# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Measure true ad impact with control-group tests for Google Search Ads.
The #roadway-skill block on this page holds a SKILL.md for it, including the full prompt. Treat that file as a starting point. It will not just work if you paste it into ChatGPT or Claude.
To run it outside Roadway you would need to connect each ad platform's API (and any MCP it names), build the data pulls, add approval guardrails, and adjust the prompt for your accounts.
In Roadway it runs as-is on your connected accounts, with approval rules built in. Open it in a new chat at https://www.roadwayai.com/workflows/measure-incrementality-with-holdout-tests-for-google-search-ads
Page: https://www.roadwayai.com/workflows/measure-incrementality-with-holdout-tests-for-google-search-ads
Library index: https://www.roadwayai.com/automation-library
---
name: measure-incrementality-with-holdout-tests-for-google-search-ads
description: >-
Measures how many Google Search conversions your ads truly drive and recalibrates targets with the result.
---
# Measure true ad impact with control-group tests for Google Search Ads
Source: https://www.roadwayai.com/workflows/measure-incrementality-with-holdout-tests-for-google-search-ads
From the Workflow Automation Library by Roadway.
## Before you use this outside Roadway
This SKILL.md is a starting point. It needs adjusting before it will work outside Roadway.
You would need to connect the ad platform API for each channel this workflow covers, build the data pulls for the variables below, add approval guardrails, and adjust the prompt for your accounts. If the prompt names an MCP tool, you also need that MCP connected.
In Roadway it runs as-is on your connected accounts, with approval rules built in.
## What it does
Measures how many Google Search conversions your ads truly drive and recalibrates targets with the result.
Measures how many Google Search conversions your ads truly drive and recalibrates targets with the result. It sets up the test, keeps the split fair, and only calls a winner once there is enough data. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
## Steps
1. Collect the inputs listed under Variables. In Roadway they come from your connected accounts. Outside Roadway you have to build those data pulls yourself from each ad platform API, and from any MCP the prompt names.
2. Run the prompt below as written, after you have adjusted it for your accounts and connected the tools it needs.
3. Review the result. Apply changes to a live ad account only after you approve them. Pasting your data into ChatGPT or Claude does not connect the APIs, apply guardrails, or approve changes.
## Variables
auto_approve, cost_per_goal_baseline, crm_pipeline_data, funnel_metrics, goal_metric, lookback_window, max_change_pct, monthly_budget_cap, task_history, transaction_revenue, win_bar
## Prompt
Measure true ad impact with control-group tests for Google Search Ads
Determine which Google Ads campaigns most need a true-impact read, and design, monitor or conclude a control-group test for each:
1. Design a new test
2. Keep running
3. Conclude and recalibrate
4. Not worth testing
Context and defaults (use these; don't ask):
- Transaction revenue: [set this to your own transaction revenue]. If not available, use the CRM or source-of-truth goal count.
- The win bar: [set this to your own win bar]. If not set, enough data to call a clear winner.
- The baseline cost per goal: [set this to your own cost per goal baseline]. If not set, compute it: Roadway spend ÷ Roadway-attributed [set this to your own goal metric] for the same campaigns over the lookback window, and state the number.
- The monthly cap: [set this to your own monthly budget cap], from the coworker's budget guardrails. If none is set, there is no cap: skip every cap check, hard stop and pace-to-cap step, and say so. Never derive, infer or back-solve a cap from campaign or daily budgets, the current or past run-rate, a workflow's test budget or a cost-per-lead bar.
- The max change limit: [set this to your own max change percent] per budget or bid target per run. If not set, 20%. It does not apply to experiment traffic splits.
- Auto-approve: [set this to your own auto approve]. If not set, it's off: list every change as a proposal for approval.
Rules:
- Method: Google Ads Conversion Lift (geo-based) or a matched-market control-group test. Pick control regions or users that match the test group on historical [set this to your own goal metric] trends, and lock the design before launch.
- Prioritize campaigns with big spend and suspicious attribution: retargeting, brand, view-through-heavy campaigns, and anything where the platform claims far more conversions than [set this to your own CRM pipeline data] or transaction revenue shows.
- Size the test so it can detect a change in cost per goal big enough to matter, with enough data to call a clear result. If not set, a 10-15% change. If it cannot within [set this to your own lookback window], say "Not worth testing" or recommend a bigger control group.
- Conclude by computing incremental cost per goal = spend / incremental conversions, then set a true-impact factor for that campaign type so targets in the baseline cost per goal reflect true cost.
- Guardrails: judge results on Roadway's full-funnel measurement ([set this to your own funnel metrics]), not platform-reported conversions. Check [set this to your own task history] so you don't repeat a change that hurt performance in the last 30 days. Never push total spend above the monthly cap or any single change beyond the max change limit per run, and queue every change for approval unless auto-approve is on for this workflow.
Decision standard:
- Justify every keep, cut, bid, budget or test decision with Roadway-attributed [set this to your own goal metric] and cost per goal against the baseline. Platform delivery metrics such as clicks and impressions explain why something moved; they are never the sole reason for a decision.
- Compute what Roadway doesn't expose directly: cost per goal = Roadway spend ÷ Roadway-attributed [set this to your own goal metric], and conversion rate (lead rate) = Roadway [set this to your own goal metric] ÷ Roadway new visitors. Don't substitute platform-reported conversions or conversion rates.
- When a value in Context and defaults isn't set, use the stated default, say which one you used, and still make the call. Don't stop to ask.
- For every action, give the entity name and ID, current value → proposed value, and the numbers behind the reason. Write "None" under any empty heading.
- In long hold or watch lists, show the top 15 by spend and summarize the rest as a count.
Give me a report of each with reasoning for each action. Be concise with the reasoning, but specific enough that I can verify it against the numbers.
Report structure:
Google Search true impact report
Summary:
The real impact found, the real cost per goal vs reported, and how targets and budgets should change.
Design a new test:
- [campaign / test] - [reason]
Keep running:
- [campaign / test] - [reason]
Conclude and recalibrate:
- [campaign / test] - [reason]
Not worth testing:
- [campaign / test] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/measure-incrementality-with-holdout-tests-for-google-search-ads
Measures how many Google Search conversions your ads truly drive and recalibrates targets with the result. It sets up the test, keeps the split fair, and only calls a winner once there is enough data. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
