AI AGENTS
Split oversized Linear epics into estimated child issues
An agent scans newly created Linear epics, breaks each one above a size threshold into discrete child issues with point estimates and acceptance criteria.
How it runs
The automated pipeline, trigger to output.
- TriggerLinear epic created or updatedLinear
- LogicSkip if epic already groomed
- ActionOpenAI decomposes epic into child issuesOpenAI
- LogicValidate breakdown and estimates
- ActionCreate estimated child issues under epicLinear
What it does
When a Linear epic crosses a size threshold (too many points, no children, or a long description), an agent decomposes it into 4-8 concrete child issues. Each child gets a title, a short scope, acceptance criteria, and a story-point estimate, and is linked under the original epic so the team can plan immediately.
When to use it
Use when product or engineering leads keep filing large "do the whole feature" epics that sit ungroomed until sprint planning. This does the first-pass breakdown so refinement meetings start from real, estimated tickets instead of a blank epic.
How it works
- 1A Linear webhook fires whenever an issue labeled `epic` is created or updated.
- 2A logic step checks the epic against thresholds (estimate, child count, description length) and exits if it is already groomed.
- 3The epic title and description are sent to an OpenAI model that returns a structured list of child issues with estimates and acceptance criteria.
- 4A logic step validates the breakdown (no duplicates, total points sane).
- 5Each child issue is created in Linear, parented to the epic, with labels and estimates applied.
Set it up
What you configure once, before turning it on.
- 1Connect LinearIssues, projects, cycles, triage.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Observability Cost Allocation Report
Monthly, an agent pulls Datadog and Honeycomb usage, allocates spend to teams and services by tags, writes the breakdown to Snowflake, and posts a chargeback summary to Slack.
Vendor Shortlist Matrix from a Buying Brief
An agent reads a buying brief, researches candidate vendors across the live web, and builds a scored comparison matrix in Coda ranking each vendor against your stated criteria.
Datadog Bill Spike Attribution Agent
When a daily Datadog cost check detects a spend jump, an agent attributes the increase to the specific services and metric types driving it and posts a ranked breakdown to Slack.
Buying Brief Email to Shortlist Doc in Drive
When a buying brief arrives by email, an agent researches the market and produces a polished narrative shortlist document in Google Drive, then replies to the sender with the link.
Zoom Demo Low-Score Objection Escalation to Manager
Scores how well a rep handled objections in each Zoom demo, and only when the handling score falls below a threshold does it create a coaching task in ClickUp and alert the rep's…
Weekly Vendor Watch and Shortlist Refresh
On a weekly schedule, an agent re-researches every vendor on an existing shortlist, flags pricing or capability changes since last run, and posts a change digest to Slack.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.