MARKETING

Detect CTR Decay by Ad Variant and Open Notion Refresh Briefs

Runs daily against BigQuery ad-performance data, flags ad variants whose click-through rate has decayed past a threshold versus their own 7-day peak.

CategoryMarketing
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule fires the fatigue scan
  • ActionQuery per-variant CTR (today + trailing 7 days) from BigQueryGoogle BigQueryBigQuery
  • LogicCompute decay vs. 7-day peak; keep variants past threshold with enough impressions
  • ActionCreate a pre-filled refresh brief in the Notion Creative database for each flagged variantNotionNotion
  • OutputRefresh briefs land in Notion for the creative team to actionNotionNotion

What it does

Every morning this workflow scans your paid-campaign performance table in BigQuery, compares each ad variant's current click-through rate against its rolling 7-day peak, and identifies the variants that have slipped below a decay threshold (for example, CTR down 25% or more from peak with enough impressions to be statistically meaningful). For each fatigued variant it opens a structured refresh brief in Notion so the creative team has a ready-to-action ticket instead of a raw number.

When to use it

Use this when you run always-on paid social or search campaigns and want to catch creative fatigue before wasted spend piles up. It replaces the manual habit of squinting at dashboards and pinging designers ad hoc.

How it works

  1. 1A daily schedule fires the run.
  2. 2BigQuery returns per-variant CTR for today and the trailing 7-day window.
  3. 3A decay-detection step computes the drop from each variant's peak and filters to variants past the threshold with sufficient impressions.
  4. 4For each flagged variant, a Notion page is created in the Creative Refresh database, pre-filled with the variant name, campaign, peak vs. current CTR, spend, and a suggested angle.
  5. 5The new brief is the delivered output the team picks up.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect NotionPages, databases, comments.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.