# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Investigate drops in revenue per dollar by market.
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/investigate-drops-in-marketplace-revenue-efficiency
Page: https://www.roadwayai.com/workflows/investigate-drops-in-marketplace-revenue-efficiency
Library index: https://www.roadwayai.com/automation-library
---
name: investigate-drops-in-marketplace-revenue-efficiency
description: >-
Spots when revenue per dollar falls, and works out whether the cause is the ads, order value, supply in a market, or tracking, before proposing a fix.
---
# Investigate drops in revenue per dollar by market
Source: https://www.roadwayai.com/workflows/investigate-drops-in-marketplace-revenue-efficiency
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
Spots when revenue per dollar falls, and works out whether the cause is the ads, order value, supply in a market, or tracking, before proposing a fix.
This workflow compares revenue efficiency since the last run with the usual level and breaks any drop into its parts. 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, conversion_lag_days, cost_per_goal_baseline, funnel_metrics, goal_metric, marketplace_liquidity, max_change_pct, monthly_budget_cap, task_history, transaction_revenue
## Prompt
Investigate drops in revenue per dollar by market
Compare Roadway-attributed revenue per dollar since the last run with the usual level, by channel, campaign and market, and decide for each drop:
1. Fix now
2. Watch
3. No action
Context and defaults (use these; don't ask):
- Revenue: completed-transaction revenue (GMV, or your take rate on each transaction) from [set this to your own transaction revenue], as your Roadway funnel defines it. ARR, MRR, subscription, pipeline or closed-won deal revenue don't count. If [set this to your own goal metric] isn't completed-transaction revenue, use the transaction-revenue stage in [set this to your own funnel metrics] and say so. If neither is mapped, say so and stop: don't rank, bucket or propose anything.
- The time from click to a completed transaction: [set this to your own conversion lag days] days. If not set, compute it from Roadway's click and transaction timestamps and state it. Don't judge days that haven't had time to convert.
- Supply and demand balance by market or category: [set this to your own marketplace liquidity]. If it isn't available, say so and skip the rules that depend on it.
- 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, and state the number.
- 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 or the current run-rate.
- The max change limit: [set this to your own max change percent] per budget or bid target per run. If not set, 20%.
- Auto-approve: [set this to your own auto approve]. If not set, it's off: list every change as a proposal for approval.
Rules:
- A drop is revenue per dollar 25%+ under baseline with at least 2x the baseline cost per goal in spend.
- Break each drop into cost per click, conversion to a completed transaction, and revenue per transaction, and name the part that moved most.
- If the drop sits in one market and supply there got worse, it's a supply problem: propose holding spend in that market rather than changing creative or bids.
- If revenue fell everywhere at once, check tracking and the transaction data sync first.
- Guardrails: judge results on Roadway's full-funnel measurement ([set this to your own funnel metrics]), not platform-reported conversions, conversion value or ROAS. Check [set this to your own task history] so you don't repeat a change that already hurt performance. Never push total spend above the monthly cap or any single change beyond the max change limit per run, keep changes small enough that smart bidding doesn't restart its learning phase, 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 revenue ([set this to your own goal metric]) and revenue per dollar of spend against the account average. 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: revenue per dollar = Roadway-attributed revenue ÷ Roadway spend. Don't substitute platform-reported conversion value or ROAS.
- 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:
Revenue efficiency check
Summary:
The drops found, the likely cause of each, and the fixes proposed.
Fix now:
- [campaign, channel or market] - [reason]
Watch:
- [campaign, channel or market] - [reason]
No action:
- [campaign, channel or market] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/investigate-drops-in-marketplace-revenue-efficiency
This workflow compares revenue efficiency since the last run with the usual level and breaks any drop into its parts. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.