AI AGENTS
Split oversized Linear stories from thin acceptance criteria
An agent scans your Linear backlog nightly, flags stories whose acceptance criteria are too thin to justify their estimate.
How it runs
The automated pipeline, trigger to output.
- TriggerNightly schedule fires grooming run
- ActionFetch backlog issues estimated 5+ pointsLinear
- ActionScore acceptance-criteria completeness and scopeOpenAI
- LogicKeep only large AND thin-criteria stories
- ActionDraft and create right-sized child issuesLinear
- OutputPost split summary to Slack for approvalSlack
What it does
This agent grooms your Linear backlog by finding stories that are estimated large (5+ points) but carry vague or missing acceptance criteria — a classic sign the work is actually several stories hiding in one. It proposes a split into smaller child issues, each with concrete, testable criteria, and links them back to the parent.
When to use it
Run it on teams that estimate in points and let stories drift to the backlog without refinement. It is most useful the night before sprint planning, so the team walks into refinement with oversized items already decomposed instead of arguing about them live.
How it works
- 1A nightly schedule fires the grooming run.
- 2The agent queries Linear for backlog issues at 5+ points.
- 3An LLM reads each issue's description and acceptance criteria and scores criteria completeness and scope coherence.
- 4A logic step keeps only issues that are both large and thin.
- 5For each survivor, the agent drafts 2-4 child issues with discrete acceptance criteria.
- 6It creates the child issues in Linear, links them to the parent, and marks the parent as an epic.
- 7A Slack summary lists every split for the lead to approve.
Set it up
What you configure once, before turning it on.
- 1Connect LinearIssues, projects, cycles, triage.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
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.