CONTENT CREATION

Supplier photo intake with automated QC and approval routing

Polls a shared Dropbox supplier-upload folder, upscales and cleans each new photo through Replicate, runs automated QC checks.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerScheduled poll of Dropbox /supplier-uploadsDropboxDropbox
  • ActionUpscale image to catalog resolution with ReplicateReplicateReplicate
  • ActionRemove background with ReplicateReplicateReplicate
  • LogicQC branch: validate dimensions and aspect ratio
  • ActionUpload approved assets to Dropbox and log in AirtableDropboxDropbox
  • OutputAlert merchandising in Slack for rejected photosSlack

What it does

Gives suppliers a single drop folder and automatically turns their raw uploads into QC-checked, catalog-spec assets — passing the good ones through and escalating the bad ones so nothing broken reaches your storefront.

When to use it

Use when external suppliers submit product photos of wildly varying quality and you need a gatekeeper that enforces resolution, aspect ratio, and background standards before anything is published.

How it works

  1. 1A scheduled poll checks the Dropbox `/supplier-uploads` folder for new files.
  2. 2Replicate upscales each image to the minimum catalog resolution.
  3. 3Replicate removes the background and returns the cleaned asset.
  4. 4A QC branch validates output dimensions and aspect ratio against catalog rules.
  5. 5Passing assets are uploaded to the Dropbox `/catalog-approved` folder and logged in Airtable as Approved.
  6. 6Failing assets are logged as Rejected with the reason and a Slack alert is sent to the merchandising channel for manual review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect AirtableBases, tables, views, automations.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.