# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Test trial landing pages, then move ads to the winner.
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/allocate-trial-traffic-across-landing-pages-with-a-bandit
Page: https://www.roadwayai.com/workflows/allocate-trial-traffic-across-landing-pages-with-a-bandit
Library index: https://www.roadwayai.com/automation-library
---
name: allocate-trial-traffic-across-landing-pages-with-a-bandit
description: >-
Drafts 2-3 signup landing page variants for paid traffic, reads the test results once enough data is in, and tells you when and how far to shift traffic to the winner. Needs a page builder MCP such as Webflow, Framer, Lovable or Ploy connected in Roadway.
---
# Test trial landing pages, then move ads to the winner
Source: https://www.roadwayai.com/workflows/allocate-trial-traffic-across-landing-pages-with-a-bandit
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
Drafts 2-3 signup landing page variants for paid traffic, reads the test results once enough data is in, and tells you when and how far to shift traffic to the winner. Needs a page builder MCP such as Webflow, Framer, Lovable or Ploy connected in Roadway.
Each run, the agent checks each paid signup test. It uses a page builder MCP such as Webflow, Framer, Lovable or Ploy to draft the 2 to 3 variant pages, never publishing them, then judges them on signups who go on to use the product, once enough time has passed to tell. When one variant is clearly ahead, it recommends the next step of the traffic shift, in measured steps with a small holdback on the old page. The page builder MCP does not route traffic, so the split itself lives on your page or in your testing tool.
## 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
activation_event, activation_window_days, auto_approve, experiment_budget_pct, funnel_metrics, goal_metric, max_change_pct, monthly_budget_cap, task_history
## Prompt
Test trial landing pages with a fixed split, then shift traffic to the winner
For each traffic source sending paid visitors to signup, review the landing page test and decide:
1. Start a test
2. Keep running
3. Move traffic to the winner
4. Hold
Context and defaults (use these; don't ask):
- The activation event: [set this to your own activation event]. If it isn't available, say so and skip the rules that depend on it.
- The activation window: [set this to your own activation window days] days. If not set, 14 days.
- 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 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:
- Page builder: use a page builder MCP such as Webflow, Framer, Lovable or Ploy connected in Roadway to create each page as a draft. If none is connected, say so, write the page brief instead of the page, and stop. Never publish a page. Publishing is a person's call. Use it to draft the 2-3 variant pages.
- Optimize for signups who reach the activation event, not raw signups, and wait for the activation window to pass before reading a result.
- Test 2-3 landing page variants at a time with a fixed, even traffic split (for example 50/50, or 34/33/33), using the same ads and audiences, with one change per variant. Do not move the split while a test is running.
- Split traffic on the page or with a testing tool, not by editing live ad URLs, so ads are not sent back to review and bidding does not restart learning. Do not change campaign budgets, bids or targeting as part of this workflow.
- Call a test only when every variant has at least 100 signups, the activation window has passed, and the leader is clearly ahead on signups who reach the activation event with enough data to call a winner. If that is not reached in 4 weeks, call it a tie and keep the control.
- Recommend moving traffic to the winner in steps of at most [set this to your own max change percent] of the split per run (for example 50% to 70% to 90%), with 3+ days between steps. The page builder MCP cannot change a split, so the person or the testing tool applies each step. Keep a small holdback on the old page so the result can be checked again.
- Start the next variant only after the current test is read out, and one at a time. Retire a variant after its test ends, not mid-test.
- 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:
Trial landing page test report
Summary:
The variant results, the traffic split, and the changes.
Move traffic to the winner:
- [variant] - [reason]
Start a test:
- [variant] - [reason]
Retire variant:
- [variant] - [reason]
Hold:
- [variant] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/allocate-trial-traffic-across-landing-pages-with-a-bandit
Test trial landing pages, then move ads to the winner
Test trial landing pages, then move ads to the winner
Drafts 2-3 signup landing page variants for paid traffic, reads the test results once enough data is in, and tells you when and how far to shift traffic to the winner. Needs a page builder MCP such as Webflow, Framer, Lovable or Ploy connected in Roadway.
Each run, the agent checks each paid signup test. It uses a page builder MCP such as Webflow, Framer, Lovable or Ploy to draft the 2 to 3 variant pages, never publishing them, then judges them on signups who go on to use the product, once enough time has passed to tell. When one variant is clearly ahead, it recommends the next step of the traffic shift, in measured steps with a small holdback on the old page. The page builder MCP does not route traffic, so the split itself lives on your page or in your testing tool.
