PROJECT MANAGEMENT

Linear Epic Acceptance-Criteria Drift Detector

Snapshots a Linear epic's acceptance criteria at kickoff, then on every edit diffs the live description against the baseline and posts a Slack alert when criteria were silently…

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerwebhook
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerLinear issue updated webhookLinearLinear
  • LogicFilter to locked epics with changed description
  • ActionFetch kickoff baseline criteriaPostgreSQLPostgres
  • LogicDiff current criteria vs baseline
  • OutputPost drift alert to SlackSlack

What it does

This workflow watches a Linear epic after it has been committed to and catches when its acceptance criteria quietly expand. It keeps a frozen baseline of the criteria captured at kickoff, and any time the epic description changes it compares the current criteria against that baseline. If lines were added, removed, or reworded, it posts a clear before/after diff to the squad's Slack channel so the change is seen and acknowledged rather than absorbed.

When to use it

Use it on committed-to epics where scope has been locked for a sprint or release. It is for teams who keep losing predictability because requirements grow inside the same ticket without anyone re-estimating.

How it works

  1. 1A Linear webhook fires when an issue is updated.
  2. 2A filter checks the issue is a kickoff-locked epic and that its description body actually changed.
  3. 3The stored baseline criteria for that epic are fetched from Postgres.
  4. 4The current acceptance-criteria block is extracted and diffed line-by-line against the baseline.
  5. 5If meaningful additions or edits are found, a formatted diff is sent to Slack tagging the epic lead and reviewers.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LinearIssues, projects, cycles, triage.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.