CONTENT CREATION

Agent-built research-backed explainer series from a blog topic

A CEO-driven agent takes a blog post, fact-checks and enriches it with live web research, drafts a multi-clip explainer script series, narrates each part in two languages.

CategoryContent Creation
Enginepaperclip
Difficultyadvanced
Triggermanual
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerAgent tasked with a flagship blog post
  • ActionVerify claims and gather fresh statsPerplexityPerplexity
  • LogicPlan and split into a sequence of episodes
  • ActionNarrate each episode in two languagesElevenLabsElevenLabs
  • ActionRender each episode clipReplicateReplicate
  • OutputAssemble playlist and publish to platformsSocial publishing

What it does

Uses an agent to turn one in-depth blog post into a researched, multi-part explainer series rather than a single clip, narrated in two languages and published as a playlist.

When to use it

Use it for flagship or evergreen articles that deserve a structured video series with current, verified supporting facts — not just a quick read-aloud.

How it works

  1. 1The agent is tasked with a blog post selected for the series treatment.
  2. 2It reads the post and runs Perplexity research to verify claims and pull fresh supporting stats.
  3. 3It plans the series, splitting the material into a logical sequence of short episodes with its own judgment on pacing.
  4. 4For each episode it writes a script in two languages.
  5. 5ElevenLabs narrates every episode and language variant.
  6. 6Replicate renders each episode clip.
  7. 7The agent assembles the clips into a playlist and publishes it across social platforms, then reports the links.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PerplexitySearch-grounded answers with citations.
  2. 2
    Connect ElevenLabsText-to-speech, voice cloning.
  3. 3
    Connect ReplicateImage, video, and model inference.
  4. 4
    Connect Social publishingCross-post to X, LinkedIn, Instagram, TikTok, and 4 more in one call.
  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.