# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Hold the experiment budget guardrail.
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/hold-the-experiment-budget-guardrail
Page: https://www.roadwayai.com/workflows/hold-the-experiment-budget-guardrail
Library index: https://www.roadwayai.com/automation-library
---
name: hold-the-experiment-budget-guardrail
description: >-
Keeps the total spend on tests and experiments across all channels within the agreed experiment budget, so exploration never eats the core.
---
# Hold the experiment budget guardrail
Source: https://www.roadwayai.com/workflows/hold-the-experiment-budget-guardrail
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 the total spend on tests and experiments across all channels within the agreed experiment budget, so exploration never eats the core.
Keeps the total spend on tests and experiments across all channels within the agreed experiment budget, so exploration never eats the core. It keeps spend inside the limits you set and shows you what it would change. 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, connected_channels, experiment_budget_pct, funnel_metrics, goal_metric, max_change_pct, monthly_budget_cap, naming_convention, task_history
## Prompt
Hold the experiment budget guardrail
List every active experiment, test campaign and new launch across the channels in [set this to your own connected channels] that this coworker owns (for a single-channel coworker, only its own channel), sum their spend against the experiment budget share of the monthly cap, and decide for each experiment:
1. Keep funding
2. Reduce funding
3. End experiment
4. Graduate to core budget
Context and defaults (use these; don't ask):
- The experiment budget share: [set this to your own experiment budget percent] of the channel budget. If not set, 10%.
- 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 naming convention: [set this to your own naming convention]. If not set, infer the dominant pattern from existing names and say so.
- 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:
- Experiments include anything labeled as a test per the naming convention, campaigns younger than 30 days, and new channels.
- When total experiment spend is over the allowance, reduce or end the experiments with the weakest early signal first. When under, let promising experiments finish faster.
- Graduate experiments that met their success criteria. They move to core budget and stop counting against the experiment allowance.
- Never let a single experiment take too much of the experiment allowance. If not set, no more than 40%.
- If no campaign qualifies to receive budget, still make the justified cuts and report the freed budget as unallocated savings for approval. Never pause the entity producing the most [set this to your own goal metric] at or below baseline.
- 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:
Experiment budget report
Summary:
Experiment spend vs allowance, the experiments funded or cut, and graduations.
Keep funding:
- [experiment] - [reason]
Reduce funding:
- [experiment] - [reason]
End experiment:
- [experiment] - [reason]
Graduate to core budget:
- [experiment] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/hold-the-experiment-budget-guardrail
Keeps the total spend on tests and experiments across all channels within the agreed experiment budget, so exploration never eats the core. It keeps spend inside the limits you set and shows you what it would change. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
