# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Suggest new workflows from Task History and performance gaps.
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/suggest-new-workflows-from-task-history-and-performance-gaps
Page: https://www.roadwayai.com/workflows/suggest-new-workflows-from-task-history-and-performance-gaps
Library index: https://www.roadwayai.com/automation-library
---
name: suggest-new-workflows-from-task-history-and-performance-gaps
description: >-
Reviews what every coworker did, what it changed and what happened (Task History plus action-impact memory), and proposes the next workflows worth automating, or the ones to retire.
---
# Suggest new workflows from Task History and performance gaps
Source: https://www.roadwayai.com/workflows/suggest-new-workflows-from-task-history-and-performance-gaps
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
Reviews what every coworker did, what it changed and what happened (Task History plus action-impact memory), and proposes the next workflows worth automating, or the ones to retire.
Reviews what every coworker did, what it changed and what happened (Task History plus action-impact memory), and proposes the next workflows worth automating, or the ones to retire. It pulls the numbers from your live account and writes them up for you.
## 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
connected_channels, funnel_metrics, goal_metric, max_change_pct, task_history
## Prompt
Suggest new workflows from Task History and performance gaps
Review [set this to your own task history] for every coworker over the last 30 days, plus the manual changes made in [set this to your own connected channels], and decide for each candidate:
1. Propose a new workflow
2. Tighten an existing workflow
3. Retire a workflow
4. Expand auto-approval
Context and defaults (use these; don't ask):
- 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.
Rules:
- Propose a new workflow when the same manual change was made 3+ times in 30 days, or when a recurring anomaly or opportunity had no workflow to catch it. Write the draft name, schedule, steps and approval setting.
- Tighten an existing workflow when a large share of its recommendations were declined. If not set, 30%+. Read the decline reasons and change the thresholds or rules that produced them.
- Retire a workflow that produced no approved action in 6+ runs, or whose approved actions show no measurable impact in action-impact memory.
- Recommend expanding auto-approval only for workflows with 20+ approved actions, very few declines, and positive measured impact on [set this to your own funnel metrics]. If not set, under 5% declines. Never for budget increases above the max change limit.
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:
Workflow suggestions
Summary:
The workflows to add, tighten, retire or auto-approve, and the hours and cost impact expected.
Propose a new workflow:
- [workflow] - [reason]
Tighten an existing workflow:
- [workflow] - [reason]
Retire a workflow:
- [workflow] - [reason]
Expand auto-approval:
- [workflow] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/suggest-new-workflows-from-task-history-and-performance-gaps
Suggest new workflows from Task History and performance gaps
Suggest new workflows from Task History and performance gaps
Reviews what every coworker did, what it changed and what happened (Task History plus action-impact memory), and proposes the next workflows worth automating, or the ones to retire.
Reviews what every coworker did, what it changed and what happened (Task History plus action-impact memory), and proposes the next workflows worth automating, or the ones to retire. It pulls the numbers from your live account and writes them up for you.
