Call ads.research_pull

See what one competitor is running as ads, longest-running first — 'what ads is our competitor running?', 'what ads is HubSpot running', 'pull up their Facebook ads', 'what are they running on Google?', 'show me their LinkedIn ads', 'what ads are they running on TikTok?'. It looks the competitor up by name in the Meta, Google, LinkedIn or TikTok ad library (the platform the member names; Meta when they name none) and returns their three longest runners: the hook, the format, how long each has run (or the date it was first seen; LinkedIn's library states neither) and a link to it in the library — the ads they keep paying for are the ones working. Each run's ad_id is what ads.pick_reference takes when the member wants one as a reference. This charges the workspace one lookup; a competitor pulled in the last 30 days answers from what we already have and costs nothing unless refresh is set. The ads' pictures are never stored: send the member to each run's link to see one. Not for suggesting which competitors to watch — that is ads.suggest_competitors. Over the API it answers in two calls: without confirmation_id it proposes — says what would happen, returns a confirmation_id and changes, spends and sends nothing; the same arguments again with that confirmation_id, on a member's own API key, do it.

Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.