Quick overview This workflow pulls ad spend and platform-reported revenue from Meta (with placeholders for Google Ads and TikTok), combines it with your actual store revenue and new-customer count, calculates blended ROAS/MER and blended CAC plus over-claiming, and uses Anthropic Claude to generate a short executive efficiency brief. How it works Runs manually to start the reconciliation for the configured date range. Loads the reporting window plus store revenue, new-customer count, and any additional platform spend/revenue inputs. Calls the Meta Marketing API to fetch account-level ad spend and conversion value, then merges it with the additional platform figures. Calculates total spend, total platform-reported revenue, blended ROAS/MER, blended CAC, and the over-claim amount and percentage, plus per-platform reported ROAS. Sends the reconciled metrics to Anthropic Claude to generate a terse JSON brief with a verdict, over-claim note, and recommended action. Prints a console scorecard with blended ROAS/MER, CAC, over-claiming, per-platform breakdown, and the Claude-generated brief.
Tags
Facebook Graph APIWHTTP RequestRelated workflows
See all Facebook Graph API→WMonitor Meta CAPI event match quality with Meta Graph API and Claude
Quick overview This workflow runs on demand to monitor Meta Conversions API Event Match Quality across the pixels in a Meta ad account, calculates a weighted 0–100 match-quality score from Graph API stats, and uses Anthropic Claude to summarize risks and fixes for any pixels below an alert threshold. How it works Runs when you manually trigger the workflow. Loads configuration for which pixels to monitor, how far back to consider pixels active, which conversion events to weight more heavily, and the alert threshold. Uses the Meta Graph API to discover recently active pixels (or uses a provided list of pixel IDs) and pulls per-event “had_pii” coverage stats for each pixel. Computes a weighted match-quality score per pixel (conversion events count triple) and builds a scorecard sorted from lowest to highest. Sends the scorecard to Anthropic Claude to generate a short JSON summary with a one-line risk and a concrete fix for each pixel below the threshold. Prints a formatted EMQ scorecard with alerts and Claude’s recommendations to the execution log. Setup Create a Meta access token with permissions to read pixel stats, and set META_ACCESS_TOKEN, META_AD_ACCOUNT_ID, and (optionally) ME
WFind wasted Meta ad spend by placement, region, age and hour with Claude
Quick overview This workflow pulls the last 30 days of Meta Ads insights across multiple breakdowns, calculates an account cost-per-result benchmark, flags high-waste delivery slices, and uses Anthropic Claude to rank a prioritized “kill list” with recommended actions. How it works Runs when triggered manually. Sets the analysis configuration, including the date preset, spend floor, cost-per-result multiple, minimum attribution threshold, and which Meta “action” events count as results. Queries the Meta Marketing API for account-level insights and breakdown insights (placement, region, age/gender, and hour), then computes the account cost-per-result benchmark and skips breakdowns with low conversion attribution coverage. Flags breakdown slices that exceed the spend floor and either have zero results or a cost-per-result above the benchmark threshold, then calculates “at risk” spend and keeps the top waste candidates. Sends the waste list and benchmark context to Anthropic Claude to rank the slices and return a recommended action (pause, exclude, or reallocate) with a one-line rationale. Prints a formatted wasted-spend report (and returns the parsed JSON ranking) for use in downstre
WFlag Meta ad creative fatigue with Facebook Graph API and send ranked reports to Slack
Quick overview This workflow runs every morning, pulls 14 days of daily ad-level insights from the Meta (Facebook Graph) API, detects creative fatigue by comparing yesterday’s CTR to each ad’s own historical average, and posts a ranked fatigue report to Slack via an incoming webhook. How it works Runs daily on a cron schedule (default 10:00). Loads configuration values such as the lookback window and fatigue thresholds. Retrieves daily ad-level insights from the Meta (Facebook Graph) API for the configured ad account, including CTR, spend, and impressions. Calculates each ad’s CTR drop by comparing yesterday’s CTR to that same ad’s average CTR across prior running days that meet minimum spend and impression thresholds, then labels ads as WARN/WATCH/OK/NEW and ranks the biggest drops. Sends a formatted, monospaced Slack message containing the ranked table and summary counts to your Slack channel using an incoming webhook. Setup Create or connect Facebook Graph API credentials with access to the target Meta ad account. Set environment variables for META_AD_ACCOUNT_ID (your act_… ID) and SLACK_WEBHOOK_URL (your Slack incoming webhook URL). Review and adjust the thresholds in the Confi