CONTENT CREATION

Evergreen Post Refresh: Quarterly Stat-Decay Triage to Slack

Each quarter, scores every published post for stat decay and sends a ranked Slack digest of which articles need updating, with the specific outdated numbers called out.

CategoryContent Creation
Enginesim
Difficultybeginner
Triggerschedule
Steps6
Setup~5 min

How it runs

The automated pipeline, trigger to output.

  • TriggerQuarterly schedule fires
  • ActionRead post list and traffic from AirtableAirtableAirtable
  • ActionExtract key statistics per post (LLM)OpenAI
  • ActionPull current source valuesFirecrawl
  • LogicScore decay severity weighted by traffic
  • OutputPost ranked refresh-needed digest to SlackSlack

What it does

Gives a content team a prioritized to-do list instead of silent edits. It reads your post catalog, checks each statistic against live data, and produces a Slack report ranked by how stale and how high-traffic each post is — so editors spend their refresh time where it matters most.

When to use it

You have too many evergreen posts to rewrite blindly and want a human in the loop. This is the triage layer: it tells you what's decayed and by how much, but leaves the editorial decision and rewrite to your team.

How it works

  1. 1A quarterly schedule starts the audit.
  2. 2Read the published-post list and traffic metrics from Airtable.
  3. 3An LLM extracts each post's key statistics.
  4. 4Firecrawl pulls the current value for each cited source.
  5. 5A logic step scores decay severity and weights it by traffic.
  6. 6Posts above the threshold are sorted into a ranked digest.
  7. 7Post the digest to a Slack channel with per-post stale-stat callouts and links.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect FirecrawlCrawl, scrape, structured extract.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  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.