Google Ads integrationIn development
Rooky reads your Google Ads account and your site, then proposes what to change: ads for pages and products that have none, searches that waste money, budgets in the wrong place. Your own AI provider writes the ads from your real pages. You swipe right to make one live. The integration is in development: it works with Google Ads test accounts now, and with live accounts once Google approves ROOKON's API access.
The problem
New pages and products launch without ads, search terms that never convert keep costing money, and the budget sits with the campaign that converts worst. Fixing it means hours in Google Ads you don't have.
Live demo 1 of 2
A simulated review deck. Ad cards work the same way: the ad as Google shows it, the budget and the numbers behind it. Right makes it live, left skips it.
rookon · acme-cloud · commit requests
Simulated data#128rookon/fix-legacy-billing-interval → main
How Rooky helps
Responsive search ads, keywords and negative keywords written by your own AI provider from the page's content and the searches that already find it. Lines Google would reject never reach a card.
Rooky ranks pages without ads by search demand and visits. Product pages get product ads with the price your page states.
Search terms and keywords that cost money and never converted, ads far below their ad group, and budget shifts toward the campaign that converts. Each card shows spend, clicks, conversions and cost per conversion.
You set a daily budget for new campaigns and a monthly ceiling. ROOKON refuses anything that could go over it, and nothing that spends money happens without your swipe, in any autonomy mode.
Every change can be undone in one tap, is written to the audit log, and is measured like any change ROOKON ships.
Live demo 2 of 2
Every applied ad change is logged, so clicks and conversions are compared before and after. This report is simulated.
rookon · acme-cloud · impact of changes
Simulated dataEach change: 14 days before vs. 14 days after.
12 NovLive
Conversion rate · pages Rooky changed
4.67% → 5.85%
+1.2 pp since Rooky’s first change
Bounce rate · same pages
41.4% → 38.5%
−2.9 pp since Rooky’s first change
Rooky’s changes
2 improved of 3 measured
1 no significant change · 0 worse · 1 collecting
Conversion rate · /billing · 7-day rolling
| Time | conversion rate |
|---|---|
| 14 Sept | 3.1% |
| 15 Sept | 3.1% |
| 16 Sept | 2.7% |
| 17 Sept | 2.5% |
| 18 Sept | 2.5% |
| 19 Sept | 2.4% |
| 20 Sept | 2.5% |
| 21 Sept | 2.8% |
| 22 Sept | 2.7% |
| 23 Sept | 2.7% |
| 24 Sept | 2.9% |
| 25 Sept | 2.9% |
| 26 Sept | 2.9% |
| 27 Sept | 3.0% |
| 28 Sept | 2.9% |
| 29 Sept | 3.2% |
| 30 Sept | 3.5% |
| 1 Oct | 3.4% |
| 2 Oct | 3.6% |
| 3 Oct | 3.7% |
| 4 Oct | 3.5% |
| 5 Oct | 3.6% |
| 6 Oct | 3.5% |
| 7 Oct | 3.4% |
| 8 Oct | 3.7% |
| 9 Oct | 3.3% |
| 10 Oct | 3.1% |
| 11 Oct | 3.5% |
| 12 Oct | 3.8% |
| 13 Oct | 3.9% |
| 14 Oct | 3.7% |
| 15 Oct | 3.2% |
| 16 Oct | 3.6% |
| 17 Oct | 3.9% |
| 18 Oct | 3.9% |
| 19 Oct | 3.7% |
| 20 Oct | 3.7% |
| 21 Oct | 3.8% |
| 22 Oct | 4.4% |
| 23 Oct | 4.6% |
| 24 Oct | 4.5% |
| 25 Oct | 4.3% |
| 26 Oct | 4.3% |
| 27 Oct | 4.3% |
| 28 Oct | 4.4% |
| 29 Oct | 3.9% |
| 30 Oct | 3.7% |
| 31 Oct | 3.6% |
| 1 Nov | 3.7% |
| 2 Nov | 3.8% |
| 3 Nov | 3.7% |
| 4 Nov | 3.7% |
| 5 Nov | 3.8% |
| 6 Nov | 3.7% |
| 7 Nov | 3.7% |
| 8 Nov | 3.6% |
| 9 Nov | 3.7% |
| 10 Nov | 3.6% |
| 11 Nov | 3.7% |
| 12 Nov | 4.1% |
Shaded: baseline and after windows of the selected change.
It was better before
“Release v2.15.0: new onboarding checklist”
Bounce rate +2.6 pp (32.9% → 35.5%)
p < 0.001 (Holm-adjusted) · 14 days before vs. after
Either way, Rooky won’t propose this exact change again. A different approach to the same page is still allowed.
Overlaps with “Release v2.15.0: new onboarding checklist”, so part of the difference may come from that change.
Observed changes between equal windows before and after each change, tested for significance (two-proportion z-test for rates, Welch’s test for durations, Holm-adjusted, p < 0.05). This shows association, not proof of cause: seasonality, campaigns and other releases can contribute, so overlapping changes are flagged.
Sign in with Google and choose the Google Ads account, also through a manager account.
A daily budget for new campaigns, a monthly ceiling, countries and language.
Rooky reads the account and your site, then writes ads with your AI provider.
Right makes it live through the Google Ads API. Left skips it for good.
Rooky tracks what each change did, and Undo is one tap away.
FAQ
It is in development. It works with Google Ads test accounts today. Live accounts follow once Google approves ROOKON's API access, and this page will say so.
No. Nothing that spends money goes live without a person's swipe, in every autonomy mode, and new campaigns can never go over the daily cap and monthly ceiling you set.
Your own AI provider, with your key and within your AI budget. ROOKON sends the page's content and search data, never your Google login or keys.
Only what you approve: new Search campaigns, ads, keywords and negative keywords, pausing a keyword or ad, and moving daily budget between campaigns. Every change can be undone.
Sign up today, connect Search Console and your AI provider, and add Google Ads when it opens for live accounts.