CONTENT CREATION
Generate blog social variants tuned to what performed best, logged to a metrics table
On a new published post, this pulls recent post-performance data, has OpenAI write variants biased toward the styles that performed best, posts them, and logs each variant…
How it runs
The automated pipeline, trigger to output.
- TriggerWebhook fires on newly published postHTTP webhook
- ActionRead recent performance metricsPostgres
- LogicDistill top-performing patterns into prompt guidance
- ActionGenerate weighted variants and cover imageOpenAI
- ActionPublish variants across platformsSocial publishing
- OutputLog variants to metrics tablePostgres
What it does
Makes repurposing learn from itself. When a new blog post is published, the flow first reads historical engagement data from a Postgres metrics table, feeds the top-performing hook and format patterns into the prompt, and generates social variants biased toward what already works. After posting, it logs each variant back to Postgres so the next run is smarter.
When to use it
Use it once you have a few weeks of posting history and want variant generation to compound — favoring the hooks, lengths, and angles your audience actually engages with instead of guessing fresh every time.
How it works
- 1A blog post is published, firing the trigger via webhook.
- 2The flow queries Postgres for recent variant performance metrics.
- 3A logic step distills the top-performing patterns into prompt guidance.
- 4OpenAI generates variants weighted toward those patterns, plus generate-image makes a cover.
- 5post-to-platforms publishes the variants.
- 6Each variant is inserted into the Postgres metrics table for future learning.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect Image generationManaged Nano Banana image renders, metered per image.
- 5Connect Social publishingCross-post to X, LinkedIn, Instagram, TikTok, and 4 more in one call.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Content Creation workflows
Full multi-format snippet pack from one episode
An agent takes a published episode and produces a complete repurposing pack: quote cards, show notes, audiogram scripts, and a thread, organized into a Notion hub page.
Guest recap email draft after episode publish
When an episode publishes, transcribe it, draft a personalized thank-you email to the guest with their best quotes and shareable links, and queue it as a Gmail draft.
Build a Dropbox B-roll library from exported blog drafts
Triggers when a new blog draft file lands in a Dropbox folder, generates a Replicate B-roll clip for each paragraph.
Audiogram script and clip-timestamp builder
From a transcript dropped in Drive, pick three viral-worthy 30-to-60-second segments, write captions and hook text, and post the clip plan to Slack for editors.
Generate B-roll clips when a blog post is marked Ready in Notion
Watches a Notion blog database for posts flipped to 'Ready', splits the body into paragraphs, and generates a short B-roll video clip for each paragraph with Replicate.
Podcast episode to branded quote cards
When a new episode audio file lands in Drive, transcribe it, pull the five most quotable lines, and generate branded quote-card images ready to post.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.