MARKETING

CEO agent triages fatigued creatives and assigns refresh tasks in Linear

An agent reviews each morning's fatigued-creative report, decides whether to refresh, retire, or hold each one based on spend and trend.

CategoryMarketing
Enginepaperclip
Difficultyadvanced
Triggerschedule
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule starts the triage run
  • ActionPull fatigued creatives with spend and trend from BigQueryGoogle BigQueryBigQuery
  • LogicAgent decides refresh, retire, or hold per creative with rationale
  • ActionCreate prioritized refresh tasks in LinearLinearLinear
  • OutputSummarize triage decisions in SlackSlack

What it does

This workflow hands the fatigue report to an agent that makes a judgment call per creative rather than applying a single fixed rule. For each declining creative the agent weighs spend, decay speed, and remaining headroom to decide refresh, retire, or hold, then files a prioritized Linear task for anything worth acting on, with a short rationale attached.

When to use it

Use it when a blunt threshold produces too much noise and you want triage that accounts for context, like sparing a high-spend evergreen creative that dipped briefly while flagging a fast-collapsing one. Best for teams that want explained decisions, not just alerts.

How it works

A daily schedule kicks off the run. A BigQuery action pulls the fatigued-creative set with spend and trend metrics. The agent reasons over each creative and assigns a recommended action and priority with a one-line justification. A logic step routes only refresh and retire decisions forward. A Linear action creates a prioritized task per actionable creative including the agent's rationale. A Slack output summarizes the triage outcome and counts by decision.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect LinearIssues, projects, cycles, triage.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.