SUMMARIZATION

Turn Loom standup action items into Linear issues

Transcribes each new Loom standup video, extracts concrete action items and their owners with AI, and creates matching Linear issues while posting the brief summary to the team.

CategorySummarization
EngineSim + Paperclip
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew Loom standup video postedLoomLoom
  • ActionFetch video transcriptLoomLoom
  • ActionExtract action items with ownersOpenAI
  • LogicDedupe against open issues
  • ActionCreate Linear issue per action itemLinearLinear
  • OutputPost created-issues summary to SlackSlack

What it does

This workflow listens for new Loom standups, reads the transcript, and pulls out the actual commitments people make on camera. For each clear action item it creates a Linear issue assigned to the named owner, so spoken promises become tracked work instead of evaporating after the video ends. It also drops a short written summary so the team has context.

When to use it

Use this when your standups generate real follow-ups ("I'll fix the deploy script," "I'll review the PR") that nobody captures in your tracker. It closes the gap between talking about work and tracking it.

How it works

  1. 1A new Loom standup video triggers the run.
  2. 2The transcript is fetched from Loom.
  3. 3OpenAI extracts discrete action items, each with an owner and one-line description, and filters out vague statements.
  4. 4A logic step deduplicates against open issues so repeated mentions don't create duplicates.
  5. 5A Linear issue is created for each new action item, assigned to its owner.
  6. 6A summary of created issues is posted to the team channel.

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 LinearIssues, projects, cycles, triage.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  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.