# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Detect attribution drift between platforms and Roadway.
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/detect-attribution-drift-between-platforms-and-roadway
Page: https://www.roadwayai.com/workflows/detect-attribution-drift-between-platforms-and-roadway
Library index: https://www.roadwayai.com/automation-library
---
name: detect-attribution-drift-between-platforms-and-roadway
description: >-
Alerts when a platform's reported conversions start drifting away from CRM or backend truth, which usually means a tracking or modeling change.
---
# Detect attribution drift between platforms and Roadway
Source: https://www.roadwayai.com/workflows/detect-attribution-drift-between-platforms-and-roadway
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
Alerts when a platform's reported conversions start drifting away from CRM or backend truth, which usually means a tracking or modeling change.
Alerts when a platform's reported conversions start drifting away from CRM or backend truth, which usually means a tracking or modeling change. It keeps an eye on your live account and flags anything unusual early. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
## 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
goal_metric
## Prompt
Detect attribution drift between platforms and Roadway
Track the weekly ratio of CRM-matched to platform-reported conversions per channel, and classify each channel:
1. Drifting up (over-claiming more)
2. Drifting down
3. Stable
Rules:
- Drift: the ratio moved clearly vs its 8-week average. If not set, by 20%+. Check for platform modeling changes, consent banner changes, CAPI or deduplication breaks, and attribution window changes.
- Update the trust factors used by the cross-channel budget workflow once drift is confirmed.
- Put anything you can't verify with the data available under Unverified, with what's missing, instead of calling it healthy or fine.
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.
- Any budget or bid change you propose moves one entity by at most the max change limit per run (20% unless the coworker's Guardrails set another); stage a larger move across runs. Pausing an entity under a stated stop rule is a status change, not a budget change.
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:
Attribution drift report
Summary:
The ratios by channel, the drift, and the likely cause.
Drifting up:
- [channel] - [reason]
Drifting down:
- [channel] - [reason]
Stable:
- [channel] - [reason]
Unverified:
- [channel] - [what couldn't be checked and why]
## Run it in Roadway
https://www.roadwayai.com/workflows/detect-attribution-drift-between-platforms-and-roadway
Alerts when a platform's reported conversions start drifting away from CRM or backend truth, which usually means a tracking or modeling change. It keeps an eye on your live account and flags anything unusual early. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
