DOCUMENT OPS

Validate uploaded spreadsheet rows and route fixes back to the owner

Watches a Google Drive folder for new spreadsheets, checks every row against your schema rules.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew spreadsheet added to Drive intake folderGoogle DriveGoogle Drive
  • ActionDownload and parse rowsGoogle DriveGoogle Drive
  • LogicValidate each row against schema rules
  • LogicBranch: clean vs. has errors
  • ActionDM owner the failing rows and reasonsSlack
  • OutputMove flagged file to needs-fixes folderGoogle DriveGoogle Drive

What it does

Whenever a new spreadsheet lands in a shared Drive folder, this workflow reads every row and validates it against a schema you define (required columns, type checks, value ranges, enum membership). If any row fails, the uploader gets a Slack DM listing the precise row numbers and reasons, and the file is moved to a `needs-fixes` subfolder so it never reaches downstream systems dirty.

When to use it

Use it when teammates drop CSVs or sheets into a Drive intake folder and you keep getting malformed data — missing IDs, bad dates, wrong currency formats — that breaks the next step. It puts the fix back on the person who owns the file instead of on you.

How it works

  1. 1A new file in the watched Drive folder triggers the run.
  2. 2The file is downloaded and parsed row by row.
  3. 3Each row is checked against the rule set; failures are collected with row index and reason.
  4. 4A branch decides: clean file proceeds, file with errors is routed to remediation.
  5. 5The owner gets a Slack DM with the failing rows and instructions.
  6. 6The file is moved to the `needs-fixes` folder to quarantine it.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google DriveDocs, sheets, slides, files.
  2. 2
    Connect SlackChannels, DMs, threads, mentions.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.