You point AdWhispr at a brand or a niche and it hands back the ads that have stayed live the longest, sorted so the survivors sit at the top. It never guesses spend or invents a click rate. The one signal it trusts is longevity, because an ad a brand keeps paying to run week after week is an ad that is earning its keep. Everything else on the page is a distraction from that one honest fact.
Use this when
You want a shortlist of proven ideas fast, before writing a brief or planning a shoot. It is the right move when you are entering a category and want to know what has already survived, or when you have one competitor in mind and want their durable winners rather than their whole library.
Do not use this when you need the two brands compared side by side; for that, use the Head-to-Head Brand Comparison skill. And do not use it to grade your own account; this reads public ad-library data only.
What you need
- A brand or page name, or a keyword or niche to search across, as it appears in the Meta Ad Library.
- AdWhispr connected to your AI client. The one-time setup is in the box at the top of this page. No ad account of your own is needed for read-only research.
- The market, if it matters, since the ad library is region aware and results differ by country.
How it runs
- Confirm the target with the user: a specific brand, or a keyword and niche, plus the market if it is region sensitive.
- Pull the matching ads from the tracked library and read each one's first-seen and last-seen dates.
- Rank every ad by days running, longest first, so the survivors rise to the top on their own.
- Attach the days-running figure to each ad, along with its hook, format, and offer, so the shortlist is readable, not just ordered.
- Hand back the top survivors with a short note on what the longest-lived ads have in common.
What the skill checks
- Every ad's status and dates are read fresh from the tracked library, never carried over from an earlier session, because a brand can pause a long-runner mid-week.
- No spend, CTR, ROAS, or impression figure is stated. Days running is the only performance quantity here, and none of the others can be seen.
- The market filter is confirmed before concluding a brand has "no long-runners," since an empty result under the wrong region is a false negative, not a finding.
- A recent launch is not mistaken for a winner; a low days-running count is reported as young, not as proven.
When it stops
- Done: a longevity-ranked shortlist with days-running attached to each ad and a note on shared patterns.
- Nothing to report: the brand or niche has no ads in the requested market right now, which is reported plainly with the date.
- Blocked: the brand or keyword does not resolve to any advertiser after reasonable variants are tried, so the skill asks you for the exact name or URL rather than guessing.
What it will and won't do
Read only. This skill reads the public ad library and returns a ranked list. It never touches an ad account, never spends, and never contacts anyone. Cloning a winner or launching against it is a separate skill with its own approval step.
What you get
A ranked list of the longest-running ads for the brand or niche, each with its days-running count, hook, format, and offer, plus a short read on the patterns the survivors share. No spend estimates, no invented scores, no ranking by anything other than how long each ad has actually stayed live.
FAQ
How do you find the best performing Facebook ads without spend data?
By how long each ad has been running. Brands cut ads that lose money and keep the ones that pay, so an ad still live after months is the closest honest signal to a winner. AdWhispr tracks every ad's first- and last-seen dates daily and ranks by that, instead of inventing a CTR or ROAS it cannot see.
Can I find winning ads across a whole niche, not just one brand?
Yes. Search by keyword or category and the skill ranks the matching ads across brands by longevity, so you see the durable ideas in the space rather than one advertiser's library.
Does a longer-running ad always mean a better ad?
It means the brand has chosen to keep paying for it, which is the strongest public signal there is. It is a proxy, not proof, so the skill reports days running as a fact and leaves the judgment to you.
Does this touch my ad account?
No. It reads public ad-library data and returns a list. Your own account is never queried by this skill.