PROJECT MANAGEMENT

Scope-creep approval gate: agent investigates and proposes a re-baseline

On demand for a given Linear epic, an agent gathers the added issues since kickoff, drafts a re-baseline proposal with a revised target date.

CategoryProject Management
Enginepaperclip
Difficultyadvanced
Triggermanual
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerManual run with a target epic ID
  • ActionFetch current issues and baseline from LinearLinearLinear
  • LogicDiff added issues and estimate schedule impact
  • ActionSend re-baseline proposal to lead with approve/reject in SlackSlack
  • LogicBranch on the lead's decision
  • OutputApply new target date and note to the Linear epicLinearLinear

What it does

Turns a scope-creep flag into an actionable decision. For a specified epic, an agent diffs the current child issues against the kickoff baseline, identifies which issues were added after kickoff, estimates schedule impact, and drafts a re-baseline proposal with a suggested new target date. It sends that to the lead in Slack as an interactive approval. On approval, it writes the new target date and a re-baseline note back to the Linear epic.

When to use it

Use it when a creep alert has fired and you want a structured, auditable re-baseline rather than an ad hoc Slack thread. Best for epics where the target date is a real external commitment.

How it works

  1. 1A manual trigger supplies the epic ID.
  2. 2The agent fetches current issues and the kickoff baseline from Linear.
  3. 3It isolates issues added after kickoff and reasons about schedule impact.
  4. 4A re-baseline proposal with a revised target date is drafted.
  5. 5Slack sends the proposal to the lead with approve and reject actions.
  6. 6On approval, Linear is updated with the new target date and a re-baseline comment.

Set it up

What you configure once, before turning it on.

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