Complete AI Training
Sign inGet started

AI agent for digital marketing managers

Evergreen Content Recycling Agent

Keep the calendar full with proven posts, without errors and without too much repetition.

DecisionsAutomationMarketing
See how it worksGet access
Evergreen Content Recycling Agent: what goes in, what the agent does and what you get

What it does

The team's best posts of the last two years sit in an archive while the calendar is being filled with new ideas under time pressure. The agent finds top posts by engagement and results per platform, and checks which ones are evergreen rather than tied to a date. For each candidate it checks accuracy, such as prices, features and statistics, and whether it still matches the brand voice and visuals. It adjusts the copy, suggests a new hook and picks repost slots with spacing, so that the same post does not appear twice within a set period. After the repost, it measures the result against the original and against the average. Reposts that perform badly are dropped from the pool. Edge case: a post featuring a person who has left the company. The manager approves each batch.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedYes, continueNoNo 1 STARTS WHEN Monthly recycling run 2 USES A TOOL Pull posts from the last 24 months with engagementresults 3 DOES Select the top 15 percent and remove date-boundposts 4 USES A TOOL Check facts, prices and people in each post 5 CHECKS THE RESULT Is every post accurate and on brand? If not: fix the text, or drop the post if it cannot befixed. Back to step 3. 6 DOES Rewrite the hook and choose repost slots withspacing 7 YOU APPROVE Manager approves each batch 8 USES A TOOL Schedule the approved reposts 9 USES A TOOL After posting, compare results with the original 10 CHECKS THE RESULT Did each repost reach 70 percent of the originalresult? If not: try a new hook once, then drop the post from thepool. Back to step 5. 11 RESULT Recycling log updated
Read the steps as a list
  1. Monthly recycling run
  2. Pull posts from the last 24 months with engagement results
  3. Select the top 15 percent and remove date-bound posts
  4. Check facts, prices and people in each post
  5. Is every post accurate and on brand?If not: fix the text, or drop the post if it cannot be fixed. Back to step 3.
  6. Rewrite the hook and choose repost slots with spacing
  7. Manager approves each batchThe agent waits here for your OK.
  8. Schedule the approved reposts
  9. After posting, compare results with the original
  10. Did each repost reach 70 percent of the original result?If not: try a new hook once, then drop the post from the pool. Back to step 5.
  11. Recycling log updated

How it decides

A post qualifies when it is in the top 15 percent of engagement and is not date-bound. A repost stays in the pool only if it reaches at least 70 percent of the original result.

  • Choose posts in the top 15 percent of engagement
  • Skip posts tied to a date, event or person who has left
  • Space repeated posts at least 60 days apart
  • Drop a post after two weak reposts

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Engagement percentile (default 15)
  • Minimum spacing (default 60 days)
  • Platforms
  • Success rate (default 70 percent)
  • Batch size

What keeps you in control

It always asks you first

  • Manager approves each batch
  • Manager approves changes to brand wording

Hard limits

  • Never repost without approval
  • Do not reuse content with expired claims

It stops when

  • Done: batch scheduled and measured
  • Stop: product facts have changed widely, pause and ask the manager

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensThe agent selects 22 top posts. Five are date-bound and two feature a former colleague. For the remaining 15, it finds one quoting a 12 percent customer stat from 2022, which it replaces with the current 17. After approval, 12 reposts go out over 6 weeks. Nine reach 70 percent or more of their original result, and 3 are retried with new hooks.

More agents for digital marketing managers

Quality control · Marketing

Campaign Landing-Page Consistency Agent

Every ad promise is supported by its landing page, with working links and forms.

7 steps2 checks7 jobs Communication · Marketing

Webinar Follow-up Segmentation Agent

Relevant, consent-respecting follow-ups for every attendee.

8 steps2 checks14 jobs Monitoring · Analysis

Campaign Budget Pacing Diagnosis Agent

Pacing alerts that reflect real spend, not data delays.

8 steps1 check7 jobs Creating · Marketing

Marketing Newsletter Assembly Agent

A fresh, relevant newsletter draft every cycle.

8 steps2 checks9 jobs