Closed-loop Google Ads optimization engine

Problem

I inherited campaigns where only 5% of ad-driven phone calls were qualified leads. Google's bidding was optimizing on call volume, which meant it was optimizing on noise. The truth about each call lived in its transcript, not in the ad platform, so no off-the-shelf tool could close the loop. The engine was built to replace the bidding signal with verified outcomes and then to act on that signal every night without me.

Architecture

One nightly cycle, scheduled by launchd with missed-run recovery, in this order:

1. Snapshot performanceCampaign and keyword metrics pulled across all 8 accounts via GAQL.
2. Classify every new callTranscripts pulled from the call-tracking API and classified by the Claude API as qualified lead, applicant, existing client, or cannot service, with a cache to hold cost near $0.03 per call.
3. Attribute leads to keywordsA custom attribution engine joins each call to the campaign and keyword that produced it. 124K attribution rows to date.
4. Upload offline conversionsQualified leads are uploaded to Google Ads as call conversions, with an alert if the pipeline stalls. 4,449 uploaded. Along the way I found that click-conversion uploads do not attribute for call ads, a quiet API behavior that would have invalidated the whole loop.
5. Grade campaigns and keywordsEvery campaign and keyword graded A through F against qualified-lead truth, not against Google's reported conversions.
6. Mine waste patternsCannot-service transcripts are mined for recurring waste and converted into negative keywords, with location-aware compliance exceptions.
7. Generate and execute the action queueBudget-aware, deduplicated, risk-tiered. Low-risk actions execute automatically. Medium and high wait for approval.
8. Detect anomalies and failuresPer-campaign z-score deviation against 30-day baselines, zero-spend detection, bid-strategy phase checks, and self-monitoring that alerts when the engine itself is broken.
9. ReportA prioritized email with a triaged subject line, from critical down to all clear with the count of optimizations applied.

Weekly, the engine also drafts new campaign proposals with ad groups, keywords, and budget sizing, and checks for experiment learnings that have not been applied.

Controls that let it spend real money

• Dry run by default. Every mutation class runs in dry-run mode unless explicitly confirmed.
• Risk tiers. Eight action types across high, medium, and low. Only low risk auto-executes, under budget caps and protected-keyword whitelists.
• Paused-by-default creation. New campaigns pass a single validation gateway, are created paused, receive baseline negatives, and are verified against live API state before registration.
• Rollback on every mutation class. Full state tracking with orphan detection.
• Never assume success. After a self-audit found a dedup bug that had silently discarded approved optimizations and conversion uploads that had failed without error, every API mutation is now verified against its response, and failures have a permanent taxonomy.
• Statistically honest scoring. A failing keyword grade requires a 60-day window, a 30-click minimum, and 90-day confirmation, because low-volume keywords that converted every few weeks were being falsely flagged.
• Bid-strategy phases require two signals. Moving from capped-CPC launch to maximize-conversions to target-CPA requires both Google-reported conversions and verified qualified leads, so the engine cannot optimize toward junk calls.

Evaluation

• 38 controlled A/B experiments in a custom framework, with a knowledge base that stops failed ideas from being re-tested.
• A head-to-head benchmark against an external agency across 4 locations, using audit scripts that compare the engine's performance to the agency's on equal footing.
• z-score anomaly detection against 30-day baselines on every campaign.
• Live-CPL reports always query the source APIs. Financials are never reported from cached snapshots.

Numbers

Built on the same data

• Call-scoring and coaching product. An eight-rule rubric applied by the Claude API to every qualified call at about $0.03 per call, a director review workflow with transcript evidence and a dispute path, red-flag escalation, and a cross-office roll-up. Requirements gathered from the operating client, pilot location moved on their input, live training delivered to directors across 7 locations.
• Multi-tenant attribution dashboard. Franchise directors close the loop from lead to revenue. Own page.
• Executive reporting. Automated weekly reports with Plotly charts and Excel workbooks, delivered as Outlook drafts through Microsoft Graph for human review. 18+ weekly executive reports to the C-suite.
• Distribution. An enterprise software vendor building for the same sector, after a full year of monthly product reviews in which I resolved their Google Ads API blockers, is preparing to distribute the optimization engine and the call-scoring product to its customers.