SOCIAL MEDIA

Repurpose queued videos into A/B hook caption variants

When a video is marked Ready in a Notion content queue, generates two competing hook variants per platform, schedules both at offset times.

CategorySocial Media
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNotion row marked ReadyNotionNotion
  • ActionRead video URL and target platformsNotionNotion
  • ActionGenerate A/B hook caption variantsOpenAI
  • LogicTag variants and assign offset slots
  • ActionSchedule all variantsSocial publishing
  • OutputWrite variant mapping back to NotionNotionNotion

What it does

Monitors a Notion content queue for rows flipped to a Ready status. For each ready video it generates two distinct opening-hook caption variants per platform, schedules them at offset slots so they don't cannibalize each other, and writes the variant assignments back to Notion so you can compare engagement later.

When to use it

Use it when you want to test which framing of a video actually lands instead of guessing. Good for teams running an editorial calendar in Notion who treat captions as experiments rather than one-shots.

How it works

  1. 1A Notion trigger fires when a queue row's status changes to Ready.
  2. 2Read the row's video URL, target platforms, and any angle notes.
  3. 3An OpenAI step writes two contrasting hook variants (A and B) per platform from the supplied context.
  4. 4A logic step assigns each variant an offset schedule slot and tags it A or B.
  5. 5Post-to-Platforms schedules every variant on its destination channel.
  6. 6Update the Notion row with the variant-to-platform-to-time mapping for follow-up analysis.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect NotionPages, databases, comments.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect Social publishingCross-post to X, LinkedIn, Instagram, TikTok, and 4 more in one call.
  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.