moco
Pull a few hundred records to feel the loop, then point the agent at the whole CRM.