CONTENT CREATION

Nightly audit of this week's scheduled posts for unsourced claims

Every night, sweep all posts scheduled to publish in the next seven days, fact-check their claims against the web.

CategoryContent Creation
EngineSim + Paperclip
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNightly schedule fires
  • ActionQuery Notion for posts publishing in the next 7 daysNotionNotion
  • ActionVerify each post's uncited claims via PerplexityPerplexityPerplexity
  • LogicScore and rank posts by count of unsourced/contradicted claims
  • OutputSend a ranked risk digest to the editorial Slack channelSlack

What it does

This is a scheduled safety net that reviews your entire upcoming publishing queue in one pass. Each night it pulls every post slated to go live within the next week, checks the factual claims in each one, and produces a single ranked digest so an editor can triage the riskiest posts first thing in the morning.

When to use it

Use it when posts get scheduled days in advance and you want a recurring backstop rather than a per-post gate. It suits teams with a steady cadence who would rather review a morning summary than interrupt every writer.

How it works

  1. 1A nightly schedule triggers the run.
  2. 2The workflow queries the Notion content database for posts with a publish date inside the next seven days.
  3. 3For each post the agent extracts uncited claims and uses Perplexity to find and summarize supporting sources.
  4. 4A scoring step tallies unsourced and contradicted claims per post and sorts the queue by risk.
  5. 5A Slack digest lists each post with its risk score, the specific weak claims, and direct links so editors can fix the top offenders before they publish.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect NotionPages, databases, comments.
  2. 2
    Connect PerplexitySearch-grounded answers with citations.
  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.