CONTENT CREATION

Weekly hero-image batch from a Postgres product table with review digest

On a weekly schedule, queries the product table for SKUs missing hero art, generates and brand-checks images with Replicate, archives them to S3.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule starts the batch
  • ActionQuery Postgres for SKUs missing approved hero artPostgreSQLPostgres
  • ActionRender hero image per SKU with ReplicateReplicateReplicate
  • LogicBrand-consistency check; mark each pass or fail
  • ActionArchive approved images to S3 and update Postgres rowsAWS S3
  • OutputSend pass/fail review digest to SlackSlack

What it does

Runs a steady weekly cadence so the catalog never falls behind on hero art. It queries Postgres for products without an approved image, generates and reviews each one, archives the approved files, and reports a single digest summarizing pass rates and the items still needing a person.

When to use it

Use it when product data lives in your own database and you want hands-off weekly coverage with a clear accountability report. Ideal for ops teams that prefer a scheduled batch plus one summary over real-time per-item noise.

How it works

  1. 1A weekly schedule starts the run.
  2. 2Postgres is queried for SKUs with no approved hero image.
  3. 3Replicate renders a hero image for each missing SKU.
  4. 4A brand-consistency check scores every render and marks pass or fail.
  5. 5Approved images are archived to S3 and the Postgres row is updated with the link and status.
  6. 6A Slack digest summarizes counts, pass rate, and the list of SKUs flagged for human review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PostgresAny Postgres URL — query, write, migrate.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect AWS S3Buckets, objects, signed URLs.
  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.