Skip to content

Archive Content Refresh Auditor

Example prompt: "Once a month, look at every published article in our blog Google Sheet that is more than 12 months old. For each one, check whether the page still loads, count any links in the body that now 404, and search the web to see if there is significant news on that topic from the last 6 months. Score each article on whether it is worth refreshing — high if it still gets traffic and the topic has moved on, low if the content is genuinely evergreen. Write the prioritised list to a new tab called 'Refresh Queue' and post the top five candidates in #editorial Slack."

The Problem

Most publications sit on hundreds or thousands of older articles, some still pulling search traffic and some quietly rotting with broken links and stale facts. There is real upside in refreshing the right ones, but auditing the archive by hand is the kind of project that gets scheduled, postponed, and never done. Editors need a way to identify the small set of pieces actually worth rewriting, without spending a week clicking through old URLs.

How GloriaMundo Solves It

We build a monthly workflow that audits the archive and produces a prioritised refresh list. An integration step reads the article inventory from your blog Google Sheet (URL, title, publish date, optional traffic figure). A code step filters to articles older than the chosen threshold. For each one, a URL extract step fetches the page and a code step checks every body link for a live response. A web search step looks for major developments on the topic in the last 6 months. An LLM step weighs traffic, link rot, and topic movement to assign each article a refresh score and a one-line rationale. An integration step writes the ranked queue to a new sheet tab, and the top candidates are posted to Slack. Glass Box preview shows the full table before anything is written.

Example Workflow Steps

  1. Trigger (scheduled): Runs on the first Monday of every month.
  2. Step 1 (integration): Read the article inventory tab from the blog Google Sheet.
  3. Step 2 (code): Filter to articles older than 12 months and chunk into batches.
  4. Step 3 (URL extract): Fetch each article page and capture body links.
  5. Step 4 (code): Check every body link for a 200 response and count failures.
  6. Step 5 (web search): Search for significant developments on each article's topic in the last 6 months.
  7. Step 6 (LLM): Score each article (high, medium, low refresh value) and write a one-line rationale.
  8. Step 7 (integration): Write the prioritised queue to a 'Refresh Queue' tab in the same Google Sheet.
  9. Step 8 (integration): Post the top five refresh candidates to the #editorial Slack channel.

Integrations Used

  • Google Sheets — article inventory in, prioritised refresh queue out
  • Slack — top candidates posted to the editorial channel

Who This Is For

Editorial managers and SEO leads at publications, content marketing teams with several years of accumulated posts, and bloggers running long-running sites who know there is value buried in the archive but cannot justify the audit time.

Time & Cost Saved

A manual archive audit of a few hundred articles typically takes one to two full days of editorial time, which is why it rarely gets done at all. This workflow runs unattended overnight and produces a defensible prioritised list, reducing the human task to roughly an hour of reviewing the top candidates each month. The credit cost scales with archive size and is dominated by URL extracts and web searches.