Ask a chat model whether an ad will pass and it answers from memory. Sometimes it names a policy that does not exist. SERP-to-Spend gives the model the actual rules, each one cited, and makes it name the authority behind every finding. When it writes ads, it also works from live Google results.
Illustrative example, not recorded runs. The model, the ad and the question are the same in both rows. Checking an ad adds two things: cited rules in the system prompt and a fixed schema on the way out. Together they give the model the actual rules to cite and put the authority it names in a field you can inspect. They do not establish that the cited rule applies. Generating ads adds a third: live market context (below).
Inside the pipeline
Checking an ad uses the rules only: your ad is the input, judged against cited policy. When you generate ads, the model also gets market context from one source, chosen by what you enter: a competitor URL is fetched, and a keyword uses live Google results through Gemini (or SerpApi where Gemini isn’t set up). With search turned off, the run is labelled as not grounded instead of passing as researched. If the chosen source fails, the run stops with an error.
The rules come from a curated set of FTC, FDA, Meta, Google and TikTok modules. The modules include references to statutes, regulations and published platform policies. The model must answer in fixed fields, so the authority it names is always visible. Structured fields make findings easier to inspect. They do not establish that a cited rule applies; check the source before relying on a finding.
Each module carries the date its content last changed: FTC 2026-10-02 · FDA 2026-06-25 · Meta 2026-10-03 · Google 2026-06-25 · TikTok 2026-06-25. A date shows when the module was last edited, not that every rule in it was re-checked that day.
The Generate ads pipeline
This is the Generate ads flow. Pick a source to see the path a run takes; hover any part for detail. Each run uses one market source, chosen by what you enter and how the site is set up; if it fails, the run stops with an error rather than quietly continuing without it. Checking an ad uses the compliance lane only: your ad is the input.