PROJECT MANAGEMENT

Weekly scope-creep digest across all epics to Confluence and Slack

Every Monday, ranks all active Linear epics by percentage point growth since kickoff, publishes a portfolio scope-creep digest page in Confluence.

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly Monday schedule fires
  • ActionFetch all active epics and points from LinearLinearLinear
  • LogicCompute growth percentage per epic and rank
  • ActionGenerate digest narrative and table with OpenAIOpenAI
  • ActionPublish dated digest page to ConfluenceConfluenceConfluence
  • OutputPost top offenders to program Slack channelSlack

What it does

Builds a portfolio-level view of scope drift. Each Monday it pulls every active Linear epic, compares current points to the stored kickoff baseline, ranks epics by growth percentage, and publishes a single Confluence digest page. It then posts the worst three offenders to your program channel so leadership sees the trend without opening Linear.

When to use it

Use it when you manage many epics across squads and need one weekly artifact for staff or steering reviews, rather than per-epic pings. Pairs naturally with the baseline-capture workflow.

How it works

  1. 1A weekly Monday schedule triggers the digest.
  2. 2Linear returns all active epics and their child-issue points.
  3. 3Each epic is matched to its kickoff baseline and a growth percentage is calculated.
  4. 4Epics are sorted descending by growth and OpenAI writes a short narrative plus a ranked table.
  5. 5Confluence publishes the full digest as a dated page.
  6. 6Slack posts the top three offenders with a link to the Confluence page.

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 ConfluenceSpaces, pages, blueprints.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  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.