Skip to content
Docs

Check cadence

RankX AI runs scheduled checks every night on the cadence you choose, daily to monthly, held to your plan's floor or a seven-day floor during the trial.

Check cadence is how often RankX AI repeats a check: daily, every three days, weekly, fortnightly or monthly. RankX AI looks every night for checks that are due and runs only those, so nothing runs nightly unless you set it to.

Each cadence is raised to a floor. Two floors apply and the slower one wins: your plan's floor, and a seven-day floor while your account is on trial. Cadence is also where most of your credit spend is decided, because every recurring check is a per-unit charge multiplied by how often it runs.

What does RankX AI check on a schedule?

RankX AI schedules four check families, and each has its own cadence setting and its own floor.

FamilyWhat it checksCharged perNightly pass (UTC)
AI visibilityEvery active prompt that is due, on the assistants it targetsPrompt, assistant, run22:00
Rank trackingEvery tracked keyword, with AI Overview captureKeyword, check23:00
AI ShoppingEvery shopping prompt, on both surfacesPrompt, surface, run21:00
Website AuditA crawl of the sitePage crawledEvery six hours

The three nightly passes run in that order so they do not compete with each other. Settings, Automation shows each family's cadence, its live credit estimate and when the next check is due.

Can each prompt have its own cadence?

Yes. AI visibility is set per Website and then per prompt, and the per-prompt setting is the one most accounts should use. The other three families are set per Website.

Every tracked prompt carries two settings of its own, both of which start out following the Website:

SettingWhat you can chooseDefault
ScheduleDaily, every three days, weekly, fortnightly or monthlyUse the Website default
AssistantsAny of the assistants the Website has switched onUse the Website's list

So one prompt can run on ChatGPT every night while another runs on Perplexity once a week. The effective cadence is the slower of the prompt's choice and the floor, and a prompt's assistant list can only narrow the Website's, never widen it.

This is the control worth reaching for first. Pausing the prompts you do not act on and slowing the ones that do not need daily watching changes the bill more than anything else on this page. See AI Prompts.

What are the two cadence floors?

Your plan's floor is the fastest cadence the plan allows. On most plans and most families that is one day; the entry plan on each track checks rankings and runs audits less often. The per-plan figures are in plans and limits.

A seven-day floor applies while your account is on trial, on every plan and every family. A daily sweep of a full prompt list would use the whole trial grant within days, so seven days buys what matters most: a first measurement and a scheduled re-check that shows real movement. See the free trial.

The slower floor wins, and your plan's floor applies again the moment you subscribe.

A slower cadence is always allowed. A floor is a lower bound on the interval between checks, not a target. Checking less often than the floor is the right answer for many Websites.

How does cadence turn into credits?

Recurring spend is almost entirely three multiplications:

FamilyCharged checks per month
AI visibilityFor each prompt: assistants it targets x runs per month
Rank trackingKeywords x checks per month
AI ShoppingShopping prompts x 2 surfaces x runs per month

Twenty-five prompts on ChatGPT alone, checked daily, is 750 charged checks a month. With four assistants switched on, the same panel checked daily is 3,000, and checked weekly about 430. A mixed panel on four assistants, with five prompts on two of them daily and twenty on all four weekly, is about 650 charged checks a month.

Match cadence to plan first. Each plan's monthly credit grant is sized for a cadence that answers real questions, not for the fastest cadence on a full prompt list. That is why the floors exist as floors rather than as defaults.

Prices per check are in the credit cost reference.

How do I choose the right cadence?

Ask what decision the data changes. If a position moving today would change what you do today, check daily. If you review monthly, a daily check costs 30 times as much as a measurement you look at once.

AI visibility is noisy at any cadence. AI assistants are non-deterministic, and two runs of the same prompt often name different brands. A weekly rate across a wider panel is a better measurement than a daily rate on a small one.

Rank tracking rewards frequency more, because a Google position is a much steadier measurement than an AI answer. If you want to spend on speed, spend it here.

Audits reward it least. A site rarely changes technically from one day to the next unless you changed it, so run an audit after a change and on a slow schedule otherwise.

Prune before you speed up. Halving a prompt panel and doubling its cadence costs the same and measures better, because a smaller panel of prompts you care about beats a larger one you scroll past.

Can I run a check outside the schedule?

Yes. You can run a check at any time for one prompt, one keyword or a whole panel. A manual check is charged exactly as a scheduled one, and its cost is shown before you run it.

A manual check ignores the cadence, because you asked for it, and it still honours the prompt's assistant list.

The floor governs the schedule, not your ability to ask. An account on trial can still check something now; it just does not get a daily automatic sweep. A manual check is most useful after a real change to your site or content.

What happens when a scheduled run is interrupted?

RankX AI keeps what a run completed and never reports unchecked items as absences. An AI visibility run that reaches its time limit records what it finished, marks itself partial, and dispatches the remainder rather than starting again. Rank tracking puts the keywords it did not reach first in the queue for the next run.

If the credit balance runs out mid-run, the run stops and says so. Prompts it never reached are not recorded as "not mentioned".

Every skipped keyword shows why. A tracked keyword that missed a scheduled check is labelled with the reason: the balance ran out, the check failed and will be retried, or the run reached its time limit and the keyword is queued for the next one.

Where to go next

Questions

Can I check one prompt daily and the rest weekly?

Yes. Every AI visibility prompt has its own schedule and its own assistant list, so one prompt can run daily on ChatGPT while the rest run weekly on every assistant you have switched on. See AI Prompts.

Why can I not choose a daily cadence during the free trial?

Scheduled checks run at most every seven days while an account is on trial, so the trial credits pay for a first measurement and a re-check. You can still run a manual check at any time, and your plan's own floor applies as soon as you subscribe.

Does a manual check cost more than a scheduled one?

No. A manual check is charged at exactly the same rate as a scheduled one and uses the prompt's own assistant list. Prices are in the credit cost reference.

What time do scheduled checks run?

RankX AI runs three passes each night in UTC: AI Shopping at 21:00, AI visibility at 22:00 and rank tracking at 23:00. Website Audits are picked up every six hours. The Automation settings for each Website show when the next check is due.

Last updated

Cookie settings

Choose which cookies we can use. You can change this at any time from “Cookie settings” in the footer.

Essential

Security, bot protection and remembering your choice. The site needs them to run, and they do not identify you. Always on.

Google Analytics cookies that tell us which pages are read and which links are followed, so we can improve them. Off until you switch it on.

Tells advertisers when their advert led to your visit. Includes the Meta (Facebook) pixel and the LinkedIn Insight Tag, which set cookies on this domain (LinkedIn also on linkedin.com) and can be told if you later start a trial.

More in the cookie policy and the privacy policy.