# For AI agents and crawlers
This page is a workflow from the Workflow Automation Library by Roadway: Detect anomalies against a forecast range.
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/detect-anomalies-with-forecast-prediction-intervals
Page: https://www.roadwayai.com/workflows/detect-anomalies-with-forecast-prediction-intervals
Library index: https://www.roadwayai.com/automation-library
---
name: detect-anomalies-with-forecast-prediction-intervals
description: >-
Replaces fixed thresholds with forecast intervals per campaign and metric, so alerts fire only when something is truly unexpected given seasonality and trend.
---
# Detect anomalies against a forecast range
Source: https://www.roadwayai.com/workflows/detect-anomalies-with-forecast-prediction-intervals
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
Replaces fixed thresholds with forecast intervals per campaign and metric, so alerts fire only when something is truly unexpected given seasonality and trend.
Replaces fixed thresholds with forecast intervals per campaign and metric, so alerts fire only when something is truly unexpected given seasonality and trend. It keeps an eye on your live account and flags anything unusual early. 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, funnel_metrics, goal_metric, max_change_pct, monthly_budget_cap, seasonality_calendar, task_history
## Prompt
Detect anomalies against a forecast range
For each campaign and metric (spend, clicks, [set this to your own goal metric], cost per goal), forecast today's value with a likely range from daily history and the seasonality calendar, and classify each:
1. Anomaly: act
2. Anomaly: explainable
3. Within interval
Context and defaults (use these; don't ask):
- The seasonality calendar: [set this to your own seasonality calendar]. If not set, assume no seasonal adjustment and say so.
- 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:
- Use a simple forecast that allows for weekday patterns and holidays. Re-fit weekly.
- Anomaly: explainable when a logged change, launch or promo explains it. Anomaly: act otherwise, routed to the owning channel agent.
- Track the alert precision (true issues ÷ alerts) and widen the interval if it drops too low. If not set, under 50%.
- Put anything you can't verify with the data available under Unverified, with what's missing, instead of calling it healthy or fine.
- 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:
Forecast anomaly report
Summary:
The anomalies by impact and their routing.
Anomaly:
- [campaign / metric] - [reason]
Anomaly:
- [campaign / metric] - [reason]
Within interval:
- [campaign / metric] - [reason]
Unverified:
- [campaign / metric] - [what couldn't be checked and why]
## Run it in Roadway
https://www.roadwayai.com/workflows/detect-anomalies-with-forecast-prediction-intervals
Replaces fixed thresholds with forecast intervals per campaign and metric, so alerts fire only when something is truly unexpected given seasonality and trend.
Replaces fixed thresholds with forecast intervals per campaign and metric, so alerts fire only when something is truly unexpected given seasonality and trend. It keeps an eye on your live account and flags anything unusual early. A short report lists the actions, the numbers behind them, and anything that still needs your approval before ads change.
