# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Detect conversion tracking breakage for ChatGPT 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/detect-conversion-tracking-breakage-for-chatgpt-ads
Page: https://www.roadwayai.com/workflows/detect-conversion-tracking-breakage-for-chatgpt-ads
Library index: https://www.roadwayai.com/automation-library
---
name: detect-conversion-tracking-breakage-for-chatgpt-ads
description: >-
Detects when ChatGPT conversion tracking breaks or double counts, and protects automated bidding from bad data.
---
# Detect conversion tracking breakage for ChatGPT Ads
Source: https://www.roadwayai.com/workflows/detect-conversion-tracking-breakage-for-chatgpt-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
Detects when ChatGPT conversion tracking breaks or double counts, and protects automated bidding from bad data.
Detects when ChatGPT conversion tracking breaks or double counts, and protects automated bidding from bad data. It keeps an eye on your live account and flags anything unusual early. 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, crm_pipeline_data, funnel_metrics, goal_metric, max_change_pct, monthly_budget_cap, site_release_log, slack_delivery, task_history, transaction_revenue
## Prompt
Detect conversion tracking breakage for ChatGPT Ads
Compare ChatGPT Ads Manager (OpenAI) conversions over the last 72 hours with the expected volume and with the source of truth ([set this to your own CRM pipeline data], transaction revenue or analytics), and classify each conversion action:
1. Broken: act now
2. Double counting
3. Degraded
4. Healthy
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 site release log: [set this to your own site release log]. If no release log is connected, say so.
- The delivery channel: [set this to your own slack delivery]. If Slack isn't connected, deliver in the run's thread.
- 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:
- Tracking here is the OpenAI ads conversion pixel/standard events and an OAI-AdsBot-crawlable landing page. Broken: zero or near-zero conversions for 24+ hours on an action that normally fires daily, while clicks continue.
- Double counting: platform conversions well above the source of truth, or duplicated event IDs. If not set, well above means more than 130%. Check for a new tag, a duplicate pixel or deduplication failure between browser and server events.
- Degraded: conversions down sharply with clicks steady, or match quality or diagnostics warnings. If not set, sharply means 30%+. Check recent site releases (the site release log), consent banner changes and form changes.
- When tracking is broken, protect bidding: on Google and Microsoft apply a data exclusion for the affected dates; elsewhere switch target-based ad sets to a bid cap or pause the most automated campaigns until it is fixed. Alert the delivery channel with exactly what broke and when.
- Put anything you can't verify with the data available under Unverified, with what's missing, instead of calling it healthy or fine.
- 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:
ChatGPT conversion tracking health report
Summary:
The status of each conversion action, the likely cause, and the protective actions proposed.
Broken:
- [conversion action] - [reason]
Double counting:
- [conversion action] - [reason]
Degraded:
- [conversion action] - [reason]
Healthy:
- [conversion action] - [reason]
Unverified:
- [conversion action] - [what couldn't be checked and why]
## Run it in Roadway
https://www.roadwayai.com/workflows/detect-conversion-tracking-breakage-for-chatgpt-ads
Detects when ChatGPT conversion tracking breaks or double counts, and protects automated bidding from bad data. It keeps an eye on your live account and flags anything unusual early. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
