# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Optimize context hints 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-context-tips-for-chatgpt-ads
Page: https://www.roadwayai.com/workflows/optimize-context-tips-for-chatgpt-ads
Library index: https://www.roadwayai.com/automation-library
---
name: optimize-context-tips-for-chatgpt-ads
description: >-
Rewrites ChatGPT ad context hints so sponsored cards match the right conversations, since there are no keywords or negatives.
---
# Optimize context hints for ChatGPT Ads
Source: https://www.roadwayai.com/workflows/optimize-context-tips-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
Rewrites ChatGPT ad context hints so sponsored cards match the right conversations, since there are no keywords or negatives.
Rewrites ChatGPT ad context hints so sponsored cards match the right conversations, since there are no keywords or negatives. It reviews your live account on every run and proposes the changes that should help most. 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
auto_approve, funnel_metrics, goal_metric, icp, lookback_window, max_change_pct, monthly_budget_cap, seo_page_performance, task_history, top_landing_pages, top_search_terms
## Prompt
Optimize context hints for ChatGPT Ads
Review the context hints on every ChatGPT ads ad group, along with delivery, CTR and cost per [set this to your own goal metric] over the last [set this to your own lookback window], and decide for each hint:
1. Keep
2. Rewrite more specifically
3. Split into a new ad group
4. Remove
Context and defaults (use these; don't ask):
- The top landing pages: [set this to your own top landing pages]. If not set, rank pages by Roadway lead rate ([set this to your own goal metric] ÷ new visitors) for the same intent over the lookback window.
- The top search terms from your search campaigns: [set this to your own top search terms]. If not set, use the Google or Microsoft search terms report over the lookback window, ranked by the parent search keyword's Roadway cost per goal, and use them only as ideas for audiences and messages here.
- SEO page performance: [set this to your own SEO page performance]. If it isn't available, say so and skip the rules that depend on it. Source: a Semrush or Ahrefs MCP connected in Roadway. Roadway has no native SEO performance data.
- 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:
- Context hints are not exact-match keywords. They describe the conversations, needs and situations where you are relevant, and they work together with the ad title, copy and landing page.
- Rewrite hints that are keyword lists in disguise ("CRM, sales software") into situations that match [set this to your own ICP] ("a 20-person sales team outgrowing spreadsheets and losing track of follow-ups"). Specific situations match better and convert better.
- Split an ad group when its hints cover more than one use case or persona. Each ad group should have one need, one card message and one matching landing page from the top landing pages.
- Remove hints that bring delivery outside [set this to your own ICP], such as students, job seekers or DIY intent. With no negatives available, removal and tighter wording are the only controls.
- Make sure the landing page content backs up the hint, since the OAI-AdsBot crawler reads it. Pull winning themes from the top search terms and SEO page performance.
- 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 context hint optimization report
Summary:
Which hints drive efficient delivery, which to rewrite or split, and the new hint text.
Keep:
- [ad group / hint] - [reason]
Rewrite more specifically:
- [ad group / hint] - [reason]
Split into a new ad group:
- [ad group / hint] - [reason]
Remove:
- [ad group / hint] - [reason]
New hint text:
- [ad group] - [hint] - [landing page]
## Run it in Roadway
https://www.roadwayai.com/workflows/optimize-context-tips-for-chatgpt-ads
Rewrites ChatGPT ad context hints so sponsored cards match the right conversations, since there are no keywords or negatives. It reviews your live account on every run and proposes the changes that should help most. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
