agent hive

PROJECT MANAGEMENT

AI Semantic Scope-Expansion Reviewer for Epics

On a Linear epic edit, an AI agent compares the new acceptance criteria against the kickoff baseline to judge whether the change is true scope expansion versus a clarification.

CategoryProject Management
EngineSim + Paperclip
Difficultyadvanced
Triggerwebhook
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerLinear epic updated webhookLinearLinear
  • LogicFilter locked epics with changed description
  • ActionLoad kickoff baseline from PostgresPostgreSQLPostgres
  • ActionAI classifies expansion vs clarificationOpenAI
  • ActionAppend verdict to Notion scope recordNotionNotion
  • OutputAlert Slack on confirmed expansionSlack

What it does

Text diffs flag every wording tweak, but not every edit is real scope creep. This workflow uses an AI agent to read the kickoff baseline and the current acceptance criteria and decide whether the change adds genuinely new deliverables or merely clarifies existing ones. It writes a structured verdict with reasoning to Notion for the audit trail, and pings Slack only when the change represents true expansion, cutting false alarms.

When to use it

Use it when literal line diffs produce too much noise and you want judgment about intent. It suits mature teams who reword criteria often and need signal, not every punctuation change.

How it works

  1. 1A Linear webhook fires when an epic is updated.
  2. 2A filter passes locked epics whose description changed.
  3. 3The kickoff baseline is loaded from Postgres.
  4. 4An AI agent compares baseline and current criteria and classifies the change as expansion, clarification, or reduction with reasoning.
  5. 5The verdict and rationale are appended to the epic's Notion scope record.
  6. 6A branch routes only confirmed expansions to a Slack alert tagging the lead.

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 OpenAIModels, embeddings, files.
  4. 4
    Connect NotionPages, databases, comments.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.