CONTENT CREATION

Sweep a Sitemap for Stale Pages by Last-Modified Date

Crawls your sitemap on a monthly schedule, flags pages not updated in over a year, scores each for refresh urgency.

CategoryContent Creation
Enginesim
Difficultybeginner
Triggerschedule
Steps6
Setup~5 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMonthly schedule fires
  • ActionMap sitemap and read last-modified datesFirecrawl
  • LogicFlag stale pages and score urgency
  • ActionWrite refresh rationale per pageOpenAI
  • ActionAppend flagged pages to Airtable triage baseAirtableAirtable
  • OutputPost ranked summary to SlackSlack

What it does

It treats your sitemap as the source of truth, finds every page that hasn't been touched in too long, and turns staleness into a ranked monthly triage list — so old content gets reviewed on a cadence instead of being forgotten.

When to use it

Use it when your content backlog is large enough that age alone is a useful first filter. Good for teams without analytics warehousing who still want a recurring, low-effort way to surface refresh candidates.

How it works

  1. 1A monthly schedule triggers the sweep.
  2. 2Firecrawl maps the sitemap and pulls last-modified dates plus metadata for every URL.
  3. 3A logic step flags pages older than a configurable threshold (default 365 days) and computes an urgency score from age and content type.
  4. 4OpenAI writes a one-line refresh rationale for each flagged page.
  5. 5Each flagged page is appended as a row to an Airtable triage base with status, age, and score.
  6. 6A ranked summary of the top candidates is posted to a Slack channel for the content team's monthly 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 AirtableBases, tables, views, automations.
  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.