# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Scale winning targets and campaigns 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/scale-winning-targets-and-campaigns-for-chatgpt-ads
Page: https://www.roadwayai.com/workflows/scale-winning-targets-and-campaigns-for-chatgpt-ads
Library index: https://www.roadwayai.com/automation-library
---
name: scale-winning-targets-and-campaigns-for-chatgpt-ads
description: >-
Finds the ChatGPT campaigns and context hints plus country, platform (iOS app, Android app, web) and custom audience targeting that beat your cost per goal and scales them without breaking efficiency.
---
# Scale winning targets and campaigns for ChatGPT Ads
Source: https://www.roadwayai.com/workflows/scale-winning-targets-and-campaigns-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
Finds the ChatGPT campaigns and context hints plus country, platform (iOS app, Android app, web) and custom audience targeting that beat your cost per goal and scales them without breaking efficiency.
Finds the ChatGPT campaigns and context hints plus country, platform (iOS app, Android app, web) and custom audience targeting that beat your cost per goal and scales them without breaking efficiency. On every run it looks for what is working and proposes small steps to scale it without breaking efficiency. 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, funnel_metrics, goal_metric, lookback_window, max_change_pct, monthly_budget_cap, pay_back_target, task_history
## Prompt
Scale winning targets and campaigns for ChatGPT Ads
Find every ChatGPT Ads Manager (OpenAI) campaign and context hint beating the baseline cost per goal over the last [set this to your own lookback window] and decide how to scale each:
1. Increase budget
2. Loosen bid target
3. Duplicate into new campaign
4. Hold
Context and defaults (use these; don't ask):
- 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 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.
- The payback target: [set this to your own pay back target]. If not set, 12 months.
- 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.
- Auto-approve: [set this to your own auto approve]. If not set, it's off: list every change as a proposal for approval.
Rules:
- Only scale what is proven: at least 15 [set this to your own goal metric] events, cost per goal clearly under the baseline for long enough to trust it, and a stable trend over the last 2 weeks rather than one lucky week.
- Increase budget by at most the max change limit every 3-4 days when the campaign is budget-constrained (check for a bid target that is too low, narrow context hints and landing pages the OAI-AdsBot cannot crawl). Bigger jumps reset the short calibration period (conversion-optimized campaigns need steady conversion volume) and usually spike cost per goal.
- Loosen the bid target or cost cap a little, within the max change limit, when the budget is not spending because the target is too tight.
- Duplicate a winning context hint into its own campaign when it shares a budget with weaker targets and is getting starved, or when a new geo or audience version needs its own budget.
- Hold when the winner is already at the edge of the market (delivery is limited by the conversations your context hints match, not by budget).
- Scale in steps of no more than the max change limit every 3-4 days. Hold the step if attributed cost per [set this to your own goal metric] over the step has risen clearly vs. the prior 14 days, or if payback time goes past the payback target. Roll back the last step if cost per goal has moved over the cost per goal guardrail.
- If no campaign qualifies to receive budget, still make the justified cuts and report the freed budget as unallocated savings for approval. Never pause the entity producing the most [set this to your own goal metric] at or below baseline.
- Delivery-constrained (budget-limited) means it spent nearly all of its daily budget on most recent days. If not set, 95%+ of the daily budget on 4+ of the last 7 days.
- 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 scaling report
Summary:
The winners found, the budget being added, and the expected incremental [set this to your own goal metric] at what cost per goal.
Increase budget:
- [campaign / target] - [reason]
Loosen bid target:
- [campaign / target] - [reason]
Duplicate into new campaign:
- [campaign / target] - [reason]
Hold:
- [campaign / target] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/scale-winning-targets-and-campaigns-for-chatgpt-ads
Scale winning targets and campaigns for ChatGPT Ads
Scale winning targets and campaigns for ChatGPT Ads
Finds the ChatGPT campaigns and context hints plus country, platform (iOS app, Android app, web) and custom audience targeting that beat your cost per goal and scales them without breaking efficiency.
Finds the ChatGPT campaigns and context hints plus country, platform (iOS app, Android app, web) and custom audience targeting that beat your cost per goal and scales them without breaking efficiency. On every run it looks for what is working and proposes small steps to scale it without breaking efficiency. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
