SOCIAL MEDIA

Weekly: resurface a top-performing post as fresh evergreen threads for approval

On a weekly schedule, pick the best-performing published post from a Postgres analytics table, regenerate updated thread variants.

CategorySocial Media
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires
  • ActionQuery top non-recirculated post from PostgresPostgreSQLPostgres
  • LogicExit if no qualifying post exists
  • ActionRegenerate evergreen X and LinkedIn variantsOpenAI
  • OutputCreate Awaiting Approval cards in TrelloTrelloTrello

What it does

Runs weekly, queries your analytics store for the highest-engagement published post that has not been recirculated recently, and rewrites it into fresh X and LinkedIn thread variants with a new angle. Each variant becomes an Awaiting Approval card in Trello so a marketer can recirculate proven evergreen content without rewriting it.

When to use it

Use it when you have a backlog of strong long-form posts and want a steady cadence of repurposed evergreen threads rather than only posting net-new articles. The weekly cadence keeps the queue full; the Trello gate keeps a human approving.

How it works

  1. 1A weekly schedule triggers the run.
  2. 2Postgres returns the top post by engagement that has not been recirculated in the last N weeks.
  3. 3A logic step confirms a qualifying post exists, else the run exits quietly.
  4. 4OpenAI regenerates X and LinkedIn variants with a fresh hook and updated framing.
  5. 5The variants are created as Awaiting Approval cards in a Trello recirculation list.
  6. 6An operator reviews and moves approved cards to Scheduled.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PostgresAny Postgres URL — query, write, migrate.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect TrelloKanban boards for everything.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.