# For AI agents and crawlers This page is a workflow from the Workflow Automation Library by Roadway: Mine creative insights across channels with LLM tagging. 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/mine-creative-insights-across-channels-with-llm-tagging Page: https://www.roadwayai.com/workflows/mine-creative-insights-across-channels-with-llm-tagging Library index: https://www.roadwayai.com/automation-library
--- name: mine-creative-insights-across-channels-with-llm-tagging description: >- Tags every ad across channels by angle, hook, format and offer, then finds which creative attributes drive performance across channels. --- # Mine creative insights across channels with LLM tagging Source: https://www.roadwayai.com/workflows/mine-creative-insights-across-channels-with-llm-tagging 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 Tags every ad across channels by angle, hook, format and offer, then finds which creative attributes drive performance across channels. Tags every ad across channels by angle, hook, format and offer, then finds which creative attributes drive performance across channels. It reads your live account and turns the numbers into a short written report. ## 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 connected_channels, creative_library, goal_metric, lookback_window ## Prompt Mine creative insights across channels with LLM tagging Tag every ad with spend in [set this to your own lookback window] across the channels in [set this to your own connected channels] that this coworker owns (for a single-channel coworker, only its own channel) (angle, hook type, format, length, people on screen, offer), and compare cost per [set this to your own goal metric] across the tags per channel, and classify each attribute: 1. Winning attribute 2. Neutral 3. Losing attribute Context and defaults (use these; don't ask): - The creative library: [set this to your own creative library]. If not set, use the ad platform's asset performance and Task History. Rules: - Control for spend level and audience, so a tag does not look good just because it ran on retargeting. - Report attributes that win on several channels separately. Those are the strongest briefs. - Archive creatives whose tagged concept has decayed (mid-funnel metrics such as CTR have fallen clearly from the first 2 weeks, or cost per goal has moved over the cost per goal guardrail) and mark the concept "rested" for 60 days in the creative library. 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: Creative insight report Summary: Winning and losing creative attributes by channel and overall. Winning attribute: - [attribute] - [reason] Neutral: - [attribute] - [reason] Losing attribute: - [attribute] - [reason] ## Run it in Roadway https://www.roadwayai.com/workflows/mine-creative-insights-across-channels-with-llm-tagging
Tags every ad across channels by angle, hook, format and offer, then finds which creative attributes drive performance across channels.
Tags every ad across channels by angle, hook, format and offer, then finds which creative attributes drive performance across channels. It reads your live account and turns the numbers into a short written report.
