CONTENT CREATION

Agent-driven bulk refresh of an aging product catalog

On request, an agent audits the Airtable catalog for low-quality or outdated photos, upscales and re-cleans the worst offenders through Replicate.

CategoryContent Creation
Enginepaperclip
Difficultyadvanced
Triggermanual
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerTeam member starts catalog refresh with scope
  • ActionRead and score catalog photos in AirtableAirtableAirtable
  • LogicSelect lowest-scoring images in scope
  • ActionUpscale and clean selected images via ReplicateReplicateReplicate
  • ActionStore assets in R2 and update Airtable rowsCloudflareCloudflare R2
  • OutputPost before/after summary to SlackSlack

What it does

Drives a one-off catalog cleanup as an agent task rather than a fixed pipeline. The agent reviews the catalog, decides which photos most need rework using quality signals, re-processes them through Replicate, and writes back a human-readable summary of what it changed and why.

When to use it

Use it for periodic catalog hygiene, such as before a big sale or after inheriting a messy product set, when you want judgment about which images to touch rather than blindly reprocessing everything.

How it works

  1. 1A team member kicks off the run with a target scope (a collection or the whole catalog).
  2. 2The agent reads catalog rows from Airtable and scores each photo for resolution and background cleanliness.
  3. 3It selects the lowest-scoring images within the requested scope.
  4. 4Each selected image is upscaled and background-cleaned via Replicate and stored in R2.
  5. 5The agent updates each Airtable row with the new asset and a note on what it improved.
  6. 6A summary of items touched, skipped, and improved is posted to Slack.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect Cloudflare R2Object storage, S3-compatible.
  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.