# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Optimize titles and copy 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/optimize-headlines-and-descriptions-for-chatgpt-ads
Page: https://www.roadwayai.com/workflows/optimize-headlines-and-descriptions-for-chatgpt-ads
Library index: https://www.roadwayai.com/automation-library
---
name: optimize-headlines-and-descriptions-for-chatgpt-ads
description: >-
Looks at how the title and copy on each ChatGPT sponsored card are performing, replaces the weak ones, adds missing angles and keeps the strongest.
---
# Optimize titles and copy for ChatGPT Ads
Source: https://www.roadwayai.com/workflows/optimize-headlines-and-descriptions-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
Looks at how the title and copy on each ChatGPT sponsored card are performing, replaces the weak ones, adds missing angles and keeps the strongest.
Looks at how the title and copy on each ChatGPT sponsored card are performing, replaces the weak ones, adds missing angles and keeps the strongest. Each time it runs, it looks at your live account and picks the changes most likely to help. 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
approved_claims, auto_approve, brand_voice, cost_per_goal_baseline, funnel_metrics, goal_metric, max_change_pct, monthly_budget_cap, proof_points, task_history, value_props
## Prompt
Optimize titles and copy for ChatGPT Ads
Review the performance of the title and copy on every sponsored card in my ChatGPT Ads Manager (OpenAI) account and decide for each card:
1. Keep
2. Replace
3. Rewrite
4. Add new variant
Context and defaults (use these; don't ask):
- The proof points: [set this to your own proof points]. If not set, use only approved claims.
- The value props: [set this to your own value props]. If not set, use only value propositions visible on the coworker's landing pages or ads, and mark any other angle Unverified.
- The brand voice: [set this to your own brand voice]. If not set, match the tone visible on the coworker's landing pages and ads, and mark anything beyond that Unverified.
- The approved claims: [set this to your own approved claims]. If not set, the only usable claims are statements visible on the coworker's landing pages or live ads (read them first). Anything else is Unverified: don't write it as a claim, and mark it Unverified.
- 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:
- Keep titles and copy that beat [set this to your own cost per goal baseline]. Replace ones whose cost per goal is clearly worse than their siblings once they have enough spend and goal events to judge, confirmed against [set this to your own funnel metrics]. Never replace on click-through rate alone. Treat cards with little spend or few goal events as too new to judge.
- Rewrite assets that state features without a benefit, repeat another headline almost word for word, or do not match the context hints of the ad group. Each asset should add a distinct angle.
- Add new variants until every ad group has cards that cover the main angles: the problem solved, a proof point (customer count, rating, the proof points), the offer, and urgency or a CTA. Pull language from the value props and the brand voice.
- For ChatGPT, write titles as direct answers to a need ("Payroll for 50-person teams in one click") rather than slogans, and check that each claim matches the approved claims.
- Never invent claims. Only use numbers and promises from the approved claims.
- 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 title and copy optimization report
Summary:
How many cards changed, which angles were missing, and the copy you will ship.
Keep:
- [title / copy] - [reason]
Replace:
- [title / copy] - [reason]
Rewrite:
- [title / copy] - [reason]
Add new variant:
- [title / copy] - [reason]
New copy to ship:
- [ad group] - [title / copy] - [angle it adds]
## Run it in Roadway
https://www.roadwayai.com/workflows/optimize-headlines-and-descriptions-for-chatgpt-ads
Looks at how the title and copy on each ChatGPT sponsored card are performing, replaces the weak ones, adds missing angles and keeps the strongest. Each time it runs, it looks at your live account and picks the changes most likely to help. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
