Build a Citation Decay Alert System from Comparable Snapshots

A page with few AI citations today may have lost them or may never have had any, and its status cannot say which. Save a dated page snapshot, read it against the citation change the tools compute, and the refresh queue separates confirmed declines from review candidates on its own.

The GEO problem it solves

A low citation count looks like a drop, so the page goes into the refresh queue. But page presence is a current-state view: WORKING, NEEDS_ATTENTION, NOT_CITED and DISCOVERED say how much citation evidence exists now, not how it got there. A refresh booked on status alone can spend writer time on a page nobody ever cited.

One snapshot answers what is cited now; two equivalent snapshots answer what changed. That is also what separates this from measuring a campaign: no intervention, no launch date, no window chosen in advance. It runs on a schedule and asks whether ground you already held is eroding.

How the workflow breaks down

1. Map current citation health. get_page_presence returns monitored and discovered URLs with status, total citations, unique questions, average position and providers. Save URL, citation count, status and date.

2. Compare against your prior snapshot. Re-run on the same monitored set and diff URL by URL against the saved file. The tool carries no history, so the comparison is yours. Without an earlier file the run is a baseline.

3. Read the change the tool computes. get_source_trends compares source domains against the immediately preceding equal-length period and returns, per domain, current mentions, previous mentions and the percent change. Your own domain's row gives the site-level direction, and the third-party domains gaining fastest are displacement candidates. It ranks by current citations, so a collapsed domain can fall out of the rows, and the change is null when the previous period held no citations.

4. Read the surrounding evidence. get_source_urls filtered to your domain shows which pages are cited, get_source_domains the landscape around them, get_content_opportunities the prompts where competitors are mentioned and you are not. All are current views, so a prominent competitor page is a displacement candidate, not a proven replacement.

What a run actually returns

A real first run: 263 pages, 13 cited, and a citation spread of 66, 44, 43, 31, then 6, 5, 5, then a floor of 1 and 0. No previous snapshot existed, so nothing could be called decay.

That is the correct output of run one and why this playbook refuses to rank on it: a page at 1 citation is indistinguishable from a page that fell from 40 until a second snapshot exists. The spread also sets the alert bar. With four pages holding most of the evidence, a drop of 10 on the top row matters and a drop of 1 on the tail is noise, so set the threshold against your own distribution.

What to do with the output

Write only what the diff confirms. A URL enters the refresh queue when two snapshots at least 30 days apart show its citation count falling by half or more, or falling to zero from three or more. Order the queue by the citation count in the older snapshot, highest first: that is what you actually lost. Smaller drops, and anything backed by a single snapshot, go to the watch list and are not written this cycle.

Save every run as a dated snapshot, including the first that compares nothing: on run one the baseline is the deliverable.

Before writing, check whether a queued URL was redirected or renamed since the earlier snapshot: a moved page loses citations without decaying. Preserve cited passages and stable URLs when you edit.

The Complete Prompt

I want to detect citation decay and build a content refresh plan. List the brands I monitor and, if there is more than one, ask which to use. Explain what each step reveals.

1. Pull page presence and group the URLs by current status, with citation counts and providers, and never infer history from a status. Output URL, citation count, status and today's date as a snapshot I can save. If no pages come back, tell me the brand has no monitored pages or no domain set, and stop.
2. Ask whether I have a prior saved snapshot. If I do, compare it URL by URL and list only real movements in count and status. If I do not, say plainly that this run is the baseline and no decay claim is possible yet.
3. Call get_source_trends for the last 30 days. Report my own domain's current mentions, previous mentions and change, then the third-party domains with the largest gains as displacement candidates. Read a null change as no citations in the previous period, not as stability. If my domain is absent from the rows, say so and treat the snapshot diff as the only trend evidence. Then call get_topics and repeat it on the two or three topic IDs I care about most.
4. Pull source URLs filtered to my domain, then source domains, then content opportunities. Name the prominent competitor sources and the prompts where I have room, labelling any replacement or causation as an unconfirmed hypothesis. An empty list is no current evidence, not an improvement.
5. Build the queue. A URL is a confirmed decline only when the two snapshots are at least 30 days apart and its count fell by half or more, or to zero from three or more. Order those by the older snapshot's count, highest first; everything else goes to review candidates or the watch list. Give each entry its evidence and one specific update to test.
6. Ask which queued URLs were redirected, merged or renamed since the earlier snapshot, and drop those from confirmed declines: a moved page loses citations without decaying.