CONTENT CREATION

Evergreen Post Refresh: Source-Update Cascade Rewrite

When a watched authoritative source publishes a new figure, finds every post that cites it, rewrites the affected passages with the updated number.

CategoryContent Creation
Enginesim
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSchedule re-checks watched sources
  • ActionScrape source and detect figure changes (LLM)Firecrawl
  • LogicStop if no source figure changed
  • ActionFind all repo files citing the sourceGitHubGitHub
  • ActionRewrite affected passages with new figure (LLM)OpenAI
  • OutputOpen GitHub pull request with all editsGitHubGitHub

What it does

Flips the refresh model: instead of auditing posts, it watches the sources. When a tracked authority (an industry report, a pricing page, a government dataset) updates a number, the workflow cascades that change into every article that cites it and proposes the edits as one reviewable pull request.

When to use it

Many of your evergreen posts lean on a handful of canonical sources. When one of those sources updates, you want the change propagated everywhere at once — not rediscovered post by post months later.

How it works

  1. 1A schedule re-checks each watched source page.
  2. 2Firecrawl scrapes the source and an LLM detects whether its key figure changed.
  3. 3A logic step stops the run if no source changed.
  4. 4Search the content repo for all markdown files citing the changed source.
  5. 5The LLM rewrites each affected passage with the new figure and updated date.
  6. 6Open a GitHub pull request bundling every edited file for editorial review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect FirecrawlCrawl, scrape, structured extract.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect GitHubRepos, issues, pull requests, actions.
  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.