CONTENT CREATION

Agent-run docs pipeline: triage a Loom recording and route it to the right destination

On a new Loom recording, an agent reads the transcript, decides whether it is a public help article, an internal runbook, or a bug repro, and routes a drafted version to ReadMe.

CategoryContent Creation
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew Loom recording processedLoomLoom
  • ActionAgent fetches transcript and timestampsLoomLoom
  • LogicAgent classifies intent and chooses destination
  • ActionDraft and route to ReadMe, Confluence, or LinearReadMeReadMe
  • OutputPost routing summary to SlackSlack

What it does

Uses an agent to interpret each new Loom recording rather than forcing one fixed output. The agent reads the transcript, classifies the recording's intent, drafts the appropriate document, and sends it to the matching system: customer-facing how-tos go to ReadMe, internal procedures to Confluence, and anything describing a defect becomes a Linear issue with the repro steps and Loom link.

When to use it

For orgs where recordings serve mixed purposes and you don't want a separate workflow per outcome. Let the agent decide where each video belongs and produce the right artifact.

How it works

  1. 1A new Loom recording fires the trigger.
  2. 2The agent fetches the transcript and chapter timestamps from Loom.
  3. 3The agent classifies intent: public help article, internal runbook, or bug report.
  4. 4Based on the decision, it drafts the correctly formatted document for that destination.
  5. 5It routes the output, creating a ReadMe draft, a Confluence page, or a Linear issue.
  6. 6It posts a summary of what it created and why to Slack for oversight.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LoomVideo transcripts, libraries.
  2. 2
    Connect ReadMeAPI docs, changelog, auth.
  3. 3
    Connect ConfluenceSpaces, pages, blueprints.
  4. 4
    Connect LinearIssues, projects, cycles, triage.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.