# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Roll back changes that hurt results after seven days.
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/roll-back-changes-that-hurt-results-after-seven-days
Page: https://www.roadwayai.com/workflows/roll-back-changes-that-hurt-results-after-seven-days
Library index: https://www.roadwayai.com/automation-library
---
name: roll-back-changes-that-hurt-results-after-seven-days
description: >-
Checks every approved change against its measured impact a week later, and rolls back the ones that hurt, so bad changes never become the baseline.
---
# Roll back changes that hurt results after seven days
Source: https://www.roadwayai.com/workflows/roll-back-changes-that-hurt-results-after-seven-days
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
Checks every approved change against its measured impact a week later, and rolls back the ones that hurt, so bad changes never become the baseline.
Checks every approved change against its measured impact a week later, and rolls back the ones that hurt, so bad changes never become the baseline. Seven days after a change, if cost per goal or conversions are worse than the control, it will roll back and write the lesson into Task History. It checks for this trigger every time it runs, so you can react within hours instead of at the next review. 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
auto_approve, conversion_lag_days, funnel_metrics, goal_metric, impact_history, max_change_pct, min_sample_size, monthly_budget_cap, task_history
## Prompt
Roll back changes that hurt results after seven days
Read the changes made in the last 7-14 days from [set this to your own task history] and [set this to your own impact history], measure each against its before-period and a comparable control, and decide for each:
1. Roll back
2. Keep and monitor
3. Keep
4. Needs more data
Context and defaults (use these; don't ask):
- Measured impact of past changes by workflow: [set this to your own impact history]. If it isn't available, say so and skip the rules that depend on it.
- Minimum conversions per variant before declaring a test: [set this to your own min sample size]. If not set, 30 conversions per variant.
- Typical delay between click and goal event: [set this to your own conversion lag days]. If it isn't available, say so and skip the rules that depend on it.
- 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:
- Compare cost per goal and Roadway-attributed [set this to your own goal metric] for the changed entity with its own 14 days before, and with an unchanged similar entity as control when available.
- Roll back when the changed entity's cost per goal has moved past the cost per goal guardrail versus control with [set this to your own min sample size]+ conversions, or is clearly worse with fewer conversions and 3 clear days of weakness.
- Keep and monitor when results are flat or the sample is small. Needs more data when [set this to your own conversion lag days] have not elapsed.
- Do not roll back a change that is part of an active test, and do not roll back anything older than 21 days without a human decision.
- Write what was learned into [set this to your own task history] so the same change is not proposed again within 30 days.
- 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:
Change impact and rollback report
Summary:
The changes reviewed, their measured impact, the ones rolled back, and the lessons logged.
Roll back:
- [change] - [reason]
Keep and monitor:
- [change] - [reason]
Keep:
- [change] - [reason]
Needs more data:
- [change] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/roll-back-changes-that-hurt-results-after-seven-days
Checks every approved change against its measured impact a week later, and rolls back the ones that hurt, so bad changes never become the baseline. Seven days after a change, if cost per goal or conversions are worse than the control, it will roll back and write the lesson into Task History. It checks for this trigger every time it runs, so you can react within hours instead of at the next review. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
