PROJECT MANAGEMENT

Reconcile Loom standup videos against Linear board movement to surface silent blockers

Each morning, collects the team's Loom async-standup videos, reads their transcripts, and cross-checks who said they were blocked against which Linear issues actually moved.

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

How it runs

The automated pipeline, trigger to output.

  • TriggerMorning schedule fires after standup window
  • ActionFetch last 24h Loom standup videos + transcriptsLoomLoom
  • ActionExtract per-person status and blocker mentionsOpenAI
  • ActionPull each engineer's Linear issue state changesLinearLinear
  • LogicCompare spoken status vs board movement; tag silent blockers
  • OutputPost reconciled blocker digest to SlackSlack

What it does

Gathers the daily Loom standup videos from your team's workspace, pulls each transcript, and reconciles spoken updates against real Linear activity. It flags people who said "blocked" but whose issues never moved, and issues that sat untouched despite a verbal commitment. The result is a single Slack digest naming who is genuinely stuck.

When to use it

For distributed teams running async video standups where talk and board state drift apart. Use it when blockers get mentioned on Loom but never make it into the tracker, so they quietly stall.

How it works

  1. 1A morning schedule fires after the standup window closes.
  2. 2Loom returns the videos posted to the standup space in the last 24 hours, with transcripts.
  3. 3An agent extracts each person's claimed status and any blocker language from the transcript.
  4. 4Linear is queried for each engineer's issue state changes over the same window.
  5. 5Logic compares spoken status to board movement and tags mismatches as silent blockers.
  6. 6A formatted blocker digest is posted to the team Slack channel.

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.