# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Prioritize the experiment backlog.
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/prioritize-the-experiment-backlog
Page: https://www.roadwayai.com/workflows/prioritize-the-experiment-backlog
Library index: https://www.roadwayai.com/automation-library
---
name: prioritize-the-experiment-backlog
description: >-
Keeps a ranked backlog of test ideas across channels, ordered by expected effect and the spend at risk, so the next test is the one with the best payoff. You can set your own scores.
---
# Prioritize the experiment backlog
Source: https://www.roadwayai.com/workflows/prioritize-the-experiment-backlog
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
Keeps a ranked backlog of test ideas across channels, ordered by expected effect and the spend at risk, so the next test is the one with the best payoff. You can set your own scores.
Keeps a ranked backlog of test ideas across channels, ordered by expected effect and the spend at risk, so the next test is the one with the best payoff. You can set your own scores. It sets up the test, keeps the split fair, and only calls a winner once there is enough data. 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
competitor_ad_insights, creative_library, customer_reviews, experiment_budget_pct, goal_metric
## Prompt
Prioritize the experiment backlog
Collect test ideas from all channel agent reports, competitor ad snapshots and customer reviews, rank each, and decide:
1. Run next
2. Keep in backlog
3. Drop
Context and defaults (use these; don't ask):
- Competitor ad snapshots: [set this to your own competitor ad insights]. If none are stored, pull them from the ad libraries or skip.
- Customer reviews: [set this to your own customer reviews]. If it isn't available, say so and skip the rules that depend on it.
- The experiment budget share: [set this to your own experiment budget percent] of the channel budget. If not set, 10%.
- The creative library: [set this to your own creative library]. If not set, use the ad platform's asset performance and Task History.
Rules:
- Rank each idea by the expected change in [set this to your own goal metric] or cost per goal, how solid the evidence is, and how much spend it puts at risk. Use real results from the creative library where you have them. If you give scores, use yours instead of inventing numbers.
- Run next: the top 3 ideas that fit inside the experiment budget share and do not collide with a running test in the same audience.
- Drop ideas that have already been tested (check the creative library) or depend on resources you do not have.
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:
Experiment backlog
Summary:
The ranked backlog, the next 3 tests, and the dropped ideas.
Run next:
- [idea] - [reason]
Keep in backlog:
- [idea] - [reason]
Drop:
- [idea] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/prioritize-the-experiment-backlog
Keeps a ranked backlog of test ideas across channels, ordered by expected effect and the spend at risk, so the next test is the one with the best payoff. You can set your own scores.
Keeps a ranked backlog of test ideas across channels, ordered by expected effect and the spend at risk, so the next test is the one with the best payoff. You can set your own scores. It sets up the test, keeps the split fair, and only calls a winner once there is enough data. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
