SOCIAL MEDIA

Propose recycled evergreen posts to Slack for one-tap approval

Surfaces a recycled variant of a top older post to a Slack channel for human approval, then publishes only the ones your team greenlights.

CategorySocial Media
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerRecycling cadence schedule
  • ActionPick top evergreen candidateAirtableAirtable
  • ActionDraft variant and relevance noteOpenAI
  • ActionPost proposal to Slack for approvalSlack
  • LogicApproved or skipped?
  • OutputPublish approved variantSocial publishing

What it does

Adds a human checkpoint to evergreen recycling. On a schedule, it selects a high-performing older post from your Airtable archive, generates a refreshed variant with OpenAI, and posts the proposed copy to a Slack channel. A reviewer approves or skips it. Approved variants go live on your social channels; skipped ones are logged so they aren't proposed again immediately.

When to use it

Use it when brand voice matters and you don't want fully automated reposting. Great for teams that like the time savings of recycling but want eyes on every variant before it ships.

How it works

  1. 1A schedule trigger runs on your recycling cadence (e.g. weekday mornings).
  2. 2The flow pulls a top evergreen candidate from Airtable that hasn't been reused recently.
  3. 3OpenAI drafts a fresh variant and a one-line rationale for why it's still relevant.
  4. 4The proposal is posted to Slack with Approve and Skip options.
  5. 5On approval, the variant is published via post-to-platforms; on skip, it's noted.
  6. 6Airtable records the outcome and the recycle date for the chosen post.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect Social publishingCross-post to X, LinkedIn, Instagram, TikTok, and 4 more in one call.
  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.