Ad Creative-Angle Analyzer — CTA, Offer, Hook, Emotional Triggers

Turn ad copy — from any Ad Library scraper's output or pasted raw text — into one structured marketing-analysis record:

Field	Example
cta_type	shop / signup / learn_more / download / book / contact / subscribe / apply / watch
offer_type, offer_detail	discount_percent, "20% off"
hook_style	question / statistic / testimonial / problem / bold_claim / plain
emotional_triggers	["urgency", "social_proof"]
primary_angle	the single dominant trigger, or benefit_led
urgency_score	0..1

Why this exists

Ad Library scrapers (Meta, TikTok, Google) hand you the raw ad copy but not the strategy behind it. This actor is the enrichment layer: feed it any ad record you already have and get back the marketing angle — which CTA family it uses, what kind of offer, how it opens, which psychological triggers it leans on. Pair it with meta-ads-library-scraper (or any competitor's output): scrape → analyze → build a swipe file of what's actually working.

Zero new access: this actor never makes a network request. It is pure text analysis, so it never rate-limits, never breaks on a site redesign, and never needs a proxy.

Input

{
  "adItems": [
    {
      "ad_archive_id": "123456",
      "page_name": "Acme Fitness",
      "ad_creative_bodies": ["Only 3 spots left! Join 10,000+ members who transformed in 90 days. Sign up now."],
      "cta_text": "Sign Up",
      "link_url": "https://acmefitness.com/offer"
    }
  ],
  "adTexts": [
    "What nobody tells you about home workouts... 30% off your first month, today only."
  ]
}

• adItems — structured ad records. A meta-ads-library-scraper row works directly (ad_creative_bodies, cta_text, ad_creative_link_titles, ad_creative_link_descriptions, page_name, ad_archive_id, link_url); a simpler custom shape (body/cta/pageName/...) is also recognized.
• adTexts — raw ad copy strings, when you don't have structured fields.
• maxItems — safety cap (default 1000).

Output

One record per ad with the fields above plus trigger_hits (category → match count), social_proof_present, scarcity_present, fields_extracted and parse_confidence.

Pricing

Per-result (ad-angle-analyzed event) — pay only for ads actually analyzed.

Usage statistics

This Actor creates a small, content-free summary at the end of each run. It is used only to monitor reliability and improve this Actor. A copy is saved as USAGE_STATS in your own Apify key-value store, so you can see the exact record created for your run.

Set disableUsageStats to true in the input to opt out. Nothing is sent then; your USAGE_STATS record only says that statistics were disabled.

Only these fields are recorded:

• schema version, Actor name and build number;
• UTC start and finish hour (not a precise timestamp);
• run duration, number of results and time to the first result, each as a coarse range;
• whether the result was empty, the end status, and an error type from a fixed list;
• memory setting and counts of charged events;
• names of the input fields you set, never their values;
• the selected option for input fields that offer a fixed list of choices (for example a sort order).

We do not collect input text, search terms, URLs, domains, usernames, email addresses, names, proxy credentials, tokens, scraped records, output items, raw error messages, stack traces, or hashes of any of those values. Records are kept for no longer than 13 months, used only as aggregated operational statistics, and never sold or shared.

Additional fields (Phase 2)

This Actor also records your Apify user ID, whether Apify marks the account as paying, the size range of list inputs, the selected country when the input offers a fixed list of countries, and one category from a fixed Actor taxonomy. We use these fields only for aggregate reliability, repeat-use and cross-Actor analysis; reports suppress any cell with fewer than five distinct users.

The same disableUsageStats: true input flag turns these fields off too. The user ID is removed after 13 months; we do not export, sell, share, or attempt to re-identify this data.

Run-outcome signals (v2)

To learn whether a run did what it was asked to do, the record also holds a few more coarse ranges and yes/no flags. None of them contains content:

• the result limit you asked for (a range, when the input has one) and what share of it was delivered;
• results delivered per input item you listed (a range);
• output quality as ranges: how fully the result fields were filled, the share of rows that look like errors, the share of duplicate rows, and how many different fields appeared. These are counted in memory while results are saved; no result content is kept;
• how the run was started (console, API, schedule, webhook, another Actor);
• how it ended: stopped by you, timed out, reached the requested limit, stopped by the charge limit, and how many times the platform moved the run;
• if this Actor reports it: how many items to process worked or failed (ranges) and one failure reason from a fixed list;
• a short code made from the names of the input fields you set, never their values.

Repeat-run fingerprint (v2)

When your Apify user ID is recorded (see above), the record also holds an 8-character one-way code made from your input (proxy settings left out) and this Actor's name. It only lets us see that the same account ran the same input again soon after an unsatisfying run; we never see the input itself. It is stored only in the database, never published, and reports use it in aggregate with the same five-user minimum. It is the one exception to the statement above that no hashes are collected, and disableUsageStats: true turns it off.