# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Build agents and workflows for a newly connected channel.
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/build-agents-and-workflows-for-a-newly-connected-channel
Page: https://www.roadwayai.com/workflows/build-agents-and-workflows-for-a-newly-connected-channel
Library index: https://www.roadwayai.com/automation-library
---
name: build-agents-and-workflows-for-a-newly-connected-channel
description: >-
When a new ad platform is connected, drafts the AI Coworker (goal, funnel, guardrails) and its starter workflows from what already works on your other channels, ready for approval.
---
# Build agents and workflows for a newly connected channel
Source: https://www.roadwayai.com/workflows/build-agents-and-workflows-for-a-newly-connected-channel
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
When a new ad platform is connected, drafts the AI Coworker (goal, funnel, guardrails) and its starter workflows from what already works on your other channels, ready for approval.
When a new ad platform is connected, drafts the AI Coworker (goal, funnel, guardrails) and its starter workflows from what already works on your other channels, ready for approval. It reads all your connected channels together so you can compare them fairly. 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
connected_channels, cost_guardrail, creative_library, experiment_budget_pct, goal_metric, icp, monthly_budget_cap, top_search_terms
## Prompt
Build agents and workflows for a newly connected channel
For each ad platform in [set this to your own connected channels] that has no AI Coworker yet, draft the coworker and its starter workflows, and decide for each piece:
1. Create now
2. Create in draft
3. Wait for data
4. Skip
Context and defaults (use these; don't ask):
- 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 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 top search terms: [set this to your own top search terms]. If not set, use the search terms report over the lookback window, ranked by the parent keyword's Roadway cost per goal.
- The creative library: [set this to your own creative library]. If not set, use the ad platform's asset performance and Task History.
Rules:
- Set the coworker's goal to the same [set this to your own goal metric] and funnel as your best channel, with a starting cost guardrail somewhat looser than that channel's (new channels need room to learn) and a test budget of the experiment budget share of the monthly cap. If not set, 20% looser.
- Starter workflows, in this order: check spend caps and unblock delivery, pace daily spend, report weekly performance, detect conversion tracking breakage, then the channel's core targeting optimization. Add scaling and experiments only after 30 attributed conversions.
- Create now only when conversion tracking on the new platform closely matches Roadway's attributed [set this to your own goal metric] over 7 days. If not set, within 25%. Otherwise create in draft and wait for data.
- Seed the first campaigns from what wins elsewhere: the top 10 the top search terms, the best creative angles in the creative library, and [set this to your own ICP]. Leave every action approval-first.
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.
- Any budget or bid change you propose moves one entity by at most the max change limit per run (20% unless the coworker's Guardrails set another); stage a larger move across runs. Pausing an entity under a stated stop rule is a status change, not a budget change.
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:
New channel setup plan
Summary:
The coworker and workflows drafted for each new channel, and what is still blocking go-live.
Create now:
- [channel / workflow] - [reason]
Create in draft:
- [channel / workflow] - [reason]
Wait for data:
- [channel / workflow] - [reason]
Skip:
- [channel / workflow] - [reason]
## Run it in Roadway
https://www.roadwayai.com/workflows/build-agents-and-workflows-for-a-newly-connected-channel
Build agents and workflows for a newly connected channel
Build agents and workflows for a newly connected channel
When a new ad platform is connected, drafts the AI Coworker (goal, funnel, guardrails) and its starter workflows from what already works on your other channels, ready for approval.
When a new ad platform is connected, drafts the AI Coworker (goal, funnel, guardrails) and its starter workflows from what already works on your other channels, ready for approval. It reads all your connected channels together so you can compare them fairly. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
