CONTENT CREATION

Weekly digest of Loom recordings turned into ReadMe article drafts

On a weekly schedule, gather all Loom recordings made that week, draft a ReadMe help article for each, and send a single review digest summarizing what was created.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires
  • ActionList week's Loom recordings and transcriptsLoomLoom
  • ActionLLM drafts a chaptered article per recordingOpenAI
  • LogicFilter out recordings already documented
  • ActionCreate unpublished ReadMe draft for eachReadMeReadMe
  • OutputEmail consolidated review digestGmailGmail

What it does

Runs once a week, collects every Loom recording captured in the past seven days, and batch-converts each transcript into a chaptered ReadMe draft. Instead of pinging the team per video, it sends one consolidated digest listing every new draft with links.

When to use it

For teams that record frequently and want documentation processed in a predictable weekly batch rather than reacting to each recording. Keeps the docs review queue tidy and the team's inbox quiet.

How it works

  1. 1A weekly schedule triggers the workflow.
  2. 2List all Loom recordings created in the trailing seven-day window and fetch their transcripts.
  3. 3For each recording, an LLM produces a chaptered help-article draft from the transcript.
  4. 4A filter drops recordings already linked to an existing ReadMe page to avoid duplicates.
  5. 5Create one unpublished ReadMe draft per remaining recording.
  6. 6Compile a digest of all new drafts and email it to the docs reviewer via Gmail.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LoomVideo transcripts, libraries.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect ReadMeAPI docs, changelog, auth.
  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.