PROJECT MANAGEMENT

Turn blockers mentioned in Loom standups into tracked Linear issues

Reads each new Loom standup transcript, detects clearly stated blockers, and creates a Linear issue for any blocker that isn't already tracked.

CategoryProject Management
EngineSim + Paperclip
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew Loom standup video postedLoomLoom
  • ActionPull transcript and extract blocker + speakerOpenAI
  • ActionSearch Linear for an existing matching issueLinearLinear
  • LogicSkip if tracked, else create new issue
  • ActionCreate assigned, labeled Linear blocker issueLinearLinear
  • OutputNotify speaker in Slack with issue linkSlack

What it does

When someone posts a Loom standup, this workflow reads the transcript, identifies any blocker they describe, and checks whether a matching Linear issue already exists. If not, it files a new issue assigned to the speaker, labeled as a blocker for triage. Verbal blockers stop evaporating between standups.

When to use it

When blockers get spoken aloud in standup videos but rarely get logged, so they resurface day after day. Use it to guarantee every stated blocker becomes a trackable, owned work item.

How it works

  1. 1A new Loom video posted to the standup space triggers the run.
  2. 2The transcript is pulled and an agent extracts any blocker statements plus the speaker.
  3. 3Linear is searched for an existing open issue matching the blocker.
  4. 4Logic decides: skip if already tracked, otherwise proceed.
  5. 5A Linear issue is created, assigned to the speaker, and labeled 'blocker' for triage.
  6. 6The speaker is notified in Slack with a link to the new issue.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LoomVideo transcripts, libraries.
  2. 2
    Connect LinearIssues, projects, cycles, triage.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect OpenAIModels, embeddings, files.
  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.