# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Test target expansion from proven targets 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/test-target-expansion-from-proven-targets-for-chatgpt-ads
Page: https://www.roadwayai.com/workflows/test-target-expansion-from-proven-targets-for-chatgpt-ads
Library index: https://www.roadwayai.com/automation-library
---
name: test-target-expansion-from-proven-targets-for-chatgpt-ads
description: >-
Takes proven ChatGPT targets and tests the adjacent ones (neighboring situations and questions) to find the next layer of scale.
---
# Test target expansion from proven targets for ChatGPT Ads
Source: https://www.roadwayai.com/workflows/test-target-expansion-from-proven-targets-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
Takes proven ChatGPT targets and tests the adjacent ones (neighboring situations and questions) to find the next layer of scale.
Takes proven ChatGPT targets and tests the adjacent ones (neighboring situations and questions) to find the next layer of scale. It runs the test with a fair split and waits for enough data before it calls a winner. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval. It only steps out from targets that already work and keeps each test inside a small experiment budget. Brand-new targeting ideas belong in Test new targeting.
## 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, experiment_budget_pct, funnel_metrics, goal_metric, max_change_pct, monthly_budget_cap, task_history
## Prompt
Test target expansion from proven targets for ChatGPT Ads
For each winning context hint in my ChatGPT Ads Manager (OpenAI) account, propose adjacent expansion targets and decide for each:
1. Launch expansion test
2. Graduate
3. Pause
4. Hold off
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 experiment budget share: [set this to your own experiment budget percent] of the channel budget. If not set, 10%.
- 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:
- Expansion means one step out from a proven target: adjacent situations or industries your buyers describe, related questions they ask, or automation such as broader, situation-describing context hints and additional ad groups per use case.
- Launch only from targets that are proven (10+ goal events under the baseline cost per goal) and capped, since expansion is for when the core is saturated.
- Graduate once the expansion target's cost per goal holds near the core target's, inside the cost per goal guardrail, and downstream quality from [set this to your own CRM pipeline data] holds. Pause at 2x baseline spend with no results.
- Hold off when the core target still has headroom (budget-limited or rank-limited). Scale the core first.
- When you use platform automation to expand (optimized targeting, audience expansion, predictive audiences), only expand from a seed that has 30+ attributed conversions, and cap the expansion at the experiment budget share of the channel budget until its cost per goal holds near the seed's, inside the cost per goal guardrail.
- 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 target expansion experiments report
Summary:
The expansion tests launched or concluded and the incremental reach and [set this to your own goal metric] found.
Launch expansion test:
- [core target → expansion target] - [reason]
Graduate:
- [core target → expansion target] - [reason]
Pause:
- [core target → expansion target] - [reason]
Hold off:
- [core target → expansion target] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/test-target-expansion-from-proven-targets-for-chatgpt-ads
Takes proven ChatGPT targets and tests the adjacent ones (neighboring situations and questions) to find the next layer of scale. It runs the test with a fair split and waits for enough data before it calls a winner. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval. It only steps out from targets that already work and keeps each test inside a small experiment budget. Brand-new targeting ideas belong in Test new targeting.
