PROJECT MANAGEMENT

Turn GitHub Blocking Comments into Tracked Cross-Team Promises

When a reviewer comments that a PR is blocked waiting on another team, the flow registers a tracked dependency in Linear and notifies the team that owes the unblock.

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerwebhook
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew GitHub PR review commentGitHubGitHub
  • LogicLLM detects cross-team blocker and owning teamOpenAI
  • LogicFilter out non-blocker comments
  • ActionCreate Linear dependency issue linked to the PRLinearLinear
  • OutputNotify owning team in SlackSlack

What it does

Listens for new GitHub PR review comments and detects when one team is blocked waiting on another ("can't merge until the platform team ships the auth endpoint"). It creates a Linear issue capturing the blocking relationship, assigns it to the owning team, sets a due date if the comment names one, and posts the blocker to that team's Slack channel.

When to use it

When engineering handoffs that surface in code review never make it onto anyone's board, so PRs sit stale waiting on a dependency no one is tracking. Best for orgs where cross-team blockers regularly appear in review threads.

How it works

  1. 1A GitHub webhook fires on a new PR review comment.
  2. 2An LLM classifies whether the comment describes a cross-team blocker and extracts the owing team and any named date.
  3. 3Non-blocker comments are filtered out.
  4. 4A Linear issue is created describing the blocker, assigned to the owning team with a due date and link to the PR.
  5. 5The blocker is posted to the owning team's Slack channel with the PR and issue links.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GitHubRepos, issues, pull requests, actions.
  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.