CONTENT CREATION

Agent that drafts, fact-checks, and routes segment newsletters for human approval

An agent takes a published blog post, drafts tone-matched newsletters per segment, verifies claims against the source, posts drafts to Slack for approval.

CategoryContent Creation
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNotion post publishedNotionNotion
  • ActionAgent drafts tone-matched editions per segmentOpenAI
  • LogicSelf-fact-check claims against source, flag gaps
  • ActionPost drafts to Slack approval channelSlack
  • OutputSend approved editions to segments via GmailGmailGmail

What it does

Runs an agent-driven newsletter pipeline with a human checkpoint. The agent reads the source post, produces a tone-adapted edition for each segment, checks that every claim traces back to the original, and routes drafts to Slack so an editor approves before anything ships.

When to use it

Use it when newsletter accuracy and brand voice matter enough to require sign-off, but you still want the agent doing the heavy drafting and self-checking. Good for regulated or high-trust audiences where a bad send is costly.

How it works

  1. 1A published Notion post triggers the agent.
  2. 2The agent reads the post and the segment definitions from Notion.
  3. 3It drafts a tone-matched edition per segment and runs a self-fact-check, flagging any claim it can't ground in the source.
  4. 4Drafts post to a Slack approval channel with inline flags; an editor approves or rejects each.
  5. 5Approved editions send to their segments via Gmail; rejected ones return to the agent with the editor's notes for a revision pass.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect NotionPages, databases, comments.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect GmailRead, draft, send, label.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.