PROJECT MANAGEMENT

Linear epic scope-creep detector with re-baseline draft to lead

Daily check that compares each active Linear epic's current child-issue point total against the baseline captured at kickoff.

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule fires the scope check
  • ActionFetch active epics and child issues from LinearLinearLinear
  • LogicSum current points and compare to kickoff baseline
  • LogicKeep only epics that grew past the threshold
  • ActionDraft re-baseline summary with OpenAIOpenAI
  • OutputDM the draft to the epic lead in SlackSlack

What it does

Scans your active Linear epics once a day, sums the story points of every child issue, and compares that total to the baseline point count stored from kickoff. When an epic has grown beyond your configured percentage (for example 20%), it drafts a plain-language re-baseline summary and sends it to the epic's lead in Slack so a conversation happens before the slip becomes a surprise.

When to use it

Use it when teams quietly add issues to epics mid-flight and the original commitment date silently becomes fiction. Good for delivery leads and EMs who want an early signal instead of a retro post-mortem.

How it works

  1. 1A daily schedule fires the workflow.
  2. 2Linear is queried for all epics in active states and their child issues.
  3. 3Each epic's current point total is summed and compared to its stored kickoff baseline.
  4. 4A filter keeps only epics whose growth exceeds the threshold.
  5. 5OpenAI drafts a short re-baseline summary: original vs current points, top added issues, and a suggested new target.
  6. 6Slack delivers the draft as a direct message to the epic lead.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LinearIssues, projects, cycles, triage.
  2. 2
    Connect OpenAIModels, embeddings, files.
  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.