# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Scale winning keywords for Microsoft (Bing) Ads.
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/scale-winning-keywords-for-microsoft-bing-ads
Page: https://www.roadwayai.com/workflows/scale-winning-keywords-for-microsoft-bing-ads
Library index: https://www.roadwayai.com/automation-library
---
name: scale-winning-keywords-for-microsoft-bing-ads
description: >-
Finds the keywords on Microsoft (Bing) Ads that win on pipeline and cost per goal, then raises their budgets or bid targets a little each run.
---
# Scale winning keywords for Microsoft (Bing) Ads
Source: https://www.roadwayai.com/workflows/scale-winning-keywords-for-microsoft-bing-ads
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
Finds the keywords on Microsoft (Bing) Ads that win on pipeline and cost per goal, then raises their budgets or bid targets a little each run.
Finds the keywords on Microsoft (Bing) Ads that win on pipeline and cost per goal, then raises their budgets or bid targets a little each run. On every run it looks for what is working and proposes small steps to scale it without breaking efficiency. 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, cost_guardrail, funnel_metrics, goal_metric, lookback_days, max_change_pct, min_goal_events, monthly_budget_cap, task_history
## Prompt
Scale winning keywords for Microsoft (Bing) Ads
Find winning keywords on Microsoft (Bing) Ads and scale them. For each winner, decide:
1. Raise budget
2. Raise bid target
3. Hold
Context and defaults (use these; don't ask):
- The lookback window: [set this to your own lookback days] days. If not set, 30.
- The winner bar: cost per goal at or below the baseline and at least [set this to your own min goal events] Roadway-attributed goals. If not set, 15 goals.
- The budget raise per run: [set this to your own max change percent]. If not set, 20%.
- 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 cost guardrail: [set this to your own cost guardrail], from the coworker's Guardrails. If not set, 1.3x the baseline cost per goal. A workflow qualification bar (for example "cost per lead under $100 to build a page") is not a ceiling.
- 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:
- List keywords on Microsoft (Bing) Ads that clear the winner bar over the lookback window, using Roadway-attributed goals and cost per goal, not platform conversions.
- For each winner, check whether it is held back by budget or by bid. If it is losing meaningful impression share to budget, raise the campaign budget. If not set, meaningful means above 10%. If the cause is rank, raise the campaign's target CPA (or lower its target ROAS) under Maximize conversions or Maximize conversion value. Do not raise bids on individual keywords; if the campaign is still on manual CPC, propose switching it to Maximize conversions.
- Raise by at most the max change limit per run, and never past the monthly cap. Check the next run before raising again.
- Skip keywords with fewer goals than the bar, brand terms already at full impression share, and any keyword that is inside a campaign with a fresh learning period.
- Add the exact and phrase match versions of a winning broad keyword as separate entries only if the search terms report shows them converting.
- 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:
Microsoft (Bing) Ads winning keyword scaling report
Summary:
How many winners cleared the bar and the budget or bid changes proposed.
Raise budget:
- [keyword and campaign] - [goals, cost per goal, lost share to budget]
Raise bid target:
- [keyword and campaign] - [goals, cost per goal, lost share to rank]
Hold:
- [keyword] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/scale-winning-keywords-for-microsoft-bing-ads
Finds the keywords on Microsoft (Bing) Ads that win on pipeline and cost per goal, then raises their budgets or bid targets a little each run. On every run it looks for what is working and proposes small steps to scale it without breaking efficiency. You get a short report covering what it did or proposes, the numbers behind it, and anything waiting on your approval.
