CONTENT CREATION

Check Refresh History the Moment a URL Is Submitted

A webhook accepts a single URL, instantly crawls it, checks its trailing traffic trend, and returns a go/no-go refresh recommendation with a starter brief if the page is decaying.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerwebhook
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWebhook receives a URLHTTP webhook
  • ActionLook up trailing traffic trendPostgreSQLPostgres
  • LogicClassify healthy / watch / decaying
  • ActionScrape live page if decayingFirecrawl
  • ActionGenerate verdict and starter briefOpenAI
  • OutputReturn verdict JSON to callerHTTP webhook

What it does

It gives writers and editors an on-demand verdict for any one page: paste a URL, and within seconds get whether the page is decaying, by how much, and a ready-to-use refresh brief if it warrants one — no waiting for the next scheduled audit.

When to use it

Use it for ad-hoc checks during editorial standups, content sprints, or when triaging a page someone flagged. It fits anywhere you want an instant, single-page answer instead of running the full weekly sweep.

How it works

  1. 1An incoming webhook receives a URL (and optional target keyword).
  2. 2A Postgres lookup fetches the page's trailing traffic trend.
  3. 3A logic step classifies the page as healthy, watch, or decaying based on the trend thresholds.
  4. 4If decaying, Firecrawl scrapes the live page content.
  5. 5OpenAI generates a verdict plus a starter refresh brief for decaying pages, or a short "no action" note otherwise.
  6. 6The webhook responds with the verdict JSON, so the caller (a Slack shortcut, internal tool, or form) shows the result immediately.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect FirecrawlCrawl, scrape, structured extract.
  4. 4
    Connect OpenAIModels, embeddings, files.
  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.